Skip to main content
Glama

Find an MCP tool

find_mcp_tool
Read-only

Search the tools that hosted MCP servers really expose (about 350,000, read live by Electra Index), by what they do, e.g. 'create an invoice', 'send an email', 'query postgres'. Returns the tool name, what it does, the server, whether it works without a key, its 30-day availability and whether the publisher is verified (official) or community. Max 10 results, 3 per server.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "find_mcp_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYesWhat the tool should do.
accessNo'open' = works without a key, 'key' = key or sign-in required.
officialNotrue = verified publisher domain only, false = community only.
capabilityNoOptional capability slug, e.g. 'payments', 'web-research'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=false; the description is consistent with a read-only index lookup and adds real context beyond them: the live Electra Index source, result caps (max 10, 3 per server), and the fields returned including availability and publisher verification. It does not discuss pagination or what happens when a query matches nothing, so it stops short of full disclosure.

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

Conciseness4/5

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

Front-loaded with the verb and scope, then examples, then return shape and limits — a sensible order. Minor padding in 'really expose' and the 'about 350,000' figure, but nothing that costs comprehension.

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

Completeness4/5

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

With no output schema, the description correctly carries the burden of describing return fields and result caps, and it explains the purpose of the two filter parameters. Only the capability slug and empty-result behavior remain underspecified.

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

Parameters4/5

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

Schema coverage is 80%, so the baseline is 3, but the description adds meaning: it clarifies that query is intent-based rather than a name match, and its return-field wording ('whether it works without a key', 'whether the publisher is verified') explains what the access and official filters actually select for. The capability parameter is only partially illuminated.

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

Purpose4/5

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

States a specific verb and resource: search the tool catalog of hosted MCP servers, with concrete example queries ('create an invoice', 'send an email'). The phrase 'tools that hosted MCP servers expose' implicitly separates it from server-level siblings like search_mcp_servers, but it never names an alternative explicitly.

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

Usage Guidelines3/5

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

Usage is conveyed only by example queries ('by what they do'), leaving the agent to infer that it should describe intent rather than pass a tool name. No when-not guidance or reference to the server-level siblings, which is a notable gap given several adjacent tools exist.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources