Review your MCP server from your own scripts
Send MCP server source — TypeScript SDK, Python FastMCP or plain tool-definition JSON, one file or several concatenated — and get back one JSON object: a readiness posture, the inventory of every tool with its inputs and role, prioritized findings across tool design, schemas, errors, pagination, protocol, security, docs and hygiene, each with a corrected fragment, quick wins, and the focus areas to work through first. Everything this app does goes through the SkillSafe App API — plain JSON over HTTPS — so you can hang a review off a pull request that touches your server, a release about to be published to a registry, or a pre-merge gate. Every code step below is shown in cURL, Python, JavaScript, Go, Java, Ruby, PHP and C#; pick a language once and the whole page follows.
Basics
Base URL: https://api.skillsafe.ai/v1/app-api, app slug
mcp-clinic. Every request sends
Authorization: Bearer <token> and JSON bodies with
Content-Type: application/json. Responses are wrapped in an envelope:
{"data": …} on success, {"error": {"code", "message"}} on failure.
The review itself is produced by the gpt-terra model. Estimates are free;
runs are metered against your credit balance. There is a single run task — one server
in, one review out, no follow-up calls and no session state to carry.
| Status | Meaning |
|---|---|
401 | Missing or expired token — create a new session. |
402 | Not enough credits — top up at skillsafe.ai/account/credits. |
403 | The token isn't allowed to do this (e.g. a guest reviewing a very large bundle). |
404 | Unknown job or record id. |
5xx | Transient platform error — retry with backoff. |
Browsers enforce CORS for this API, so run these examples from a server, script or terminal — not from another website's frontend.
Step 0 — A tiny client
Every task below is a single HTTP call, so start with a short helper that adds the auth
header, sends JSON and unwraps the data envelope. The later steps reuse it.
export API="https://api.skillsafe.ai/v1/app-api"
export TOKEN="YOUR_TOKEN" # see step 1
# every call looks like:
# curl -s "$API/..." -H "Authorization: Bearer $TOKEN" [-d '{json}']
# jq is used below to pull fields out of the {"data": ...} envelope
import json, requests
API = "https://api.skillsafe.ai/v1/app-api"
TOKEN = "YOUR_TOKEN" # see step 1 — read it from your shell environment in real code
def api(method, path, body=None, **headers):
res = requests.request(method, API + path, json=body,
headers={"Authorization": f"Bearer {TOKEN}", **headers})
payload = res.json()
if not res.ok:
raise RuntimeError(payload.get("error", {}).get("message", res.reason))
return payload["data"]
// Node 18+ (built-in fetch)
const API = "https://api.skillsafe.ai/v1/app-api";
const TOKEN = "YOUR_TOKEN"; // see step 1 — read it from your shell environment in real code
async function api(method, path, body, extraHeaders = {}) {
const res = await fetch(API + path, {
method,
headers: { Authorization: `Bearer ${TOKEN}`, "Content-Type": "application/json", ...extraHeaders },
body: body === undefined ? undefined : JSON.stringify(body),
});
const json = await res.json();
if (!res.ok) throw new Error(json.error?.message ?? res.statusText);
return json.data;
}
package main
import (
"bytes"
"encoding/json"
"fmt"
"net/http"
"os"
)
const API = "https://api.skillsafe.ai/v1/app-api"
var token = os.Getenv("SKILLSAFE_TOKEN") // see step 1
func call(method, path string, body, out any) error {
var buf bytes.Buffer
if body != nil {
json.NewEncoder(&buf).Encode(body)
}
req, _ := http.NewRequest(method, API+path, &buf)
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)
if err != nil {
return err
}
defer res.Body.Close()
var env struct {
Data json.RawMessage `json:"data"`
Error *struct{ Message string `json:"message"` } `json:"error"`
}
json.NewDecoder(res.Body).Decode(&env)
if res.StatusCode >= 400 {
return fmt.Errorf("api %s %s: %s", method, path, env.Error.Message)
}
if out == nil {
return nil
}
return json.Unmarshal(env.Data, out)
}
// Java 17+, no dependencies. Pair with your JSON library (Jackson, Gson…)
// to read fields out of the returned envelope.
import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
public class SkillSafe {
static final String API = "https://api.skillsafe.ai/v1/app-api";
static final String TOKEN = System.getenv("SKILLSAFE_TOKEN"); // see step 1
static final HttpClient HTTP = HttpClient.newHttpClient();
static String api(String method, String path, String jsonBody) throws Exception {
var req = HttpRequest.newBuilder(URI.create(API + path))
.header("Authorization", "Bearer " + TOKEN)
.header("Content-Type", "application/json")
.method(method, jsonBody == null
? HttpRequest.BodyPublishers.noBody()
: HttpRequest.BodyPublishers.ofString(jsonBody))
.build();
var res = HTTP.send(req, HttpResponse.BodyHandlers.ofString());
if (res.statusCode() >= 400) throw new RuntimeException(res.body());
return res.body(); // envelope: {"data": …}
}
}
require "net/http"
require "json"
API = "https://api.skillsafe.ai/v1/app-api"
TOKEN = ENV.fetch("SKILLSAFE_TOKEN") # see step 1
def api(method, path, body = nil)
uri = URI(API + path)
req = Net::HTTP.const_get(method.capitalize).new(uri)
req["Authorization"] = "Bearer #{TOKEN}"
req["Content-Type"] = "application/json"
req.body = body.to_json if body
res = Net::HTTP.start(uri.host, uri.port, use_ssl: true) { |h| h.request(req) }
payload = JSON.parse(res.body)
raise (payload.dig("error", "message") || res.message) unless res.is_a?(Net::HTTPSuccess)
payload["data"]
end
<?php
const API = "https://api.skillsafe.ai/v1/app-api";
$TOKEN = getenv("SKILLSAFE_TOKEN"); // see step 1
function api(string $method, string $path, ?array $body = null): mixed {
global $TOKEN;
$ch = curl_init(API . $path);
curl_setopt_array($ch, [
CURLOPT_CUSTOMREQUEST => $method,
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer $TOKEN",
"Content-Type: application/json",
],
CURLOPT_POSTFIELDS => $body === null ? null : json_encode($body),
]);
$payload = json_decode(curl_exec($ch), true);
$status = curl_getinfo($ch, CURLINFO_RESPONSE_CODE);
curl_close($ch);
if ($status >= 400) {
throw new Exception($payload["error"]["message"] ?? "HTTP $status");
}
return $payload["data"];
}
// .NET 8+
using System.Net.Http.Json;
using System.Text.Json;
static class SkillSafe
{
const string Api = "https://api.skillsafe.ai/v1/app-api";
static readonly HttpClient Http = new();
static SkillSafe() =>
Http.DefaultRequestHeaders.Authorization =
new("Bearer", Environment.GetEnvironmentVariable("SKILLSAFE_TOKEN")); // see step 1
public static async Task<JsonElement> ApiAsync(HttpMethod method, string path, object? body = null)
{
var req = new HttpRequestMessage(method, Api + path);
if (body != null) req.Content = JsonContent.Create(body);
var res = await Http.SendAsync(req);
var json = await res.Content.ReadFromJsonAsync<JsonElement>();
if (!res.IsSuccessStatusCode)
throw new Exception(json.GetProperty("error").GetProperty("message").GetString());
return json.GetProperty("data");
}
}
Step 1 — Get a token
A guest token lets you check balances and estimate costs for free. For metered review runs
billed to your own account, use your personal token: open the
token page, sign in with SkillSafe, and press
Copy shell export — it puts export SKILLSAFE_TOKEN="…" on your
clipboard, which every example below reads. Treat the token like a password: it can spend
your credits. For fully headless scripts, POST /guest mints a guest token with
no browser involved.
