mcp-trust-index
Registry code: 51080b4ebbe661e3
The MCP Trust Index is a curated, trust-first shortlist of MCP servers published by StaaS Fund. Every listed server passed a 5-gate screen (maturity, security, maintenance, identity, interoperability) and is scored 0-100 into tiers: enterprise-verified (80+), recommended (60-79), emerging (40-59). Use search_servers to find servers by need, get_server for one server’s full record including caveats, get_rubric for the methodology, get_watchlist for closed/hosted vendor servers we deliberately do not score, and get_changelog for what changed and why. Listings are re-verified monthly; treat…
- endpoint
- https://staas.fund/mcp/server
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is mcp-trust-index live?
- Yes — it answered the hub's last check (checked 47m ago). It answered 100% of checks over the last 30 days.
- Is mcp-trust-index free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does mcp-trust-index have?
- 5 tools: get_server, get_rubric, get_changelog, search_servers, get_watchlist.
- Is mcp-trust-index safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 99.1%· all time 99.1%
last good check
of 5 tools
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- degraded → live
- live → degraded· timeout after 20000ms
- topic
- developer tools
- used for
- search vetted mcp servers
- get an mcp server trust score
- read trust scoring methodology
- takes → gives
- text → data, text
- tools
- 5 reads
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
get_server reads open 14h ago
Full Trust Index record for a single listed server: score, tier, publisher, description with caveats, category, install command, and links. Name is matched case-insensitively.
{ "type": "object", "required": [ "name" ], "properties": { "name": { "type": "string", "description": "Server name, e.g. \"Playwright\" or \"context7\"" } } }arguments 12 linesget_rubric reads open 47m ago
The full MCP Trust Index methodology as markdown: the 5 gates every server must pass, the 4 scoring dimensions, trust tiers, and editorial policies.
{ "type": "object", "properties": {} }arguments 4 linesget_changelog reads open 47m ago
Public log of every addition, removal, and re-score on the Trust Index, with reasoning.
{ "type": "object", "properties": {} }arguments 4 linessearch_servers reads open 14h ago
Search the MCP Trust Index for vetted MCP servers. Filter by free-text query (matched against name, publisher, description, and category), category, and/or trust tier. Returns compact records sorted by score. Call with no arguments to list the entire index.
{ "type": "object", "properties": { "tier": { "type": "string", "description": "enterprise-verified | recommended | emerging" }, "query": { "type": "string", "description": "Free-text filter, e.g. \"postgres\", \"browser\", \"search\"" }, "category": { "type": "string", "description": "One of: Database, Developer Tools, File Systems, Search, Productivity, CRM/Business, Cloud, Monitoring, AI/ML" } } }arguments 17 linesget_watchlist reads open 47m ago
Servers the Index deliberately does not score: closed-source hosted vendor endpoints and platform-native MCP capabilities (no inspectable code to gate), plus open servers being watched that have not yet passed the gates.
{ "type": "object", "properties": {} }arguments 4 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id51080b4ebbe661e3.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/51080b4ebbe661e3/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/51080b4ebbe661e3?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.