a2a
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@a2aIs https://example.com trustworthy enough to recommend?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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/a2aCard: https://170.64.146.185.sslip.io/.well-known/agent-card.json
MCP:
https://170.64.146.185.sslip.io/mcpOperator 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.bator 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.
Related MCP server: url-safety-validator-mcp
Tools
Tool | Auth | What |
| none | pass/fail + policy hash + short summary. Unknown is fail. |
| none | attested matches only, unique-in-pond first. Empty list if none. |
| write key |
|
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_forreturns 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_checkis not empty. They are not the catalogue. They do not appear inwhats_good_for..localdomains 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.jsonMCP:
mcp.jsontohttps://170.64.146.185.sslip.io/mcpSkill:
skills/trust-switchboard/SKILL.mdRule:
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
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceURL intelligence for AI agents. One URL in, structured security and data quality signals out across 7 dimensions. 13 tools, risk score 0-100 with 23 configurable weights.161601MIT
- AlicenseAqualityAmaintenanceEnables AI agents to check URL safety before fetching content, using Google Web Risk, URLhaus, PhishTank, and AI analysis to return SAFE/SUSPICIOUS/DANGEROUS verdicts.13651MIT
- AlicenseNot gradedqualityDmaintenanceEnables verification of AI agent identity, authority, and integrity at transaction time, returning signed verdicts for allow, step-up, review, or block.MIT
Related MCP Connectors
Trust infrastructure for AI agents: read a verifiable Trust Rating, claim an identity, earn a badge.
Check if an AI agent is trustworthy. Sybil detection, signed attestations, 150,000+ agents. Free.
Evidence-backed x402 web verification for AI agents, with auditable decisions for every condition.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/paul-salviani/a2a'
If you have feedback or need assistance with the MCP directory API, please join our Discord server