curl -s -X POST "$API/guest" \
-H "Content-Type: application/json" \
-d '{"slug":"mcp-clinic"}' | jq -r '.data.token'
token = api("POST", "/guest", {"slug": "mcp-clinic"})["token"]
const { token } = await api("POST", "/guest", { slug: "mcp-clinic" });
var guest struct{ Token string `json:"token"` }
err := call("POST", "/guest", map[string]string{"slug": "mcp-clinic"}, &guest)
String envelope = api("POST", "/guest", """
{"slug":"mcp-clinic"}""");
// token is at data.token in the returned JSON
token = api("POST", "/guest", { slug: "mcp-clinic" })["token"]
$token = api("POST", "/guest", ["slug" => "mcp-clinic"])["token"];
var guest = await SkillSafe.ApiAsync(HttpMethod.Post, "/guest",
new { slug = "mcp-clinic" });
var token = guest.GetProperty("token").GetString();
The app stores this browser's token under the localStorage key
skillsafe_app_token:mcp-clinic, on the app's own origin. The
token page reads and manages it for you — you never need
to open developer tools.
Step 2 — Check who you are and your balance
Returns subject_type ("user" or "guest"),
subject_id and your credits balance. Check this before reviewing a
large bundle.
curl -s "$API/me" -H "Authorization: Bearer $TOKEN" | jq '.data'
me = api("GET", "/me")
print(me["subject_type"], me["credits"])
const me = await api("GET", "/me");
console.log(me.subject_type, me.credits);
var me struct {
SubjectType string `json:"subject_type"`
Credits int64 `json:"credits"`
}
err := call("GET", "/me", nil, &me)
String envelope = api("GET", "/me", null);
// data.subject_type, data.credits
me = api("GET", "/me")
puts "#{me["subject_type"]}: #{me["credits"]} credits"
$me = api("GET", "/me");
echo "{$me['subject_type']}: {$me['credits']} credits\n";
var me = await SkillSafe.ApiAsync(HttpMethod.Get, "/me");
Console.WriteLine($"{me.GetProperty("subject_type")}: {me.GetProperty("credits")} credits");
Step 3 — Estimate the cost
Send exactly the input you would send to /run; the response's
hold_credits is the worst-case cost. Nothing is charged and no job is created,
so estimating is free — useful when you are piping a whole kustomize build
in and want a ceiling before spending credits.
| Input field | Type | Notes |
|---|---|---|
code | string, required | The MCP server source or tool-definition JSON, exactly as it sits on disk. One file or several concatenated — a // filename comment line between them helps the reviewer name things. This is the model's only evidence — nothing is fetched or executed. Pastes longer than 100,000 characters are clipped middle-out, with a [... clipped ...] comment showing where. At least 60 characters are needed for a review. |
language | string | typescript | python | json | unknown — what the paste is written in. If the code itself clearly shows the language, the code wins. |
concern | string | general | tool-design | schemas | errors | security — the review emphasis. It weights the findings and the summary, but it is emphasis and not exclusivity: a high-severity finding from another category is never suppressed. |
context | string, optional | Extra context: what service the server wraps, which clients call it (Claude Desktop, an agent framework, your own), the transport it deploys on, how auth is provisioned, and any gap you have already chosen to accept. Clipped at 20,000 characters. |
prescan_facts | object, optional | What a client-side scanner mechanically matched in the code: {"tools": [], "flags": []}. Each entry is {id, label}. Tool ids look like tool:listtickets; flag ids are <check>:<name> — secret-literal:file, no-description:listtickets, no-schema:create_ticket, any-type:create_ticket, generic-error:create_ticket, swallowed-error:create_ticket, no-pagination:search, no-annotations:set, stdio-print:file, sse-transport:file, mixed-naming:set, no-prefix:set. Every flag id you send comes back in coverage_check. The web UI fills this from its own scan; API callers may omit the field or send the two empty arrays. |
retry_note | string, optional | Only set by the app's automatic reformat retry when a first reply was not valid JSON. Leave it out. |
cat > server.ts <<'SRC'
server.tool("listTickets", async () => {
const res = await fetch(BASE + "/tickets");
return { content: [{ type: "text", text: await res.text() }] };
});
server.tool("create_ticket", { payload: z.any() }, async (args) => {
if (!args.payload) throw new Error("error");
});
SRC
jq -n --rawfile code server.ts \
'{code: $code,
language: "typescript",
concern: "general",
context: "Internal ticketing server for Claude Desktop, stdio transport, first draft.",
prescan_facts: {tools: [], flags: []}}' > input.json
curl -s -X POST "$API/estimate" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-d @input.json | jq '.data.hold_credits'
CODE = """server.tool("listTickets", async () => {
const res = await fetch(BASE + "/tickets");
return { content: [{ type: "text", text: await res.text() }] };
});
server.tool("create_ticket", { payload: z.any() }, async (args) => {
if (!args.payload) throw new Error("error");
});
"""
payload = {
"code": CODE,
"language": "typescript",
"concern": "general",
"context": "Internal ticketing server for Claude Desktop, stdio transport, first draft.",
