Skip to main content
Glama
Pryno MCP

Pryno MCP

Official
by Pryno-ai

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.

Tools

Tool

What it does

search_mcp_servers

Search by text, category, transport, language, official servers, or remote servers.

get_mcp_server

Full record for one slug, including packages and stdio install hints.

list_categories

Categories and how many servers are in each.

directory_stats

Total servers, servers added in the last 7 days, and the last crawl time.

run_readiness_check

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/categories

  • pryno://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/inspector

Connect the inspector to http://localhost:3000/mcp.

Self-hosting

The server listens on PORT and exposes:

  • GET / a short description

  • GET /health database ping and schema status

  • POST /mcp the Streamable HTTP endpoint

  • GET /mcp/server-card the MCP server card

  • GET /.well-known/ai-catalog.json a catalog entry that points at the card

docker build -t pryno-mcp .
docker run --rm -p 3000:3000 --env-file .env pryno-mcp

On 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

DATABASE_URL

For directory tools

Postgres URL for the directory_reader role.

PORT

No

HTTP port. Defaults to 3000. Railway sets this.

PUBLIC_URL

No

Public origin used in the server card. Defaults to https://mcp.pryno.ai.

RATE_LIMIT_PER_MIN

No

Per-IP limit for /mcp. Defaults to 60. Readiness checks use a tighter limit.

READINESS_CHECK_URL

No

When set, run_readiness_check POSTs { "url" } to this https endpoint instead of scoring locally.

Development

npm ci
npm test
npm run typecheck
npm run lint

Tests 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 tools
directory_statsDirectory statsA
Read-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 serverA
Read-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 categoriesA
Read-onlyIdempotent

List MCP directory categories and how many servers are in each.

Inputs: no named parameters. Returns: categories

run_readiness_checkRun readiness checkA
Read-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 serversB
Read-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

    A3.8/5.0

    Scored across 5 tools

    Disambiguation4/5

    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.

    Naming Consistency4/5

    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.

    Tool Count5/5

    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.

    Completeness4/5

    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

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI assistants to search, compare, and get detailed information about MCP servers from the mcpcatalogs.com directory.
      4
      5 npm
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Finds 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
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables 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