MCP Trust Index
Curated, trust-first index of vetted MCP servers — scored tiers, monthly re-verified. Read-only.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"mcp-trust-index": {
"url": "https://staas.fund/mcp/server"
}
}
}Remote endpoints
https://staas.fund/mcp/serverstreamable-httpWhat it can do
Tool inventory
Tools (5)
🟢search_servers(query, category, tier)
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.
Input Schema
{
"type": "object",
"properties": {
"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"
},
"tier": {
"type": "string",
"description": "enterprise-verified | recommended | emerging"
}
}
}🟢get_server(name)
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.
Input Schema
{
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Server name, e.g. \"Playwright\" or \"context7\""
}
},
"required": [
"name"
]
}🟢get_rubric
The full MCP Trust Index methodology as markdown: the 5 gates every server must pass, the 4 scoring dimensions, trust tiers, and editorial policies.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_watchlist
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.
Input Schema
{
"type": "object",
"properties": {}
}🟢get_changelog
Public log of every addition, removal, and re-score on the Trust Index, with reasoning.
Input Schema
{
"type": "object",
"properties": {}
}Community
Evidence