"prescan_facts": {"tools": [], "flags": []},
}
est = api("POST", "/estimate", payload)
print("worst case:", est.get("hold_credits", est.get("credits")), "credits")
const code = `server.tool("listTickets", async () => {
const res = await fetch(BASE + "/tickets");
return { content: [{ type: "text", text: await res.text() }] };
});
server.tool("create_ticket", { payload: z.any() }, async (args) => {
if (!args.payload) throw new Error("error");
});
`;
const payload = {
code,
language: "typescript",
concern: "general",
context: "Internal ticketing server for Claude Desktop, stdio transport, first draft.",
prescan_facts: { tools: [], flags: [] },
};
const est = await api("POST", "/estimate", payload);
console.log("worst case:", est.hold_credits ?? est.credits, "credits");
const code = `server.tool("listTickets", async () => {
const res = await fetch(BASE + "/tickets");
return { content: [{ type: "text", text: await res.text() }] };
});
server.tool("create_ticket", { payload: z.any() }, async (args) => {
if (!args.payload) throw new Error("error");
});
`
payload := map[string]any{
"code": code,
"language": "typescript",
"concern": "general",
"context": "Internal ticketing server for Claude Desktop, stdio transport, first draft.",
"prescan_facts": map[string]any{
"tools": []any{}, "flags": []any{},
},
}
var est struct{ HoldCredits int64 `json:"hold_credits"` }
err := call("POST", "/estimate", payload, &est)
String code = """
server.tool("listTickets", async () => {
const res = await fetch(BASE + "/tickets");
return { content: [{ type: "text", text: await res.text() }] };
});
server.tool("create_ticket", { payload: z.any() }, async (args) => {
if (!args.payload) throw new Error("error");
});
""";
String jsonPayload = """
{"code": %s,
"language": "typescript",
"concern": "general",
"context": "Internal ticketing server for Claude Desktop, stdio transport, first draft.",
"prescan_facts": {"tools": [], "flags": []}}
""".formatted(toJsonString(code));
String envelope = api("POST", "/estimate", jsonPayload);
// worst-case cost is at data.hold_credits
CODE = <<~SRC
server.tool("listTickets", async () => {
const res = await fetch(BASE + "/tickets");
return { content: [{ type: "text", text: await res.text() }] };
});
server.tool("create_ticket", { payload: z.any() }, async (args) => {
if (!args.payload) throw new Error("error");
});
SRC
payload = { code: CODE,
language: "typescript",
concern: "general",
context: "Internal ticketing server for Claude Desktop, stdio transport, first draft.",
prescan_facts: { tools: [], flags: [] } }
est = api("POST", "/estimate", payload)
puts "worst case: #{est["hold_credits"] || est["credits"]} credits"
$code = <<<'SRC'
server.tool("listTickets", async () => {
const res = await fetch(BASE + "/tickets");
return { content: [{ type: "text", text: await res.text() }] };
});
server.tool("create_ticket", { payload: z.any() }, async (args) => {
if (!args.payload) throw new Error("error");
});
SRC;
$payload = [
"code" => $code,
"language" => "typescript",
"concern" => "general",
"context" => "Internal ticketing server for Claude Desktop, stdio transport, first draft.",
"prescan_facts" => ["tools" => [], "flags" => []],
];
$est = api("POST", "/estimate", $payload);
echo "worst case: " . ($est["hold_credits"] ?? $est["credits"]) . " credits\n";
var code = """
server.tool("listTickets", async () => {
const res = await fetch(BASE + "/tickets");
return { content: [{ type: "text", text: await res.text() }] };
});
server.tool("create_ticket", { payload: z.any() }, async (args) => {
if (!args.payload) throw new Error("error");
});
""";
var payload = new {
code,
language = "typescript",
concern = "general",
context = "Internal ticketing server for Claude Desktop, stdio transport, first draft.",
prescan_facts = new {
tools = Array.Empty<object>(), flags = Array.Empty<object>(),
},
};
var est = await SkillSafe.ApiAsync(HttpMethod.Post, "/estimate", payload);
Console.WriteLine($"worst case: {est.GetProperty("hold_credits")} credits");
prescan_facts.flags is how you make the review answer for things you already
know about. Send {"tools": [{"id": "tool:listtickets", "label": "listTickets (TypeScript)"}],
"flags": [{"id": "no-pagination:listtickets", "label": "list tool listTickets has no limit or cursor parameter"}]} and every flag id
comes back in coverage_check — addressed by a finding, or set aside with
the reason. Nothing you flag is silently dropped, which makes it the field to assert on in a
CI check.
Step 4 — Run the review and wait for the result
/run takes the same input as /estimate, places a credit hold and
returns a job_id. Poll /jobs/{job_id} every 1–2 seconds
until status is succeeded or failed (a run typically
takes 30–90 s, since every finding carries a corrected fragment). Always send
an Idempotency-Key header so a network retry can't start a second,
double-charged run. The review is in output — usually nested as
output.output, and as a JSON string, so parse defensively. The samples
below print the posture, the inventory, the prioritized findings and the focus areas, then
save the whole object to review.json.
