Skip to main content
Glama

mcpreflight

Point it at any MCP or x402 endpoint and get a verdict in one command. Read-only: no API key, no wallet, no tool calls.

npx -y @eidonze/mcpreflight schema https://your-mcp-server.example/mcp
Status: PASS | FAIL | UNKNOWN   exit 0 | 1 | 2, so CI can gate on it

Reach for it when an agent client, a buyer, or a CI job is about to depend on an endpoint whose source you cannot read, including endpoints you do not own. It reads only what the endpoint already sends to any anonymous caller: the initialize handshake, tools/list, and the HTTP 402 / x402 payment document.

Form

Run it

Use it for

CLI

npx -y @eidonze/mcpreflight ...

one-off checks and scripts

Homebrew

brew install xka0085-byte/mcpreflight/mcpreflight

a machine-wide mcpreflight on PATH, macOS or Linux

GitHub Action

uses: xka0085-byte/mcpreflight@v1

fail a PR when a handshake, a tool schema or an x402 challenge drifts

stdio MCP server

npx -y -p @eidonze/mcpreflight mcpreflight-mcp

let an agent check an endpoint before it connects

No install to try it: run the check in the browser, free and without signup: check-your-mcp-endpoint

npm CI License Listed on mcpservers.org

Listed in the official MCP Registry as io.github.xka0085-byte/mcpreflight (browse) and on the GitHub Marketplace.

What it is

Read-only MCP and x402 preflight: it reads initialize + tools/list and x402 payment documents. No API key, no wallet, no payment, no tool calls.

This is an endpoint preflight, not a source audit. Tools that read your repository or fuzz a server you launch need a checkout and a start command; this one needs only a URL, so it can check the deployment an agent is about to connect to, including one you do not own.

Related MCP server: @melis-ai/x402-tools-mcp

Same name, different job

Search "MCP preflight" and you also meet kenimo49/mcp-preflight, now published as mcp-scorecard. Both check an MCP server before something depends on it; the input and the findings differ.

This repo (mcpreflight)

mcp-scorecard (kenimo49)

Input

a deployment URL, including one you do not own

a local checkout, a localhost URL, or a pypi: package

Reads

initialize, tools/list, and the HTTP 402 / x402 payment document, anonymously

per-turn token footprint, use-case scoping of each tool, security rules, name safety

Answers

will this deployed endpoint answer an agent, and does its payment challenge still hold?

is this server cheap and clear enough for an LLM to use, before you publish it?

One grades the source you have; the other checks the endpoint you are about to depend on.

Check an endpoint you do not own

The same read-only check runs weekly against every remote endpoint listed in the official MCP Registry, and the results are published as pages and as JSON:

  • Trust Directory — 35,325 endpoints, one report each: status, protocol version, tool count, findings, and whether credentials are required.

  • JSON API — /trust/api/{slug}.json per endpoint, plus batch indexes and a JSON Schema. No key, no signup, no rate limit.

  • x402 census dataset — the payment slice of the same sweep: 1,583 of 35,327 endpoints advertise x402 or HTTP-402, with a weekly series, a status distribution against the registry-wide baseline, and downloadable CSV/JSON.

Read the vocabulary before quoting any number: in the 2026-11-02 scan, 20,701 endpoints answered anonymously (PASS), 10,236 refused with 401 because they require credentials by design (AUTH_GATED), 167 were reachable but invalid (FAIL), and 4,223 gave no anonymous handshake (UNKNOWN, usually an auth wall we cannot see past). A "dead MCP servers" count taken from this data would be wrong — 41% of the registry cannot be checked without credentials at all.

Use it as an MCP server

The stdio entry point is bin/mcpreflight-mcp.mjs, published as the mcpreflight-mcp bin in the same npm package. It implements the MCP lifecycle a client expects: initialize returns serverInfo mcpreflight with the package version, notifications/initialized is accepted, and tools/list returns two tools.

