Skip to main content
Glama

discover_tools

Find analysis tools for your data or question. Uses semantic search across statistical and ML tools to match your dataset and query.

Instructions

Find analysis tools matching your data or question. Semantic search across 50+ statistical and ML tools.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoText query describing what you want to analyze
datasetNoDataset UUID to match tools against

Implementation Reference

  • src/index.js:43-63 (registration)
    STATIC_TOOLS array defining the static catalog of tools. 'discover_tools' is registered at line 45 as one of the available tools.
    const STATIC_TOOLS = [
      { name: "about", description: "Get platform info, pricing, usage stats, or documentation.", inputSchema: { type: "object", properties: { topic: { type: "string", description: "Topic: platform, pricing, current_usage, manual, or a docs section" } }, required: ["topic"] } },
      { name: "discover_tools", description: "Find analysis tools matching your data or question. Semantic search across 50+ statistical and ML tools.", inputSchema: { type: "object", properties: { query: { type: "string", description: "Text query describing what you want to analyze" }, dataset: { type: "string", description: "Dataset UUID to match tools against" } } } },
      { name: "tools_schema", description: "Get JSON schema for a tool — column_mapping and module_parameters required before tools_run.", inputSchema: { type: "object", properties: { tool_name: { type: "string", description: "Name of the tool" } }, required: ["tool_name"] } },
      { name: "tools_run", description: "Execute an analysis tool. Returns a shareable interactive HTML report URL.", inputSchema: { type: "object", properties: { tool_name: { type: "string", description: "Name of the tool to execute" }, taskList: { type: "object", description: "Contains inputs: dataset, userContext, column_mapping, module_parameters" } }, required: ["tool_name", "taskList"] } },
      { name: "tools_info", description: "Get detailed information about a specific analysis tool — use cases, assumptions, data requirements.", inputSchema: { type: "object", properties: { tool_name: { type: "string", description: "Name of the tool" } }, required: ["tool_name"] } },
      { name: "datasets_upload", description: "Generate a secure upload token for CSV files. Returns UUID + curl command for the user.", inputSchema: { type: "object", properties: { expires_in: { type: "integer", description: "Token expiration in seconds", default: 300 } } } },
      { name: "datasets_list", description: "List and search uploaded datasets with fuzzy matching.", inputSchema: { type: "object", properties: { search: { type: "string", description: "Search by name, description, or tags" }, limit: { type: "integer", description: "Max results", default: 20 } } } },
      { name: "datasets_read", description: "Read dataset contents — preview rows, columns, and types.", inputSchema: { type: "object", properties: { uuid: { type: "string", description: "Dataset UUID" }, secret: { type: "string", description: "Dataset secret key" }, rows: { type: "integer", description: "Number of rows to preview", default: 10 } }, required: ["uuid"] } },
      { name: "datasets_download", description: "Generate a single-use download token for securely downloading datasets.", inputSchema: { type: "object", properties: { uuid: { type: "string", description: "Dataset UUID" } }, required: ["uuid"] } },
      { name: "datasets_update", description: "Update dataset metadata — name, description, tags, visibility.", inputSchema: { type: "object", properties: { uuid: { type: "string", description: "Dataset UUID" } }, required: ["uuid"] } },
      { name: "connectors_list", description: "List available data connectors — GA4, Google Search Console, and more.", inputSchema: { type: "object", properties: {} } },
      { name: "connectors_query", description: "Pull live data from a connected source using connector:// URIs.", inputSchema: { type: "object", properties: { uri: { type: "string", description: "Connector URI (e.g., connector://mcpanalytics_gsc/search_analytics?...)" } }, required: ["uri"] } },
      { name: "reports_list", description: "List analysis reports with metadata.", inputSchema: { type: "object", properties: { limit: { type: "integer", description: "Max results", default: 10 } } } },
      { name: "reports_search", description: "Search reports by job ID, tool name, or keyword.", inputSchema: { type: "object", properties: { query: { type: "string", description: "Search query" }, job_ids: { type: "array", items: { type: "string" }, description: "Filter by processing IDs" } } } },
      { name: "reports_view", description: "View a specific report by processing ID.", inputSchema: { type: "object", properties: { processing_id: { type: "string", description: "Processing ID from tools_run" } }, required: ["processing_id"] } },
      { name: "report_cards", description: "Get individual card data from a report for rendering.", inputSchema: { type: "object", properties: { processing_id: { type: "string" } }, required: ["processing_id"] } },
      { name: "agent_advisor", description: "Conversational AI that guides analysis and interprets results.", inputSchema: { type: "object", properties: { message: { type: "string", description: "Your question or request" } }, required: ["message"] } },
      { name: "billing", description: "Check credit balance, subscription status, or open billing portal.", inputSchema: { type: "object", properties: { action: { type: "string", enum: ["status", "portal", "usage"], description: "Billing action", default: "status" } } } },
      { name: "module_request", description: "Request a custom analysis module to be built for your use case.", inputSchema: { type: "object", properties: { description: { type: "string", description: "Describe the analysis you need" } }, required: ["description"] } },
    ];
  • CallToolRequestSchema handler: proxies all tool calls (including discover_tools) to the remote MCP server via remoteClient.callTool() when connected. There is no local implementation — the actual logic lives on the remote server.
    server.setRequestHandler(CallToolRequestSchema, async (request) => {
      if (!remoteClient) {
        return {
          content: [
            {
              type: "text",
              text: "MCP Analytics API key required. Set MCP_ANALYTICS_API_KEY in your environment.\nGet a free key at https://app.mcpanalytics.ai",
            },
          ],
          isError: true,
        };
      }
    
      try {
        const result = await remoteClient.callTool({
          name: request.params.name,
          arguments: request.params.arguments || {},
        });
        return result;
      } catch (err) {
        return {
          content: [{ type: "text", text: `Error: ${err.message}` }],
          isError: true,
        };
      }
    });
  • Input schema for discover_tools: accepts 'query' (string, semantic search text) and 'dataset' (string, dataset UUID to match tools against). No properties are required.
    { name: "discover_tools", description: "Find analysis tools matching your data or question. Semantic search across 50+ statistical and ML tools.", inputSchema: { type: "object", properties: { query: { type: "string", description: "Text query describing what you want to analyze" }, dataset: { type: "string", description: "Dataset UUID to match tools against" } } } },
Behavior3/5

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

No annotations provided. The description indicates a search operation but does not disclose security requirements, rate limits, or what happens with empty results. It is minimally transparent.

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?

Single sentence, zero wasted words, front-loaded with the primary action.

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?

The tool has 2 parameters and no output schema. The description fails to specify the output format (e.g., list of tool names/details), leaving the agent uncertain about what to expect. Some additional context would be beneficial.

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?

Both parameters have descriptions in the schema (100% coverage). The description does not add substantial meaning beyond the schema, such as how the two parameters interact or which is more important.

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 clearly states the verb 'Find' and resource 'analysis tools', and mentions 'semantic search', distinguishing it from sibling tools like tools_info (which lists tools) and tools_run (which executes tools).

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?

The description implies usage when needing to find tools matching a query, but does not specify when not to use it or mention alternatives (e.g., tools_info for browsing all tools).

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/embeddedlayers/mcp-analytics'

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