Skip to main content
Glama

recommend-mcp-servers

Find external MCP servers tailored to your needs by entering a specific query. This tool analyzes requirements, searches online, and returns matching servers with IDs, descriptions, GitHub URLs, and similarity scores for informed decisions.

Instructions

Use this tool when there is a need to findn external MCP tools. It explores and recommends existing MCP servers from the internet, based on the description of the MCP Server needed. It returns a list of MCP servers with their IDs, descriptions, GitHub URLs, and similarity scores.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYes Description for the MCP Server needed. It should be specific and actionable, e.g.: GOOD: - 'MCP Server for AWS Lambda Python3.9 deployment' - 'MCP Server for United Airlines booking API' - 'MCP Server for Stripe refund webhook handling' BAD: - 'MCP Server for cloud' (too vague) - 'MCP Server for booking' (which booking system?) - 'MCP Server for payment' (which payment provider?) Query should explicitly specify: 1. Target platform/vendor (e.g. AWS, Stripe, MongoDB) 2. Exact operation/service (e.g. Lambda deployment, webhook handling) 3. Additional context if applicable (e.g. Python, refund events)

Implementation Reference

  • Handler logic for executing the 'recommend-mcp-servers' tool: parses input, fetches recommendations from COMPASS API, handles empty results, formats output as markdown text.
    if (name === "recommend-mcp-servers") {
      const { query } = GeneralArgumentsSchema.parse(args);
      const servers = await makeCOMPASSRequest(query);
    
      if (!servers || servers.length === 0) {
        return {
          content: [{
            type: "text",
            text: "No matching MCP servers found for your query. Try being more specific about the platform, operation, or service you need.",
          }],
        };
      }
    
      const serversText = await toServersText(servers);
      
      return {
        content: [
          {
            type: "text",
            text: serversText,
          },
        ],
      };
  • src/index.ts:36-72 (registration)
    Tool registration in the ListTools response, including name, detailed description, and input schema definition.
    {
      name: "recommend-mcp-servers",
      description: `
        Use this tool when there is a need to findn external MCP tools.
        It explores and recommends existing MCP servers from the 
        internet, based on the description of the MCP Server 
        needed. It returns a list of MCP servers with their IDs, 
        descriptions, GitHub URLs, and similarity scores.
        `,
      inputSchema: {
        type: "object",
        properties: {
          query: {
            type: "string",
            description: `
              Description for the MCP Server needed. 
              It should be specific and actionable, e.g.:
              GOOD:
              - 'MCP Server for AWS Lambda Python3.9 deployment'
              - 'MCP Server for United Airlines booking API'
              - 'MCP Server for Stripe refund webhook handling'
    
              BAD:
              - 'MCP Server for cloud' (too vague)
              - 'MCP Server for booking' (which booking system?)
              - 'MCP Server for payment' (which payment provider?)
    
              Query should explicitly specify:
              1. Target platform/vendor (e.g. AWS, Stripe, MongoDB)
              2. Exact operation/service (e.g. Lambda deployment, webhook handling)
              3. Additional context if applicable (e.g. Python, refund events)
              `,
          },
        },
        required: ["query"],
      },
    },
  • Zod schema for validating the tool's input arguments (query string). Used in handler for parsing.
    const GeneralArgumentsSchema = z.object({
      query: z.string().min(1),
    });
  • Helper function to make API request to COMPASS for MCP server recommendations based on query.
    const makeCOMPASSRequest = async (query: string): Promise<MCPServerResponse[]> => {
      try {
        const response = await fetch(`${COMPASS_API_BASE}/recommend?description=${encodeURIComponent(query)}`);
        
        if (!response.ok) {
          throw new Error(`COMPASS API request failed with status ${response.status}`);
        }
    
        const data = await response.json();
        return data as MCPServerResponse[];
      } catch (error) {
        console.error('Error fetching from COMPASS API:', error);
        throw error;
      }
    };
  • Helper function to format the list of recommended MCP servers into a readable text string with titles, descriptions, URLs, and similarity scores.
    const toServersText = async (servers: MCPServerResponse[]): Promise<string> => {
      if (servers.length === 0) {
        return "No MCP servers found.";
      }
    
      return servers.map((server, index) => {
        const similarityPercentage = (server.similarity * 100).toFixed(1);
        return [
          `Server ${index + 1}:`,
          `Title: ${server.title}`,
          `Description: ${server.description}`,
          `GitHub URL: ${server.github_url}`,
          `Similarity: ${similarityPercentage}%`,
          ''
        ].join('\n');
      }).join('\n');
    };
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool explores the internet and returns a list with IDs, descriptions, GitHub URLs, and similarity scores, which covers some behavioral aspects. However, it lacks details on rate limits, authentication needs, potential errors, or how the exploration works (e.g., API calls, web scraping). For a tool with no annotation coverage, this leaves significant gaps.

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?

The description is appropriately sized and front-loaded, starting with the usage context and then detailing the action and return values. It uses three sentences efficiently, with no wasted words, though it could be slightly more polished (e.g., 'findn' typo).

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

Completeness3/5

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

Given the tool's moderate complexity (1 parameter, no output schema, no annotations), the description is somewhat complete but has gaps. It explains the purpose, usage, and return format, but lacks behavioral details like error handling or exploration mechanics. Without annotations or an output schema, more context would be beneficial for an agent to use it effectively.

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?

The schema description coverage is 100%, providing detailed examples and requirements for the 'query' parameter. The description adds minimal value beyond this, only mentioning that it's 'based on the description of the MCP Server needed.' Since the schema does the heavy lifting, the baseline score of 3 is appropriate.

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 description clearly states the tool's purpose: 'explores and recommends existing MCP servers from the internet, based on the description of the MCP Server needed.' It specifies the verb (explores/recommends) and resource (MCP servers), though it doesn't need to differentiate from siblings since none exist. The purpose is specific but could be slightly more precise about the exploration mechanism.

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?

The description provides clear context for when to use the tool: 'when there is a need to find external MCP tools.' It explicitly ties usage to the query parameter's description of the needed MCP server. However, it doesn't mention when not to use it or alternatives, which isn't critical here since no siblings exist.

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

Related 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/liuyoshio/mcp-compass'

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