Tool

What it does

schema_check

Runs the read-only preflight against a server URL: initialize handshake, tools/list, then tool input schema validation. Returns PASS/FAIL/UNKNOWN with findings. Never calls a tool, never reads data.

x402_inspect

Reads an HTTP 402 challenge without paying: validates the payment document shape, the accepts[] entries and discovery manifests. Never signs or settles.

Add it to an MCP client:

{
  "mcpServers": {
    "mcpreflight": {
      "command": "npx",
      "args": ["-y", "-p", "@eidonze/mcpreflight", "mcpreflight-mcp"]
    }
  }
}

Both tools do the same work as the CLI and return the same findings, so an agent can check an endpoint before it connects to it. Read-only by construction: the transport issues only GET and POST to the URL you pass, holds no key and has no wallet.

Seen in use

  • joxo serves an MCP endpoint that is auth-gated by design. Their maintainer read the 0.2.0 source to confirm the check was two plain POSTs with no dependencies, then ran npx @eidonze/mcpreflight@0.2.0 schema https://joxo.ai/api/mcp and got UNKNOWN: MCP initialize returned HTTP 401 against a deliberate OAuth 2.1 gate (#50). That report is the reason 0.3.0 classifies an OAuth challenge as AUTH_GATED, with the RFC 9728 resource metadata verified, instead of reading as a dead endpoint. They re-checked on 2026-11-01 and closed it: "The endpoint is sign-in only, so no anonymous handshake is expected. Thanks for the AUTH_GATED handling; closing." (#50).

  • A maintainer of cueframe-mcp reran the scan after a fix and reported the result back: @eidonze/mcpdoctor@0.1.8 (the earlier npm name) now exits 0 on their endpoint, with the anonymous tools/list payload down from 1,399,189 to 550,377 bytes — under the scanner's 1 MiB limit (#11).

  • Listed in awesome-mcp-lists under MCP Toolkits / Testing Tools (#226).

These are examples of the check being run, not endorsements or a claim that a PASS makes a server safe.

Start here

Exit codes are stable for CI: 0 PASS, 1 FAIL, 2 UNKNOWN/network, 3 usage. Requires Node.js 18+.

mode is schema (MCP handshake plus tool schemas), inspect (one-off x402 preflight), baseline (record the current 402 challenge shape) or drift (fail the job when that shape moves away from the committed baseline). The report is also appended to the job summary, and steps.<id>.outputs.status carries the exit code so later steps can branch on it without parsing logs.

Find the right guide

Run it now

Check an MCP server without calling any tools:

npx @eidonze/mcpreflight schema https://your-mcp-server.example/mcp --json

Check an x402 endpoint without paying:

npx @eidonze/mcpreflight inspect https://your-api.example/paid --method=POST --json
npx @eidonze/mcpreflight inspect https://your-api.example/paid --x402   # payment layer only, one request

Requires Node.js 18+. No API key or wallet is needed.

Example schema run against a live endpoint:

$ npx @eidonze/mcpreflight schema https://your-mcp-server.example/mcp

MCP Tool Schema Report
- Status: FAIL
- Endpoint: https://your-mcp-server.example/mcp
- Protocol: 2025-06-18
- Tools: 12

- FAIL REQUIRED_PROPERTY_UNDEFINED: tools[3] requires undeclared property query
- WARN PROPERTY_DESCRIPTION_MISSING: tools[7].limit has no description

The exact same run against a healthy server prints Status: PASS and exits 0, so CI can gate on it.

Which command?

Command

Checks

Does not do

schema

MCP initialize, tools/list, tool names, descriptions, and JSON schemas

Does not call tools or prove runtime behavior

inspect

HTTP 402, x402 v1/v2 payment document, accepts[], discovery manifests, latency and response digest

Does not sign, pay, settle, retry, or verify delivery

inspect --x402

The payment layer only: one request, the 402 challenge and its accepts[] entries, no MCP handshake or discovery probes

Same limits, and it says nothing about the MCP endpoint behind the payment

Exit codes are stable for automation: 0 PASS, 1 FAIL, 2 UNKNOWN/network error, 3 usage error.

