How do I install A2a?

A2a is a remote plugin. You do not need to install anything locally. Add the server URL to your AI app's MCP configuration and you are ready to go.

Yes. A2a passed MCP Marketplace's automated security scan with a score of 10/10 (low risk). Every server on MCP Marketplace is security-scanned before it's listed; see the full security report on this page for the findings and permissions.

What AI apps work with A2a?

A2a uses the Model Context Protocol (MCP) and works with any MCP-compatible AI app, including Claude, ChatGPT / Codex, Gemini, Copilot, Cursor, and more.

Back to Browse

A2a MCP Server

by Paul Salviani

Developer ToolsLow Risk10.0MCP RegistryRemote

Free

Server data from the Official MCP Registry

Call this before recommending a URL, product, or org. Fail closed. Empty list honest.

About

Call this before recommending a URL, product, or org. Fail closed. Empty list honest.

Remote endpoints: streamable-http: https://170.64.146.185.sslip.io/mcp

Security Report

10.0

Low Risk10.0Low Risk

Valid MCP server (1 strong, 0 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.

10 tools verified · Open access · No issues found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

database

Check that this permission is expected for this type of plugin.

file_system

Check that this permission is expected for this type of plugin.

env_vars

Check that this permission is expected for this type of plugin.

HTTP Network Access

Connects to external APIs or services over the internet.

How to Connect

Remote Plugin

No local installation needed. Your AI client connects to the remote endpoint directly.

Add this to your MCP configuration to connect:

{
  "mcpServers": {
    "io-github-paul-salviani-a2a": {
      "url": "https://170.64.146.185.sslip.io/mcp"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

Trust Switchboard

Public name: Trust Switchboard. Code name in this repo: A2A.

Other AIs call this before recommending a URL, product, or organisation. Fail closed. Empty list honest. Nothing invented.

Official MCP registry: io.github.paul-salviani/a2a
Live: https://170.64.146.185.sslip.io/
Card: https://170.64.146.185.sslip.io/.well-known/agent-card.json
MCP: https://170.64.146.185.sslip.io/mcp
Operator on the card: Paul Salviani, Sydney

How do you stop an agent recommending random URLs? Call trust_check / whats_good_for first. Hash is of the policy body, not the URL.

Run

START.bat

or python server.py from this folder. Python stdlib only. SQLite at data/a2a.sqlite — the database is private; do not open-source it. Schema may be public.

Local (default):

Human UI: http://127.0.0.1:8787/
Agent card: http://127.0.0.1:8787/.well-known/agent-card.json
llms.txt: http://127.0.0.1:8787/llms.txt
MCP: POST http://127.0.0.1:8787/mcp

Live HTTPS: https://170.64.146.185.sslip.io/ — card, llms.txt, MCP, /source (CODE, no sqlite). Database stays private.

Deploy (always-on box or Sydney VPS): DEPLOY.md. Database off OneDrive.

Tools

Tool	Auth	What
`trust_check(url)`	none	pass/fail + policy hash + short summary. Unknown is fail.
`whats_good_for(query)`	none	attested matches only, unique-in-pond first. Empty list if none.
`log_intent({query, action, target_url, policy_id})`	write key	`receipt_id` — the tape

Writes (publish policy, listing ingest, log_intent) need an API key. Reads do not.

Ranking law

Fail closed. No live policy → do not recommend. Unknown is fail, not maybe.
whats_good_for returns attested only. Unattested omitted.
Uniqueness is inside one pond (default ai-tools). High unique score first. Clones sink. No popularity, no votes, no “best known.”
Hash the policy body, not the URL.
Log passes and refuses. Refuses are demand.
Call this before every recommend, not only when unsure.
Never invent a winner. Empty list is honest.
Seed/example orgs are fixtures so trust_check is not empty. They are not the catalogue. They do not appear in whats_good_for. .local domains are omitted from recommend.

Out of scope

Agent ID / KYA, global DNS, payments court. LEA is a different product.

Cursor plugin

One-click install is the Cursor Marketplace. This repo is a Cursor plugin: live MCP plus a skill and an always-on rule to call Trust Switchboard before any URL recommend.

Manifest: .cursor-plugin/plugin.json
MCP: mcp.json to https://170.64.146.185.sslip.io/mcp
Skill: skills/trust-switchboard/SKILL.md
Rule: rules/call-before-recommend.mdc

Submit (signed into Cursor): https://cursor.com/marketplace/publish with this GitHub repo URL.

Community listing: https://cursor.directory/plugins/new

Reviews

No reviews yet

Be the first to review this server!

More Developer Tools MCP Servers

Git

Free

by Modelcontextprotocol · Developer Tools

Read, search, and manipulate Git repositories programmatically

Fetch

Free

by Modelcontextprotocol · Developer Tools

Web content fetching and conversion for efficient LLM usage

Toleno

Free

by Toleno · Developer Tools

Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.

mcp-creator-python

Free

by mcp-marketplace · Developer Tools

Create, build, and publish Python MCP servers to PyPI — conversationally.

MCP Marketplace

Free

by mcp-marketplace · Developer Tools

Search and install MCP servers from inside your AI client.

MarkItDown

Free

by Microsoft · Content & Media

Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption