Find MCP - Agentage MCP Directory

Search the MCP directory

mcp_search

Read-only

Search the agentage MCP directory - a public catalog of Model Context Protocol servers crawled from the official registry - for servers matching a keyword, optionally narrowed by type, category, language, or license. Use this FIRST whenever the user wants to discover, find, compare, or pick an MCP server ("is there an MCP for X", "which MCP servers do Y"). Results are ranked by text relevance to the query first, then by popularity, so the best match is on top. Returns a page of lean cards (slug, title, description, category, transport, match_score - text relevance the ranking is based on, details_url). To read one server's full packages, tools, and install command, call mcp_get with the slug from a result; open a card's details_url for the human detail page. Valid category, language, and license values come from the mcp_categories tool, not from guesswork - call it before filtering and pass its labels verbatim, or the call is rejected. Read-only - never installs or runs anything.

Input Schema

TableJSON Schema

Name	Required	Description
`page`	No	Optional. 1-based page number; defaults to 1. Use pagination.total_pages to page.
`type`	No	Optional. Restrict to one distribution type: npm \| pypi \| oci \| mcpb \| nuget, or "remote" for hosted (HTTP) servers. Omit to search every type.
`limit`	No	Optional. Results per page; defaults to 20, capped at 50.
`query`	Yes	What to search for - a keyword, product, capability, or server name (e.g. "github", "postgres", "web search"). Matched across names, titles, and descriptions. Prefer a single distinctive term over a long phrase.
`license`	No	Optional. Restrict to a license, given either as an SPDX id ("MIT", "Apache-2.0") or as the full name mcp_categories lists ("MIT License"). Omit for no license filter.
`category`	No	Optional. Restrict to one category label. Valid values come from the mcp_categories tool - call it to get the exact labels (with counts) and pass one verbatim; anything else is rejected. Omit for no category filter.
`language`	No	Optional. Restrict to a repository language (e.g. "TypeScript", "Python"). Exact, case-sensitive; call mcp_categories for valid values. Omit for no language filter.

Output Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	The query the backend actually ran
`results`	Yes
`pagination`	Yes

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint/openWorldHint annotations, the description adds ranking behavior ('ranked by text relevance to the query first, then by popularity'), result card contents, and a hard rejection when invalid category values are passed. It also states 'Read-only - never installs or runs anything,' reinforcing the annotation without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Though longer than typical descriptions, every sentence carries distinct value: purpose, usage guidance, ranking behavior, return format, integration with siblings, filtering prerequisites, and safety. It is front-loaded with the core purpose and remains tightly structured with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 params, search semantics, pagination, sibling interactions) and the presence of an output schema, the description covers all necessary context: what to search, how results are ranked and returned, how to drill down via mcp_get, and filtering prerequisites. No critical operational detail is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema already provides detailed parameter descriptions (e.g., query guidance to 'Prefer a single distinctive term', category enums, license format). The description adds minor reinforcement by reminding the agent to call mcp_categories and pass labels verbatim, but that is already largely present in the schema. It does not significantly deepen parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource+scope: 'Search the agentage MCP directory ... for servers matching a keyword, optionally narrowed by type, category, language, or license.' This clearly distinguishes it from siblings mcp_get (fetch full details) and mcp_categories (get valid filter values).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use this FIRST whenever the user wants to discover, find, compare, or pick an MCP server' and directs to 'call mcp_get with the slug from a result' for full details, plus to call mcp_categories before filtering. This provides clear when/when-not guidance and names alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Find MCP - Agentage MCP Directory tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: mcp_categories lists filter values, mcp_search finds servers, and mcp_get retrieves full details for a single server. There is no overlap or ambiguity in their responsibilities.

Naming Consistency4/5

All tools use the mcp_ prefix, but the pattern is slightly mixed: mcp_search and mcp_get are verb-first, while mcp_categories is a noun. The convention is still predictable and readable, so this is a minor deviation.

Tool Count5/5

Three tools is exactly right for a directory service: one to discover filter options, one to search, and one to fetch details. No tool is redundant or missing.

Completeness5/5

The tools cover the complete read-only workflow for the domain: browse categories, search with filters, and inspect a server's full record. There are no dead ends or obvious gaps; the dependency between mcp_categories and mcp_search is well-documented.

Resources

Need Help?