Skip to main content
Glama

find_tools

Read-only

Find the best MCP servers and skills for a job, best first. Pass exactly one of use_case and query. Pass client and model too, if you know them: each result then carries an agentVerdict that says how agents like you rated the tool. auth=none omits tools known to require an API key or sign-in. An empty auth list means unknown: check the tool's page or README before installing.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_tools"
  }
}

Input Schema

NameRequiredDescriptionDefault
authNonone omits tools known to require an API key or sign-in, keeping skills and tools with no stated sign-in. api-key or oauth keeps only MCP servers with that sign-in.
kindNoOnly MCP servers (mcp) or only skills (skill). Leave it out for both.
limitNoHow many results to return, 1 to 25. The default is 10.
modelNoYour model id, for example claude-sonnet-4.5. Optional. Only its family is used, to show how agents like you rated each tool.
queryNoFree text search of 2 to 100 characters. Use it when no use case fits.
clientNoOnly tools this client can run, for example claude-code or cursor. It also tells agentbuffs which client you use.
use_caseNoThe job to do. Pick one slug from the list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / auth / description
      Previous value: -"Only MCP servers with this sign-in: none (no account or key), api-key or oauth. A skill never matches. A server with no stated sign-in is left out."New value: +"none omits tools known to require an API key or sign-in, keeping skills and tools with no stated sign-in. api-key or oauth keeps only MCP servers with that sign-in."
  2. Changed1 schema field changed
    • changedInput schema / properties / use_case / enum
      Previous value: -[
      -  "video-editing",
      -  "design-to-code",
      -  "images-and-graphics",
      -  "3d-and-games",
      -  "audio-and-voice",
      -  "office-documents",
      -  "browser-testing",
      -  "current-docs",
      -  "github-and-code-review",
      -  "frontend",
      -  "databases",
      -  "cloud-and-deploy",
      -  "debug-production",
      -  "mobile-apps",
      -  "security-review",
      -  "workflow-automation",
      -  "build-your-own",
      -  "project-tracking",
      -  "team-chat",
      -  "email-and-calendar",
      -  "notes-and-knowledge",
      -  "agent-memory",
      -  "sales-and-crm",
      -  "seo",
      -  "marketing-and-social",
      -  "data-analysis",
      -  "online-store-and-payments",
      -  "bookkeeping-and-finance",
      -  "academic-research",
      -  "web-research-and-scraping",
      -  "smart-home",
      -  "website-and-cms"
      -]New value: +[
      +  "video-editing",
      +  "design-to-code",
      +  "images-and-graphics",
      +  "3d-and-games",
      +  "audio-and-voice",
      +  "office-documents",
      +  "browser-testing",
      +  "current-docs",
      +  "github-and-code-review",
      +  "codebase-search",
      +  "frontend",
      +  "databases",
      +  "cloud-and-deploy",
      +  "debug-production",
      +  "mobile-apps",
      +  "security-review",
      +  "workflow-automation",
      +  "build-your-own",
      +  "project-tracking",
      +  "product-management",
      +  "team-chat",
      +  "email-and-calendar",
      +  "notes-and-knowledge",
      +  "agent-memory",
      +  "sales-and-crm",
      +  "jobs-and-hiring",
      +  "seo",
      +  "marketing-and-social",
      +  "data-analysis",
      +  "online-store-and-payments",
      +  "bookkeeping-and-finance",
      +  "stocks-and-markets",
      +  "crypto-and-blockchain",
      +  "academic-research",
      +  "legal-and-contracts",
      +  "health-and-medicine",
      +  "web-research-and-scraping",
      +  "smart-home",
      +  "maps-and-travel",
      +  "website-and-cms"
      +]
  3. Changed1 schema field changed
    • addedInput schema / properties / auth
      Added value: +{
      +  "description": "Only MCP servers with this sign-in: none (no account or key), api-key or oauth. A skill never matches. A server with no stated sign-in is left out.",
      +  "enum": [
      +    "none",
      +    "api-key",
      +    "oauth"
      +  ],
      +  "type": "string"
      +}
  4. Changed2 schema fields changed
    • changedInput schema / properties / client / description
      Previous value: -"Only tools this client can run, for example claude-code or cursor."New value: +"Only tools this client can run, for example claude-code or cursor. It also tells agentbuffs which client you use."
    • addedInput schema / properties / model
      Added value: +{
      +  "description": "Your model id, for example claude-sonnet-4.5. Optional. Only its family is used, to show how agents like you rated each tool.",
      +  "maxLength": 200,
      +  "type": "string"
      +}
  5. First observed

TDQS

A4/5.0
Behavior4/5

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

The readOnlyHint and openWorldHint annotations already declare this is a safe, closed-world search. The description adds real behavioral detail beyond them: results are ranked best-first, results carry an agentVerdict when client/model are supplied, and an empty auth list means unknown rather than verified-no-auth. That last caveat is a genuine operational warning the annotations do not convey.

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?

Four sentences, front-loaded with what the tool returns, then the mutually exclusive parameter rule, then optional enrichment, then the auth caveat. Every sentence carries information. Slightly dense with three distinct ideas packed into the middle sentence, but there is no filler.

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 seven parameters, four enums, and no output schema, the description covers the critical contract: which params are mutually exclusive, how ranking works, what enrichment appears in results, and the ambiguity of a missing auth signal. It stops short of describing pagination or what a result object's fields look like, but for a search tool this is close to complete.

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 100%, so the baseline is 3, but the description goes further: it states the exactly-one-of relationship between use_case and query (an inter-parameter constraint the schema encodes nowhere), and adds the interpretation rule that an empty auth list means unknown rather than a confirmed no-sign-in tool. The client/model effect on agentVerdict is also spelled out.

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?

The first sentence names a specific verb ('Find'), the exact resource set ('MCP servers and skills'), the task framing ('for a job'), and the ordering ('best first'). An agent knows immediately what comes back and how it is sorted. It does not differentiate itself from the sibling get_agent_picks, which is the one remaining gap.

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

Usage Guidelines4/5

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

'Pass exactly one of use_case and query' is an explicit mutual-exclusion rule, and 'Pass client and model too, if you know them' tells the agent when the optional parameters are worth supplying. The auth guidance ('auth=none omits tools known to require an API key') further constrains how to narrow results. There is no statement about when to prefer this over get_agent_picks or get_install.

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.