JOB_ID=$(curl -s -X POST "$API/run" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-H "Idempotency-Key: mc-$(date +%s)" \
-d @input.json | jq -r '.data.job_id')
while :; do
JOB=$(curl -s "$API/jobs/$JOB_ID" -H "Authorization: Bearer $TOKEN")
STATUS=$(echo "$JOB" | jq -r '.data.status')
[ "$STATUS" = "succeeded" ] || [ "$STATUS" = "failed" ] && break
sleep 2
done
# unwrap the review once, then read it
echo "$JOB" | jq -r '.data.output.output' > review.json
jq -r '
"\(.review_name) [\(.posture)]: \(.verdict)",
"",
"INVENTORY",
(.inventory[] | " \(.name) (\(.kind)) [\(.inputs)] - \(.role)"),
"",
"FINDINGS",
(.findings[] | " [\(.priority)] \(.id) \(.category) \(.tool): \(.problem)"),
"",
"QUICK WINS",
(.quick_wins[] | " - \(.)"),
"",
"FOCUS AREAS",
(.focus_areas[] | " \(.area) - \(.why)"),
"",
"COVERAGE",
(.coverage_check[] | " \(.id): \(if .addressed then "ok" else "SET ASIDE" end) - \(.note)")' \
review.json
# fail the pipeline on anything critical
jq -e '[.findings[] | select(.priority == "critical")] | length == 0' review.json > /dev/null \
|| { echo "critical findings present"; exit 1; }
import time
job_id = api("POST", "/run", payload,
**{"Idempotency-Key": "mc-001"})["job_id"]
while True:
job = api("GET", f"/jobs/{job_id}")
if job["status"] in ("succeeded", "failed"):
break
time.sleep(1.5)
if job["status"] == "failed":
raise RuntimeError(job.get("error", "run failed"))
raw = job["output"]
if isinstance(raw, dict) and "output" in raw:
raw = raw["output"]
review = json.loads(raw) if isinstance(raw, str) else raw
print(f'{review["review_name"]} [{review["posture"]}]: {review["verdict"]}')
for r in review["inventory"]:
print(f' {r["name"]:<28} {r["kind"]:<8} [{r["inputs"]}] {r["role"]}')
for f in review["findings"]:
print(f' [{f["priority"]:>8}] {f["id"]} {f["category"]} {f["tool"]}')
print(f' L:{f["likelihood"]}/S:{f["severity"]} {f["problem"]}')
print(f' fix: {f["fix"]}')
if f["snippet"]:
print(" snippet:", f["snippet"].splitlines()[0], "...")
for w in review["quick_wins"]:
print(" win:", w)
for a in review["focus_areas"]:
print(f' focus {a["area"]} {a["finding_ids"]} - {a["why"]}')
for c in review["coverage_check"]:
print(f' {c["id"]}: {"ok" if c["addressed"] else "SET ASIDE"} - {c["note"]}')
with open("review.json", "w", encoding="utf-8") as fh:
json.dump(review, fh, indent=2)
critical = [f for f in review["findings"] if f["priority"] == "critical"]
if critical:
raise SystemExit(f"{len(critical)} critical finding(s)")
import { writeFileSync } from "node:fs";
const { job_id } = await api("POST", "/run", payload,
{ "Idempotency-Key": crypto.randomUUID() });
let job;
do {
await new Promise((r) => setTimeout(r, 1500));
job = await api("GET", `/jobs/${job_id}`);
} while (job.status !== "succeeded" && job.status !== "failed");
if (job.status === "failed") throw new Error(job.error ?? "run failed");
const raw = job.output?.output ?? job.output;
const review = typeof raw === "string" ? JSON.parse(raw) : raw;
console.log(`${review.review_name} [${review.posture}]: ${review.verdict}`);
for (const r of review.inventory) {
console.log(` ${r.name} (${r.kind}) [${r.inputs}]: ${r.role}`);
}
for (const f of review.findings) {
console.log(` [${f.priority}] ${f.id} ${f.category} ${f.tool}`);
console.log(` L:${f.likelihood}/S:${f.severity} - ${f.fix}`);
}
for (const w of review.quick_wins) console.log(` win: ${w}`);
for (const a of review.focus_areas) {
console.log(` focus ${a.area} (${a.finding_ids.join(", ")}): ${a.why}`);
}
for (const c of review.coverage_check) {
console.log(` ${c.id}: ${c.addressed ? "ok" : "SET ASIDE"} - ${c.note}`);
}
writeFileSync("review.json", JSON.stringify(review, null, 2));
const critical = review.findings.filter((f) => f.priority === "critical");
if (critical.length) process.exitCode = 1;
var started struct{ JobID string `json:"job_id"` }
if err := call("POST", "/run", payload, &started); err != nil {
log.Fatal(err)
}
var job struct {
Status string `json:"status"`
Error string `json:"error"`
Output json.RawMessage `json:"output"`
}
for {
if err := call("GET", "/jobs/"+started.JobID, nil, &job); err != nil {
log.Fatal(err)
}
if job.Status == "succeeded" || job.Status == "failed" {
break
}
time.Sleep(1500 * time.Millisecond)
}
// job.Output is {"output": "<json string>"} — unwrap, then unmarshal:
type Review struct {
ReviewName string `json:"review_name"`
Posture string `json:"posture"`
Verdict string `json:"verdict"`
ExecSummary string `json:"exec_summary"`
Assumptions []string `json:"assumptions"`
OpenQuestions []string `json:"open_questions"`
Inventory []struct {
Name, Kind, Inputs, Role string
} `json:"inventory"`
Findings []struct {
ID, Category, Severity, Likelihood, Priority string
Tool, Problem, Impact, Fix, Snippet string
} `json:"findings"`
CoverageCheck []struct {
ID, Note string
Addressed bool
} `json:"coverage_check"`
QuickWins []string `json:"quick_wins"`
FocusAreas []struct {
Area, Why string
FindingIDs []string `json:"finding_ids"`
} `json:"focus_areas"`
Summary string `json:"summary"`
}
var wrapper struct{ Output string `json:"output"` }
json.Unmarshal(job.Output, &wrapper)
var review Review
json.Unmarshal([]byte(wrapper.Output), &review)
fmt.Printf("%s [%s]: %s\n", review.ReviewName, review.Posture, review.Verdict)
for _, r := range review.Inventory {
fmt.Printf(" %s (%s) [%s]: %s\n", r.Name, r.Kind, r.Inputs, r.Role)
}
for _, f := range review.Findings {
fmt.Printf(" [%s] %s %s %s: %s\n", f.Priority, f.ID, f.Category, f.Tool, f.Problem)
}
for _, a := range review.FocusAreas {
fmt.Printf(" focus %s %v: %s\n", a.Area, a.FindingIDs, a.Why)
}
os.WriteFile("review.json", []byte(wrapper.Output), 0o644)
String envelope = api("POST", "/run", jsonPayload);
String jobId = /* data.job_id via your JSON library */;
while (true) {
String job = api("GET", "/jobs/" + jobId, null);
String status = /* data.status */;
if (status.equals("succeeded") || status.equals("failed")) break;
Thread.sleep(1500);
}
// The review is at data.output.output as a JSON string — parse it again, then read
// review_name, posture, verdict, exec_summary, assumptions[], open_questions[],
// inventory[] (name/kind/inputs/role),
// findings[] (id/category/severity/likelihood/priority/tool/problem/impact/fix/snippet),
// coverage_check[] (id/addressed/note), quick_wins[],
// focus_areas[] (area/why/finding_ids[]) and summary.
