Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Active OAuth tests for remote MCP servers you own: tokens, PKCE, redirect_uri, audience, CSRF.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
MCP_AUTHPROBE_SECRET_FILE, MCP_AUTHPROBE_SECRET, MCP_AUTHPROBE_CREDENTIALS_FILE, MCP_AUTHPROBE_ALLOW_PRIVATE, MCP_AUTHPROBE_LAB_ORIGINS, MCP_AUTHPROBE_TIMEOUT_MSValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"authprobe": {
"command": "npx",
"args": [
"-y",
"mcp-authprobe",
"mcp"
],
"env": {
"MCP_AUTHPROBE_SECRET_FILE": "your-value",
"MCP_AUTHPROBE_SECRET": "your-value",
"MCP_AUTHPROBE_CREDENTIALS_FILE": "your-value",
"MCP_AUTHPROBE_ALLOW_PRIVATE": "your-value",
"MCP_AUTHPROBE_LAB_ORIGINS": "your-value",
"MCP_AUTHPROBE_TIMEOUT_MS": "your-value"
}
}
}
}Run this in your terminal
claude mcp add authprobe --env MCP_AUTHPROBE_SECRET_FILE=your-value --env MCP_AUTHPROBE_SECRET=your-value --env MCP_AUTHPROBE_CREDENTIALS_FILE=your-value --env MCP_AUTHPROBE_ALLOW_PRIVATE=your-value --env MCP_AUTHPROBE_LAB_ORIGINS=your-value --env MCP_AUTHPROBE_TIMEOUT_MS=your-value -- npx -y mcp-authprobe mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"authprobe": {
"command": "npx",
"args": [
"-y",
"mcp-authprobe",
"mcp"
],
"env": {
"MCP_AUTHPROBE_SECRET_FILE": "your-value",
"MCP_AUTHPROBE_SECRET": "your-value",
"MCP_AUTHPROBE_CREDENTIALS_FILE": "your-value",
"MCP_AUTHPROBE_ALLOW_PRIVATE": "your-value",
"MCP_AUTHPROBE_LAB_ORIGINS": "your-value",
"MCP_AUTHPROBE_TIMEOUT_MS": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"authprobe": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-authprobe",
"mcp"
],
"env": {
"MCP_AUTHPROBE_SECRET_FILE": "your-value",
"MCP_AUTHPROBE_SECRET": "your-value",
"MCP_AUTHPROBE_CREDENTIALS_FILE": "your-value",
"MCP_AUTHPROBE_ALLOW_PRIVATE": "your-value",
"MCP_AUTHPROBE_LAB_ORIGINS": "your-value",
"MCP_AUTHPROBE_TIMEOUT_MS": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
MCP_AUTHPROBE_SECRET_FILE envMCP_AUTHPROBE_CREDENTIALS_FILE envMCP_AUTHPROBE_ALLOW_PRIVATE envMCP_AUTHPROBE_LAB_ORIGINS envMCP_AUTHPROBE_TIMEOUT_MS envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account Enigmacker, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: MCP_AUTHPROBE_SECRET
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.8.0) reached the registry 2 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Fomu MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Kenya government form guides: checklists, draft letters, eCitizen, Huduma, timelines. Sample data.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Active authorization testing for remote MCP servers you own.
Passive scanners read what a remote Model Context Protocol server *announces*: its OAuth metadata, its TLS setup, its tool descriptions. Some properties can only be confirmed by actually exercising the authorization server: does it really rotate refresh tokens, does it really refuse a redirect URI it never registered, does it enforce PKCE, does it accept a token meant for another server, does it slow down repeated failures?
mcp-authprobe runs those active checks, against servers whose ownership you have proven, and reports the results as JSON, SARIF and Markdown.
19 checks, field-tested against a certified OpenID provider: OAuth discovery, refresh token rotation and replay, redirect URI strictness, PKCE enforcement, single-use codes, token audience,
Originvalidation, tokens in URLs, session IDs used as credentials, CORS, throttling and consent CSRF (in a real browser). It works as a CLI with an interactivelogin, as an MCP server so an AI assistant can run the audit, and as a GitHub Action. A deliberately vulnerable lab lets you try everything in a minute.
Only test servers you own or are explicitly authorized to test. Active checks change state on the target. The tool enforces an ownership proof before running them, but responsibility stays with the operator.
Besides its own test suite and lab, mcp-authprobe was run against real authorization stacks before each release:
Origin header. Every check that can be judged from outside passed; MAP-THR01 failed, as expected, since that provider leaves rate limiting to the deployment; and its consent page, protected by a per-flow identifier instead of an anti-CSRF field, is reported as inconclusive with the reason.redirect_uri not bound to the code, no Origin validation, unsafe redirect URIs accepted at registration, no refresh tokens, and crashes reported as inconclusive rather than passes. Its sessions correctly require the token on every request (MAP-SES01 passes).These runs led to several fixes: results kept when a server issues no refresh token or crashes during login, a throttling check that copes with a broken refresh grant, and the per-flow identifier analysis above.
