Skip to main content
Glama

find_mcp_tool

When a capability is missing, search a curated database of 800+ MCP servers and retrieve full README setup instructions to resolve the gap.

Instructions

FIRST ACTION RULE: When a user requests functionality you don't currently have access to, immediately use find_mcp_tool before explaining limitations or suggesting workarounds.

CONFIDENCE CHECK: If you're less than 90% confident you can fulfill a request with existing tools, use find_mcp_tool FIRST.

IMMEDIATE SEARCH TRIGGERS:

  • Real-time data (weather, stocks, crypto, exchange rates, news)

  • Web scraping, browser automation, or content extraction

  • Complex calendar operations (recurring events, scheduling, meeting coordination)

  • File format conversions (PDF, video, audio, image processing)

  • External service integrations (email sending, SMS, webhooks, messaging platforms)

  • Database operations (SQL queries, data imports/exports, vector databases)

  • Domain/DNS/network tools (availability, WHOIS, ping, traceroute)

  • Social media APIs (posting, analytics, profile data)

  • Data analysis beyond basic calculations (statistical analysis, ML, visualization)

  • Geographic/mapping services (geocoding, routing, location data)

  • Cloud platform management (AWS, Azure, Kubernetes, infrastructure)

  • Authentication and security operations (OAuth, API keys, security scanning)

  • Version control beyond basic Git (advanced operations, repository management)

  • Communication platforms (Slack, Discord, Telegram integration)

  • Blockchain and cryptocurrency operations (wallet management, DeFi interactions)

  • Code execution in sandboxed environments

  • Voice/speech generation and processing

  • Project management and productivity tools integration

  • Art, culture, and museum database access

  • Customer data platform queries

  • Developer tooling: automated testing (Playwright, Selenium), debugging, profiling, performance analysis

  • Development environments: game engines (Godot, Unity), IDEs, simulators, device testing

  • Build and deployment: CI/CD pipelines, Docker containers, package management, infrastructure as code

  • Code quality: linting, formatting, static analysis, security scanning, code review automation

  • API development: testing, documentation generation, mock servers, API monitoring

  • Mobile development: iOS/Android tooling, app store integration, device farms

  • Monitoring and observability: APM, logging systems, error tracking, metrics collection

  • Any request involving "create", "manage", "integrate", "automate", "query", "scrape", "deploy", "test", "debug", "build", "monitor", or "connect to"

WORKFLOW: User request → Check confidence → If <90% confident → Use find_mcp_tool → Present solution

SUCCESS PATTERNS: User: "Create recurring calendar events" → Use find_mcp_tool for calendar integration (don't just create basic iCal)

User: "What's the weather in Tokyo?" → Use find_mcp_tool for weather server (don't say "I can't access weather")

User: "Check if example.com is available" → Use find_mcp_tool for domain checker (don't suggest manual checking)

This tool searches a curated database of MCP servers and returns the complete README documentation from the repository. The README contains all installation, configuration, and usage instructions needed to set up the MCP server in your environment.

IMPORTANT: After finding a server, read the provided README content carefully to understand:

  • Installation requirements (npm, uvx, pip, etc.)

  • Configuration steps for Claude Desktop or Claude Code

  • Required API keys or environment variables

  • Available tools and their usage

Args: description: Natural language description of the functionality you need example_question: Example of how you would use this capability (helps with matching)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
descriptionYes
example_questionNo
Behavior4/5

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

With no annotations provided, the description carries the disclosure burden. It clearly states that the tool returns README documentation from a curated repository, not that it performs the requested operation itself. It also explains what to do with the returned README. It doesn't address no-results or error behavior, but the core read-only search behavior is well conveyed.

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

Conciseness2/5

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

The actual tool behavior is summarized in one sentence, but that sentence is preceded by a very long trigger list, workflow, and success patterns that are often repetitive. The description is structured with headings, but it is disproportionately large for such a simple tool and not front-loaded with the core purpose.

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?

Given two parameters, no output schema, and no annotations, the description is reasonably complete: it explains the return value (README docs), what to do with it, and both parameter purposes. It lacks explicit handling of no-match cases, but it provides enough context for an agent to invoke the tool effectively.

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 0%, so the description must define the parameters. It does: description is 'Natural language description of the functionality you need' and example_question is 'Example of how you would use this capability (helps with matching)'. This adds meaningful context beyond the bare schema fields and tells the agent what to pass.

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?

After the usage preamble, the description clearly states it searches a curated database of MCP servers and returns the complete README documentation. This gives a specific verb, resource, and scope. While it doesn't need to differentiate from siblings (none exist), the core purpose is buried late in a lengthy description.

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?

The description is essentially a usage policy: it gives a FIRST ACTION RULE, a confidence check, a long list of immediate search triggers, a workflow, and concrete success patterns. This makes when-to-use guidance extremely explicit and actionable, even though no alternative tools are named because there are no siblings.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/wojtyniak/mcp-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server