MCP Verification Gate: check an MCP server or an A2A agent before you connect or delegate

io.github.ogasurfproject-jpgPublished by GitHub account ogasurfproject-jpgv0.4.24Updated Nov 7, 2026

Check an A2A agent before you delegate, or an MCP server's measured conduct. Free, no key.

The publisher's own server: check.tattoo: tattoo size and placement guide

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A remote gate that checks a public MCP endpoint or A2A agent's declared conduct and returns a recomputable verdict before you connect or delegate.

What you can do
  • Read the gate's five measured conditions, exclusions and tier definitions
  • Measure a public MCP endpoint for conformance and disclosure, free and without a key
  • Recompute a verdict's record hash to see whether it was altered after issue
  • Look up one register record for an endpoint: watch status, measurement count, dates and latest verdict
  • Get a single machine-first verified/state answer before connecting to an endpoint
  • Preflight an unfamiliar A2A agent by fetching its public card and reporting its declarations
When to use it
Use it when an assistant is about to connect to an unfamiliar MCP server or hand work to an A2A agent and you want a quick, independently checkable signal about declared conduct. It is also useful for auditing whether a verdict you were given was modified.
Requirements
A remote streamable HTTP endpoint; no key, account, environment variables or headers are declared. The gate needs network access to the target endpoint it measures, and preflight fetches the agent's public card.
Before you install
Verdicts cover conformance and disclosure only, not whether a server is safe or trustworthy in substance. Compensation declarations are reported as declared and not verified. Checks send requests to third-party endpoints you name, and the gate is a third party whose own output you are relying on.

Installation

In SourceWeft

  1. Open MCP Verification Gate: check an MCP server or an A2A agent before you connect or delegate in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.ogasurfproject-jpg%2Fhs-verify-gate/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "verification-gate-check-an-or-an-a2a-age": {
      "type": "http",
      "url": "https://gate.horizonshield.dev/mcp"
    }
  }
}

README

This repository has no README.

Tools

6

get_conditions

Get the conformance conditions

Return the five conditions this gate measures, what it explicitly does not verify, and the tier definitions. Takes no arguments and returns identical output every time. Read this before running a check so you know what a verdict does and does not claim.

Takes no parameters.

check_conformance

Check an MCP server for conformance and disclosure

Measure a public MCP endpoint against five conditions: it speaks MCP, it publishes an A2A agent card, it declares who pays it, identical input returns identical output, and the verdict itself can be recomputed by anyone. Free, no key. Conformance and disclosure only; this says nothing about whether any figure the checked server returns is correct. By default no tool on the checked server is called, so determinism comes back as not measured rather than guessed. It is measured when the owner has published /.well-known/mcp-conduct.json with allow_tool_call true.

Parametersendpointrequiredallow_tool_call

verify_verdict

Recompute a verdict hash without trusting the issuer

Take a verdict this gate issued and recompute its record_sha256 independently. Removes record_sha256 and recompute_note, serialises the remainder in key order, and hashes it. Returns whether the verdict was altered after it was issued. You do not have to trust the party that issued the verdict, including this one.

Parametersrecordrequired

lookup_server

Look up an MCP server on this register

Returns one record (not a list). Look up what this register already holds about an MCP endpoint: whether it is watched, how often it is re-measured, how many measurements exist, when the first and latest were taken, and the latest verdict with the record_sha256 you can recompute yourself. Reads stored measurements only. It contacts nothing and measures nothing, so use check_conformance for a fresh reading. An endpoint that is absent is reported as absent and that is NOT a negative verdict: it means nobody has measured it here, not that it failed.

Parametersendpointrequired

is_verified

One glance: is this MCP server verified, with proof

A single machine-first answer for an agent deciding whether to trust an MCP endpoint BEFORE it connects. Returns verified (true only when the latest scheduled measurement passed every measured condition; null otherwise, never false), a state enum saying which case it is, measured_at, and a record_sha256 with a recompute_url so you can check the verdict without trusting this gate. Reads the stored register only: it contacts nothing and measures nothing. Absent and pending are reported honestly and are NOT negative verdicts. For a fresh measurement rather than the stored one, use check_conformance.

Parametersendpointrequired

preflight_agent

Before delegating: check an A2A agent's card, who pays it, and its register reading

Call this before handing work to an A2A agent you have not used before. Fetches the agent's public card (https://<agent>/.well-known/agent-card.json, one request), reports whether it declares the A2A Conduct Extension, who it says pays it (the compensation declaration, as declared and not verified), whether the card carries a signature, the endpoints it asks to be measured on, and this register's stored reading for each (verified is true only when the latest scheduled measurement passed; null otherwise, never false), plus where to file your own witness walk. Measures nothing new and returns counts and pointers, never a score. An agent that does not declare the extension is reported as such, which is not a negative verdict.

Parametersagentrequired

Version history

8
  1. v0.4.24LatestNov 7, 2026
  2. v0.4.22Nov 5, 2026
  3. v0.4.20Sep 29, 2026
  4. v0.4.18Sep 28, 2026
  5. v0.4.17Sep 28, 2026
  6. v0.4.15Sep 26, 2026
  7. v0.4.14Sep 22, 2026
  8. v0.4.7Sep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

Other Check integrations