What it does NOT check

mcpreflight is a protocol- and schema-level preflight, not a security audit. It does not:

  • Detect malicious code, prompt injection, or supply-chain risk in the server's implementation

  • Call tools, so it cannot prove runtime behavior, data handling, or permission scope

  • Bypass, test, or evaluate authentication and authorization

  • Verify payment settlement or delivery for x402 endpoints

  • Certify compliance with any spec beyond the response shapes it inspects

A PASS means the observed handshake and schemas were well-formed at scan time. Nothing more.

GitHub Actions

Add a read-only check to pull requests:

name: MCP Trust Check
on: [pull_request]

jobs:
  mcp-trust:
    runs-on: ubuntu-latest
    steps:
      - uses: xka0085-byte/mcpreflight@v1
        with:
          endpoint: https://your-mcp-server.example/mcp
          mode: schema
          format: markdown

Use mode: x402 when you only care about the payment layer: one request, the 402 challenge and its accepts[], no handshake, no discovery probes. Use mode: inspect for the full report. The action fails on FAIL or UNKNOWN by default; set fail-on: false for an informational check. Looking for it in the Marketplace? Search "MCP Trust Preflight" or "mcp server test", or browse the mcp-trust-preflight listing.

Starter template

Start a new MCP project with this check already wired in:

The check is read-only and should target a public test endpoint. Do not place private keys or credentials in workflow inputs.

What the report means

PASS means the observed response matched the checks in this version. It is not a security audit, protocol certification, payment-success guarantee, or proof that an endpoint is safe. UNKNOWN means the endpoint could not be observed within the timeout or response-size limits.

Example schema failure:

FAIL REQUIRED_PROPERTY_UNDEFINED tools[0] requires undeclared property query

Example x402 failure:

FAIL NO_402 Expected HTTP 402, received 400

Why it exists

The checks come from failure modes observed while building ReceiptRail: body validation that prevents an x402 challenge, payment documents in multiple headers/body shapes, and vendor hint headers that can hide the real accepts[] document.

mcpreflight ships as one read-only codebase in three forms: the CLI and the GitHub Action, and a stdio MCP server (bin/mcpreflight-mcp.mjs, npm bin mcpreflight-mcp) exposing schema_check and x402_inspect. It is not affiliated with mcpreflight.dev; verify the npm scope is @eidonze/mcpreflight.

Feedback

Found a false positive or a protocol shape we should support? Open an issue. Include the command, redacted output, Node version, and whether the endpoint is MCP or x402. Never include tokens, payment signatures, or private URLs.

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    A stdio MCP server that audits other MCP servers over the live protocol. It connects to any MCP target (stdio or HTTP), lints every tool's schema for agent-usability, then actually calls the tools with deliberately broken inputs to see how the server handles them, and returns a 0–100 conformance score with a per-dimension breakdown rendered as Markdown.
    6
    20 npm
    6
    MIT
  • A
    license
    B
    quality
    F
    maintenance
    An MCP server providing 22 pay-per-call utility tools for AI agents (scrape, validate, embed, store, moderate, notify, convert, prevent loops) without accounts or API keys, using USDC payments via the x402 protocol.
    17
    75 npm
    1
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    A remote MCP server that verifies paid x402 and MCP tools for discoverability, inspectability, and claim-bound correctness, enabling pre-submission readiness checks for agent-tool sellers.
    1
    -
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables agents to look up and search servers from the official MCP registry, probe any server live for availability, protocol, auth, tools and context-token cost, and retrieve registry-wide statistics. Also supplies a CLI and GitHub Action that measure how many tokens your own configured servers' tool definitions consume against a budget.
    MIT