Good tools already exist, and this one is meant to sit next to them, not replace them:
| Tool | Focus | Overlap with mcp-authprobe |
|---|---|---|
| mcp-posture | Passive posture of remote servers: OAuth metadata per RFC, transport, tool poisoning, rug pulls | None by design: it never sends state-changing requests. Run it first. |
| MCPJam OAuth conformance | Runs real OAuth flows and checks conformance, with a few negative checks | Basic redirect URI rejection. No refresh token replay, throttling or consent CSRF. |
| Cisco mcp-scanner, Snyk agent-scan | Malicious tools, configs, local servers | None. |
mcp-authprobe focuses on what only an active, authorized test can confirm, and uses check IDs (MAP-…) that do not clash with mcp-posture's (MCPP-…). mcp-posture reserves its own active IDs for this and points here; the two reports can be merged into one.
Requires Node.js 22.19 or later.
# run without installing
npx mcp-authprobe --help
npm install -g mcp-authprobe
Releases are published from GitHub Actions with npm trusted publishing; check the provenance on the package page before installing a security tool.
From source:
git clone https://github.com/Enigmacker/mcp-authprobe.git
cd mcp-authprobe npm ci npm run build node dist/cli.js --help
mcp-authprobe lab starts a small MCP server with its own OAuth authorization server on 127.0.0.1, so you can see every check at work without touching a real server:
# Terminal 1: a deliberately vulnerable server (or --profile secure)
npx mcp-authprobe lab
npx mcp-authprobe scan http://127.0.0.1:8787/mcp --allow-private npx mcp-authprobe login http://127.0.0.1:8787/mcp --allow-private --out lab-grant.json npx mcp-authprobe scan http://127.0.0.1:8787/mcp --allow-private --credentials-file lab-grant.json
Log in with the account test / test and click Allow.
| Profile | What you should see |
|---|---|
vulnerable (default) | Refresh token replay accepted, unsafe redirect URIs registered, PKCE not enforced, token audience ignored, foreign Origin accepted, token accepted in the URL, session ID accepted without a token, CORS open to any origin with credentials, no throttling, consent page without CSRF protection. MAP-RDR02 is reported as inconclusive: this server sends unknown visitors to its login page before looking at redirect_uri, which cannot be told apart from outside, and the scanner never turns that into a pass. |
secure | Every check passes (or is not applicable); MAP-CSR01 runs with consent-check. |
The lab only listens on 127.0.0.1 or ::1 (--host, --port, default 8787; names such as localhost are refused so that no resolver can move it elsewhere), keeps everything in memory, and stops with Ctrl-C. Its access tokens are unsigned JWTs, so MAP-AUD01 can read their audience. It is vulnerable on purpose: never expose it.
# 1. Create a secret and the proof to publish for your MCP host
mcp-authprobe ownership init mcp.example.com
export MCP_AUTHPROBE_SECRET='…'
mcp-authprobe ownership verify mcp.example.com
mcp-authprobe scan https://mcp.example.com/mcp --sarif results.sarif --markdown summary.md
mcp-authprobe login https://mcp.example.com/mcp --out ./test-grant.json
mcp-authprobe scan https://mcp.example.com/mcp --credentials-file ./test-grant.json
Without a valid proof the scan still runs discovery (the same read-only requests any MCP client sends before logging in), and every active check is reported as skipped.
For a local lab on your own machine:
mcp-authprobe scan http://127.0.0.1:8080/mcp --allow-private
Loopback targets with --allow-private do not need a proof.
Active checks register clients, rotate tokens and send failing requests. To make sure they only ever hit servers whose operator agreed to it, the scanner requires a proof for every host it would contact: the MCP server host and, when it differs, the authorization server host.
The proof is a hash, bound to the host, of a secret that only you hold:
mcp-authprobe-verification=sha256:<hex(sha256("<host>:<secret>"))>
Publish it in one of two places:
| Method | Where | Value |
|---|---|---|
| Well-known file | https:// /.well-known/mcp-authprobe.txt | one line per proof; other lines are ignored |
| DNS TXT | _mcp-authprobe. | the proof string |
Design choices:
mcp.example.com is useless for any other host.You can remove the proof as soon as you are done testing.
MCP clients are usually public clients, so OAuth 2.1 requires their refresh tokens to be rotated, and RFC 9700 recommends revoking the whole token family when an old one is reused. These properties cannot be read from metadata; they have to be exercised.
The checks need a test grant: a client and a refresh token obtained by logging in to your own server with a dedicated test account.
The easy way is mcp-authprobe login (see Interactive login), which writes the file for you. You can also write it by hand, readable only by you (chmod 600):
{
"client_id": "your-test-client-id", "refresh_token": "the-refresh-token", "client_secret": "only-for-confidential-clients", "token_endpoint_auth_method": "none" }
token_endpoint_auth_method is none (default for public clients), client_secret_post (default when a secret is present) or client_secret_basic.
The scan sends at most three refresh_token requests to the token endpoint found by discovery:
| Step | Request | Expected on a compliant server | Check |
|---|---|---|---|
| 1 | Refresh with the supplied token | New access token and a new refresh token | MAP-RTK01 |
| 2 | Refresh again with the token from step 1's input (already used) | Rejected, typically invalid_grant | MAP-RTK02 |
| 3 | Refresh with the newest token (from step 1's output) | Rejected: reuse revoked the whole family | MAP-RTK03 |
Important:
MAP-RTK01 fails and the two replay checks are reported as not applicable.error (inconclusive), never as a pass.mcp-authprobe login https://mcp.example.comOnly the beginning is shown; read the rest in the repo