Pryno MCP
OfficialClick on "Deploy 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., "@Pryno MCP find MCP servers for postgres and show readiness scores"
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.
Pryno MCP
Pryno MCP is a remote Model Context Protocol server. It lets any MCP client search the Pryno directory of public MCP servers and score a website for AI-agent readiness.
The directory is filled by a separate private crawler. This server only reads that database. It does not crawl, and it does not store CRM credentials.
Remote endpoint:
https://mcp.pryno.ai/mcpSource: github.com/Pryno-ai/pryno-mcp
Website: pryno.ai
Tools
Tool | What it does |
| Search by text, category, transport, language, official servers, or remote servers. |
| Full record for one slug, including packages and stdio install hints. |
| Categories and how many servers are in each. |
| Total servers, servers added in the last 7 days, and the last crawl time. |
| Score a public URL from 0 to 100. |
Every tool is read-only. Search and lookup results include readiness_score and last_checked_at when the crawler has stored them.
Example: search for Postgres, then open one result.
{ "query": "postgres", "limit": 5 }{ "slug": "example-postgres" }{ "url": "https://www.pryno.ai" }The readiness check fetches public files only (llms.txt, llms-full.txt, robots.txt, OpenAPI, API docs, MCP discovery, and schema.org JSON-LD). It returns pass or fail with a short summary of our own. It does not return excerpts from the target site. Private, loopback, and link-local addresses are rejected.
Resources:
pryno://directory/categoriespryno://server/{slug}
Prompt: find_mcp_server.
Related MCP server: agentalmanac-mcp
Connect
The remote URL for every client is https://mcp.pryno.ai/mcp. No API key is required.
Claude
Add a custom connector with the remote MCP URL https://mcp.pryno.ai/mcp.
ChatGPT
In developer mode, add a remote MCP server with the URL https://mcp.pryno.ai/mcp.
Cursor
{
"mcpServers": {
"pryno": {
"url": "https://mcp.pryno.ai/mcp"
}
}
}VS Code
{
"servers": {
"pryno": {
"type": "http",
"url": "https://mcp.pryno.ai/mcp"
}
}
}Local stdio
The database URL belongs in the environment that launches the process. Do not commit it.
{
"mcpServers": {
"pryno": {
"command": "npx",
"args": ["-y", "pryno-mcp"],
"env": {
"DATABASE_URL": "postgres://directory_reader@localhost:5432/pryno"
}
}
}
}You can also point the MCP Inspector at a local HTTP server:
npm run build
npm start
npx @modelcontextprotocol/inspectorConnect the inspector to http://localhost:3000/mcp.
Self-hosting
The server listens on PORT and exposes:
GET /a short descriptionGET /healthdatabase ping and schema statusPOST /mcpthe Streamable HTTP endpointGET /mcp/server-cardthe MCP server cardGET /.well-known/ai-catalog.jsona catalog entry that points at the card
docker build -t pryno-mcp .
docker run --rm -p 3000:3000 --env-file .env pryno-mcpOn Railway, use the included Dockerfile and railway.json. Keep the project private. Set variables in Railway, not in git.
This process expects the crawler's schema and a directory_reader role with SELECT only. It does not run migrations. Until those tables exist, /health still succeeds when SELECT 1 works, and the directory tools explain that the schema is not ready. run_readiness_check does not need the database.
readiness_score and last_checked_at are columns the crawler stores on servers. If they are missing, the schema is reported as incomplete.
Environment
Copy .env.example to .env. Never commit .env.
Variable | Required | Purpose |
| For directory tools | Postgres URL for the |
| No | HTTP port. Defaults to 3000. Railway sets this. |
| No | Public origin used in the server card. Defaults to |
| No | Per-IP limit for |
| No | When set, |
Development
npm ci
npm test
npm run typecheck
npm run lintTests cover tool schemas, the search query builder, the SSRF guard, and readiness scoring. They use a mocked database and do not call the network.
Available Tools
5 toolsdirectory_statsDirectory statsARead-onlyIdempotent
Return how many MCP servers are in the directory, how many were added in the last 7 days, and when the crawler last finished.
Inputs: no named parameters. Returns: last_crawl_at, total_servers, added_last_7_days
get_mcp_serverGet MCP serverARead-onlyIdempotent
Look up one MCP server by its directory slug. Returns packages, stdio install hints, the remote endpoint, license, last activity, sources, readiness score, and when that score was last checked.
Inputs: slug (required). Returns: name, slug, tags, stars, +19 more
list_categoriesList categoriesARead-onlyIdempotent
List MCP directory categories and how many servers are in each.
Inputs: no named parameters. Returns: categories
run_readiness_checkRun readiness checkARead-onlyIdempotent
Score a public website from 0 to 100 for AI-agent readiness. The result lists each check as pass or fail with a short summary and the highest-value fixes. It does not return page excerpts.
Inputs: url (required). Returns: url, host, note, fixes, +2 more
search_mcp_serversSearch MCP serversBRead-onlyIdempotent
Search the Pryno MCP directory. Results include the name, slug, a one-line description, repository, remote URL, transports, stars, categories, readiness score, and when that score was last checked.
Inputs: limit, query, cursor, category, +4 more. Returns: servers, next_cursor
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a distinct target: directory browsing (list_categories), querying (search_mcp_servers), single lookup (get_mcp_server), aggregate metrics (directory_stats), and an external scoring function (run_readiness_check). The only mild overlap is between list_categories and directory_stats, both of which surface counts, and between the 'readiness score' returned by lookup tools versus the standalone check tool. Descriptions make the boundary clear enough that misselection is unlikely.
Four of five names follow a verb_noun or verb_object pattern (list_categories, search_mcp_servers, get_mcp_server, run_readiness_check) with consistent snake_case. directory_stats breaks the pattern by being noun-only with no verb, a minor deviation. Overall readable and predictable.
Five tools is a tight, well-scoped surface for a read-only directory server: browse, search, lookup, aggregate stats, and one scoring utility. No tool appears redundant or padded, and nothing feels conspicuously absent at the count level.
The read-only lifecycle of a directory is well covered: discovery via search, detail via get, taxonomy via list_categories, and health via directory_stats. Minor gaps exist — there's no explicit way to enumerate servers within a category (you must fall back to search) and no compare/batch lookup, but agents can work around these.
Maintenance
Related MCP Connectors
Search a nightly-refreshed directory of MCP servers by keyword, category or topic.
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
Live index of AI agents, MCP servers and tools with observed liveness and capability search.
Search a directory of 550+ MCP servers, Codex/ChatGPT/Claude plugins and agent skills.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI assistants to search, compare, and get detailed information about MCP servers from the mcpcatalogs.com directory.45 npmMIT
- AlicenseAqualityDmaintenanceEnables searching and retrieving details of 9,000+ MCP servers from the Agent Almanac catalog, allowing agents to discover, inspect, and install tools directly.353 npmMIT
- FlicenseNot gradedqualityDmaintenanceFinds the right MCP server for a task from over 1,400 indexed servers ranked by community trust. Also provides outcome-ranked web search for AI agents with no API key or rate limits.4-

Socketlist MCP serverofficial
AlicenseNot gradedqualityCmaintenanceEnables AI assistants to search and browse an independent directory of 800+ open-source MCP servers by keyword, category, or use case, and to fetch individual server details, README-derived features and requirements, and known install configs. All tools are read-only, require no authentication, and are served over streamable HTTP.MIT