// Finally keep the review on disk:
// Files.writeString(Path.of("review.json"), reviewJson);
started = api("POST", "/run", payload)
job = nil
loop do
job = api("GET", "/jobs/#{started["job_id"]}")
break if %w[succeeded failed].include?(job["status"])
sleep 1.5
end
raise (job["error"] || "run failed") if job["status"] == "failed"
raw = job["output"].is_a?(Hash) ? job["output"].fetch("output", job["output"]) : job["output"]
review = raw.is_a?(String) ? JSON.parse(raw) : raw
puts "#{review["review_name"]} [#{review["posture"]}]: #{review["verdict"]}"
review["inventory"].each { |r| puts " #{r["name"]} (#{r["kind"]}) [#{r["inputs"]}]: #{r["role"]}" }
review["findings"].each do |f|
puts " [#{f["priority"]}] #{f["id"]} #{f["category"]} #{f["tool"]}"
puts " L:#{f["likelihood"]}/S:#{f["severity"]} - #{f["fix"]}"
end
review["quick_wins"].each { |w| puts " win: #{w}" }
review["focus_areas"].each { |a| puts " focus #{a["area"]} #{a["finding_ids"].join(", ")}" }
review["coverage_check"].each { |c| puts " #{c["id"]}: #{c["addressed"] ? "ok" : "SET ASIDE"}" }
File.write("review.json", JSON.pretty_generate(review))
exit 1 if review["findings"].any? { |f| f["priority"] == "critical" }
$started = api("POST", "/run", $payload);
do {
sleep(2);
$job = api("GET", "/jobs/" . $started["job_id"]);
} while (!in_array($job["status"], ["succeeded", "failed"]));
if ($job["status"] === "failed") {
throw new Exception($job["error"] ?? "run failed");
}
$raw = is_array($job["output"]) ? ($job["output"]["output"] ?? $job["output"]) : $job["output"];
$review = is_string($raw) ? json_decode($raw, true) : $raw;
echo "{$review['review_name']} [{$review['posture']}]: {$review['verdict']}\n";
foreach ($review["inventory"] as $r) {
echo " {$r['name']} ({$r['kind']}) [{$r['inputs']}]: {$r['role']}\n";
}
foreach ($review["findings"] as $f) {
echo " [{$f['priority']}] {$f['id']} {$f['category']} {$f['tool']}\n";
echo " L:{$f['likelihood']}/S:{$f['severity']} - {$f['fix']}\n";
}
foreach ($review["quick_wins"] as $w) {
echo " win: $w\n";
}
foreach ($review["focus_areas"] as $a) {
echo " focus {$a['area']}: " . implode(", ", $a["finding_ids"]) . "\n";
}
foreach ($review["coverage_check"] as $c) {
echo " {$c['id']}: " . ($c["addressed"] ? "ok" : "SET ASIDE") . "\n";
}
file_put_contents("review.json", json_encode($review, JSON_PRETTY_PRINT));
var started = await SkillSafe.ApiAsync(HttpMethod.Post, "/run", payload);
var jobId = started.GetProperty("job_id").GetString();
JsonElement job;
while (true)
{
job = await SkillSafe.ApiAsync(HttpMethod.Get, $"/jobs/{jobId}");
var status = job.GetProperty("status").GetString();
if (status is "succeeded" or "failed") break;
await Task.Delay(1500);
}
var rawText = job.GetProperty("output").GetProperty("output").GetString();
using var doc = JsonDocument.Parse(rawText!);
var review = doc.RootElement;
Console.WriteLine($"{review.GetProperty("review_name")} " +
$"[{review.GetProperty("posture")}]: {review.GetProperty("verdict")}");
foreach (var r in review.GetProperty("inventory").EnumerateArray())
{
Console.WriteLine($" {r.GetProperty("name")} ({r.GetProperty("kind")}): {r.GetProperty("role")}");
}
foreach (var f in review.GetProperty("findings").EnumerateArray())
{
Console.WriteLine($" [{f.GetProperty("priority")}] {f.GetProperty("id")} " +
$"{f.GetProperty("category")} {f.GetProperty("tool")} " +
$"(L:{f.GetProperty("likelihood")}/S:{f.GetProperty("severity")})");
}
foreach (var a in review.GetProperty("focus_areas").EnumerateArray())
{
Console.WriteLine($" focus {a.GetProperty("area")}: {a.GetProperty("why")}");
}
await File.WriteAllTextAsync("review.json", rawText!);
The model is asked for one JSON object and nothing else, but a stray code fence or preamble
is always possible. Strip a leading ```json fence, take the text between the
first { and the last }, and only then parse — that is what
the app does before it falls back to a retry_note reformat run.
The review object — output schema
One JSON object, always the same shape. Every array is present, and the review is grounded in
the pasted source alone: findings cite only tools and code that actually appear in
code, and something that is simply absent (no annotations, no
pagination, no error handling) is reported against the closest real tool or against
(missing from the server). Where the code is silent on something that changes the
verdict you get an entry in assumptions and, if it would change the ranking, in
open_questions. Expect five to fifteen findings on a typical server — a
well-built one may honestly yield two or three, and findings is never empty.
| Field | Type | Meaning |
|---|---|---|
review_name | string | A short title naming the server, taken from the code's own naming — e.g. tickets server — MCP review. |
posture | string | production-ready | hardening-recommended | not-production-ready. See the table below. |
verdict | string | One sentence justifying the posture and naming the single most important change. |
exec_summary | string | Two or three paragraphs, separated by blank lines, on the dominant themes across the set. |
assumptions | string[] | Explicit assumptions filling gaps the code left open. Read these first — a wrong assumption invalidates the findings built on it. |
open_questions | string[] | Questions whose answers would change the ranking. |
inventory | array | {name, kind, inputs, role} — every registered tool the review parsed out of the paste and the part it plays. name is the registered tool name, kind is tool (or resource / prompt when the server registers those), inputs is a compact parameter list with ? marking optionals. |
findings | array | The prioritized findings table — ids MC-001, MC-002, … in sequence, at least one entry. Columns are listed below. |
coverage_check | array | {id, addressed, note} — one entry per prescan_facts.flags id you sent, each appearing exactly once. See the semantics below. |
quick_wins | string[] | One-line changes worth doing immediately, ahead of any planning. May be empty when nothing here is a one-liner. |
focus_areas | array | {area, why, finding_ids} — what to work through first, one sentence tied to the review, and the finding ids that motivate it. Every id in finding_ids exists in findings. |
summary | string | Closing paragraph: what to fix first, and what risk remains after that. |
The three posture values:
| posture | What it means |
|---|---|
production-ready | The server holds up as written: prefixed snake_case names, described tools, typed schemas, pagination on list tools, actionable errors, truthful annotations, secrets from the environment. Findings still exist, but they are additions and refinements, not blockers. A genuinely well-built server lands here rather than having severity manufactured for it. |
hardening-recommended | The shape is right, but named gaps should be closed before agents rely on this — thin descriptions, missing annotations, a list tool without pagination, error messages that do not guide the caller. |
not-production-ready | At least one thing makes the server unusable or unsafe for agents as written: a literal credential in source, stdout logging that corrupts a stdio session, tools a model cannot discover or invoke (no description, no schema), an unbounded list flooding the context. |
Each entry in findings:
| Column | Meaning |
|---|---|
id | Sequential MC-001, MC-002, … — the stable handle referenced from focus_areas[].finding_ids. |
category | tool-design | schemas | errors | pagination | protocol | security | docs | hygiene. Weighted by the concern you sent, but never restricted to it. |
severity | low | medium | high — how bad it is when it bites. |
likelihood | low | medium | high — how likely it is to bite. |
priority | critical | high | medium | low — severity by likelihood. critical is reserved for a leaked credential, a corrupted protocol stream, or a server agents cannot use as written, so sort on this field and work top-down. This is also the field to gate a pipeline on. |
tool | The tool or place this is about — e.g. tool search_issues — always something that appears in code, or the literal (missing from the server) when the finding is about an absent capability. |
problem | What is wrong, in this code specifically. |
impact | What happens to a real agent session because of it. |
fix | The concrete change to make — not "add validation". |
snippet | A corrected fragment you can paste, in the paste's own language: the fixed registration, schema or handler, not the whole file. Empty string when a snippet would add nothing. Secret values are never echoed — a placeholder appears instead. |
coverage_check semantics:
| Case | What you get |
|---|---|
| Every flag id you sent | Each prescan_facts.flags id appears in coverage_check exactly once. Nothing you flagged is silently dropped, which makes this the field to assert on in a CI check. Ids in prescan_facts.tools are not reconciled here — they shape the inventory instead. |
addressed: true | The flag is covered by the review; note names the finding id that covers it. |
addressed: false | The flag was deliberately set aside; note gives the reason — a check that fired but is not a real problem for this server (a deliberately unpaginated tool over a tiny fixed dataset, logging that only ever runs on the HTTP transport). |
| Nothing sent | Omit prescan_facts, or send the two empty arrays, and coverage_check comes back empty. The rest of the review is unaffected. |
A small, realistic result for the ticketing server above, trimmed for length:
{
"review_name": "tickets server — MCP review",
"posture": "not-production-ready",
"verdict": "A literal API key and console.log on the stdio transport make this unusable as
written; move the key to the environment and the logging to stderr first.",
"exec_summary": "Three themes dominate: a credential is written into the source, the stdio
protocol stream is corrupted by logging to stdout, and the tool interface
(names, descriptions, schemas) gives a calling model almost nothing to work
with.
None of it needs a redesign — the fixes are all additive, and the corrected
fragments below can be applied one at a time.",
"assumptions": [
"This is the whole server, not an excerpt.",
"The stdio transport is the intended deployment, per context."
],
"open_questions": [
"What service prefix should the tools share — tickets_?",
"Which fields does the ticket API return that agents actually need?"
],
"inventory": [
{ "name": "listTickets", "kind": "tool", "inputs": "(none declared)",
"role": "Fetches every ticket and returns the raw JSON body." },
{ "name": "create_ticket", "kind": "tool", "inputs": "payload (any)",
"role": "POSTs an arbitrary payload to the ticket API." },
{ "name": "search", "kind": "tool", "inputs": "query",
"role": "Full-text search over tickets, unbounded." }
],
"findings": [
{ "id": "MC-001", "category": "security",
"severity": "high", "likelihood": "high", "priority": "critical",
"tool": "(missing from the server)",
"problem": "The ticket API key is a string literal in the source.",
"impact": "The credential ships with the package and lands in Git history; anyone with
repo access owns the ticket system.",
"fix": "Read the key from the environment at startup and exit with a clear message when
it is absent.",
"snippet": "const API_KEY = readEnv(\"TICKETS_API_KEY\");\nif (!API_KEY) {\n console.error(\"TICKETS_API_KEY is not set. Export it before starting the server.\");\n throw new Error(\"missing TICKETS_API_KEY\");\n}" },
{ "id": "MC-002", "category": "protocol",
"severity": "high", "likelihood": "high", "priority": "critical",
"tool": "tool listTickets",
"problem": "console.log writes to stdout while the server runs on StdioServerTransport.",
"impact": "Anything printed to stdout is interleaved with protocol frames; clients
disconnect mid-session — matching the behaviour described in context.",
"fix": "Log to stderr instead.",
"snippet": "console.error(\"fetched \" + data.length + \" tickets\");" },
{ "id": "MC-003", "category": "schemas",
"severity": "high", "likelihood": "high", "priority": "high",
"tool": "tool listTickets",
"problem": "Registered with no description and no input schema, and named in camelCase
with no service prefix.",
"impact": "A calling model has nothing to select on and nothing to validate against;
most clients will never call it correctly.",
"fix": "Rename to tickets_list_tickets, add a description and a Zod schema with limit
and cursor parameters.",
"snippet": "server.registerTool(\"tickets_list_tickets\", {\n description: \"List tickets, newest first.\",\n inputSchema: {\n limit: z.number().int().min(1).max(50).default(20).describe(\"Max tickets to return\"),\n cursor: z.string().optional().describe(\"Cursor from a previous call\")\n }\n}, listTickets);" }
],
"coverage_check": [
{ "id": "secret-literal:file", "addressed": true, "note": "MC-001." },
{ "id": "stdio-print:file", "addressed": true, "note": "MC-002." },
{ "id": "no-description:listtickets", "addressed": true, "note": "Folded into MC-003." },
{ "id": "no-schema:listtickets", "addressed": true, "note": "Folded into MC-003." },
{ "id": "no-pagination:listtickets", "addressed": true, "note": "Folded into MC-003." }
],
"quick_wins": [
"Switch console.log to console.error — one line.",
"Move the API key into the environment."
],
"focus_areas": [
{ "area": "Secrets and the protocol stream",
"why": "A leaked credential and a corrupted stdio session block everything else.",
"finding_ids": ["MC-001", "MC-002"] },
{ "area": "Tool interface quality",
"why": "Until the tools have names, descriptions and schemas a model can use, the server
is invisible to agents.",
"finding_ids": ["MC-003"] }
],
"summary": "Move the key to the environment and the logging to stderr, then rebuild the tool
interface: prefixed snake_case names, descriptions, typed schemas, pagination. …"
}
This is AI-generated review from source text, not a production sign-off: it sees only what
you sent, never the running server, its dependencies or its real traffic. Check
assumptions and open_questions before you act on the rankings,
compile and test every snippet against a real client (MCP Inspector is the usual harness),
and keep a human reviewer in the loop.
Step 5 — Stream the review as it is written
/run-stream takes exactly the same body as /run but answers with
server-sent events, so you can show progress instead of a spinner — useful here
because a full findings table with corrected fragments makes for a long reply. This app's own
progress panel is this endpoint. Events are separated by a blank line; each has an
event: line and a data: line carrying JSON.
| Event | Payload | Meaning |
|---|---|---|
job | {job_id, status} | Sent once, when the job is accepted — show "starting". |
delta | {text} | A chunk of the reply, in order. Append it; the accumulated length is your only progress signal (the total is not known in advance). The app advances its step list by watching for the "review_name", "inventory", "findings", "coverage_check" and "focus_areas" keys as they arrive. |
done | {job_id, status, charged_credits, output} | The final, authoritative result — read the review from output.output rather than trusting concatenated deltas, and the settled price from charged_credits. |
error | {code, message} | Replaces done when the run fails. |
# -N disables buffering so events print as they arrive
curl -N -s -X POST "$API/run-stream" \
-H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \
-H "Idempotency-Key: mc-$(date +%s)" \
-d @input.json
# event: job
# data: {"job_id":"job_...","status":"running"}
#
# event: delta
# data: {"text":"{\"review_name\":\"web stack"}
# ...
# event: done
# data: {"job_id":"job_...","status":"succeeded","charged_credits":612,"output":{"output":"{...}"}}
import json, requests
result = None
with requests.post(
API + "/run-stream",
headers={"Authorization": f"Bearer {TOKEN}",
"Idempotency-Key": "mc-001"},
json=payload,
stream=True,
) as r:
r.raise_for_status()
event = None
for line in r.iter_lines(decode_unicode=True):
if not line:
continue
if line.startswith("event:"):
event = line[len("event:"):].strip()
elif line.startswith("data:"):
data = json.loads(line[len("data:"):].strip())
if event == "delta":
print(".", end="", flush=True) # live progress
elif event == "done":
result = data
elif event == "error":
raise RuntimeError(data.get("message", "run failed"))
review = json.loads(result["output"]["output"]) # authoritative
print("charged:", result["charged_credits"], "-", review["review_name"])
print("posture:", review["posture"])
for f in review["findings"]:
print(f' [{f["priority"]}] {f["id"]} {f["tool"]}: {f["problem"]}')
with open("review.json", "w", encoding="utf-8") as fh:
json.dump(review, fh, indent=2)
const res = await fetch(API + "/run-stream", {
method: "POST",
headers: {
Authorization: `Bearer ${TOKEN}`,
"Content-Type": "application/json",
"Idempotency-Key": crypto.randomUUID(),
},
body: JSON.stringify(payload),
});
const reader = res.body.getReader();
const decoder = new TextDecoder();
let buf = "", done = null;
for (;;) {
const chunk = await reader.read();
if (chunk.done) break;
buf += decoder.decode(chunk.value, { stream: true });
const frames = buf.split("\n\n");
buf = frames.pop();
for (const frame of frames) {
const name = /^event:\s*(.+)$/m.exec(frame)?.[1];
const body = /^data:\s*(.+)$/m.exec(frame)?.[1];
if (!name || !body) continue;
const data = JSON.parse(body);
if (name === "delta") process.stdout.write("."); // live progress
if (name === "done") done = data;
if (name === "error") throw new Error(data.message ?? "run failed");
}
}
const review = JSON.parse(done.output.output);
console.log(`\n${done.charged_credits} credits - ${review.review_name} [${review.posture}]`);
for (const f of review.findings) console.log(` [${f.priority}] ${f.id} ${f.tool}`);
writeFileSync("review.json", JSON.stringify(review, null, 2));
body, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", API+"/run-stream", bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer "+token)
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Idempotency-Key", "mc-001")
res, err := http.DefaultClient.Do(req)
if err != nil {
log.Fatal(err)
}
defer res.Body.Close()
var event string
var final map[string]any
sc := bufio.NewScanner(res.Body)
sc.Buffer(make([]byte, 0, 64*1024), 4*1024*1024)
for sc.Scan() {
line := sc.Text()
switch {
case strings.HasPrefix(line, "event:"):
event = strings.TrimSpace(strings.TrimPrefix(line, "event:"))
case strings.HasPrefix(line, "data:"):
var data map[string]any
json.Unmarshal([]byte(strings.TrimPrefix(line, "data:")), &data)
switch event {
case "delta":
fmt.Print(".") // live progress
case "done":
final = data
case "error":
log.Fatal(data["message"])
}
}
}
// final["output"].(map[string]any)["output"].(string) is the review JSON —
// unmarshal it into the Review struct from step 4, then write it to review.json.
// Java 17+ — read the stream line by line instead of buffering the body.
var req = HttpRequest.newBuilder(URI.create(API + "/run-stream"))
.header("Authorization", "Bearer " + TOKEN)
.header("Content-Type", "application/json")
.header("Idempotency-Key", "mc-001")
.POST(HttpRequest.BodyPublishers.ofString(jsonPayload))
.build();
var res = HTTP.send(req, HttpResponse.BodyHandlers.ofLines());
String event = null, done = null;
for (String line : (Iterable<String>) res.body()::iterator) {
if (line.startsWith("event:")) {
event = line.substring(6).trim();
} else if (line.startsWith("data:")) {
String data = line.substring(5).trim();
if ("delta".equals(event)) System.out.print("."); // live progress
else if ("done".equals(event)) done = data;
else if ("error".equals(event)) throw new RuntimeException(data);
}
}
// parse `done`, then parse data.output.output again — it is a JSON string holding
// review_name, posture, verdict, inventory[], findings[], coverage_check[],
// quick_wins[], focus_areas[] and the rest.
require "net/http"
require "json"
uri = URI(API + "/run-stream")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{TOKEN}"
req["Content-Type"] = "application/json"
req["Idempotency-Key"] = "kc-001"
req.body = payload.to_json
event = nil
done = nil
Net::HTTP.start(uri.host, uri.port, use_ssl: true) do |http|
http.request(req) do |res|
res.read_body do |chunk|
chunk.each_line do |line|
line = line.strip
if line.start_with?("event:")
event = line.delete_prefix("event:").strip
elsif line.start_with?("data:")
data = JSON.parse(line.delete_prefix("data:").strip)
case event
when "delta" then print "." # live progress
when "done" then done = data
when "error" then raise (data["message"] || "run failed")
end
end
end
end
end
end
review = JSON.parse(done["output"]["output"])
puts "\n#{done["charged_credits"]} credits - #{review["review_name"]} [#{review["posture"]}]"
review["findings"].each { |f| puts " [#{f["priority"]}] #{f["id"]} #{f["tool"]}" }
File.write("review.json", JSON.pretty_generate(review))
$event = null;
$done = null;
$ch = curl_init(API . "/run-stream");
curl_setopt_array($ch, [
CURLOPT_POST => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer $TOKEN",
"Content-Type: application/json",
"Idempotency-Key: kc-001",
],
CURLOPT_POSTFIELDS => json_encode($payload),
CURLOPT_WRITEFUNCTION => function ($ch, $chunk) use (&$event, &$done) {
foreach (explode("\n", $chunk) as $line) {
$line = trim($line);
if (str_starts_with($line, "event:")) {
$event = trim(substr($line, 6));
} elseif (str_starts_with($line, "data:")) {
$data = json_decode(trim(substr($line, 5)), true);
if ($event === "delta") { echo "."; } // live progress
elseif ($event === "done") { $done = $data; }
elseif ($event === "error") { throw new Exception($data["message"] ?? "run failed"); }
}
}
return strlen($chunk);
},
]);
curl_exec($ch);
curl_close($ch);
$review = json_decode($done["output"]["output"], true);
echo "\n{$done['charged_credits']} credits - {$review['review_name']} [{$review['posture']}]\n";
foreach ($review["findings"] as $f) {
echo " [{$f['priority']}] {$f['id']} {$f['tool']}\n";
}
file_put_contents("review.json", json_encode($review, JSON_PRETTY_PRINT));
var req = new HttpRequestMessage(HttpMethod.Post, Api + "/run-stream") {
Content = JsonContent.Create(payload),
};
req.Headers.Add("Idempotency-Key", "mc-001");
using var res = await Http.SendAsync(req, HttpCompletionOption.ResponseHeadersRead);
using var reader = new StreamReader(await res.Content.ReadAsStreamAsync());
string? evt = null, done = null;
while (await reader.ReadLineAsync() is { } line)
{
if (line.StartsWith("event:")) evt = line[6..].Trim();
else if (line.StartsWith("data:"))
{
var data = line[5..].Trim();
if (evt == "delta") Console.Write("."); // live progress
else if (evt == "done") done = data;
else if (evt == "error") throw new Exception(data);
}
}
using var final = JsonDocument.Parse(done!);
var text = final.RootElement.GetProperty("output").GetProperty("output").GetString();
using var reviewDoc = JsonDocument.Parse(text!);
var review = reviewDoc.RootElement;
Console.WriteLine($"{review.GetProperty("review_name")} [{review.GetProperty("posture")}]");
foreach (var f in review.GetProperty("findings").EnumerateArray())
Console.WriteLine($" [{f.GetProperty("priority")}] {f.GetProperty("id")} {f.GetProperty("tool")}");
await File.WriteAllTextAsync("review.json", text!);
In a browser, the native EventSource only speaks GET, and this endpoint is a
POST — read the fetch response body incrementally, as the JavaScript
sample above does. On an idempotent replay the server may answer with a plain JSON
envelope instead of an event stream; check the Content-Type before you start
parsing frames.