Skip to main content
Glama

API-get_ai_intels_api_v1_ai_intel_get

Retrieve AI intelligence data from decentralized chains and social media via RSS3 API integration for natural language queries.

Instructions

Get Ai Intels

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • Generic handler for all MCP tools: locates the OpenAPI operation corresponding to the tool name via openApiLookup and executes it using the HttpClient, returning the JSON response. This handles the execution of 'API-get_ai_intels_api_v1_ai_intel_get'.
    // find operation const mcpToolWithClient = mcpToolWithClients.find( (t) => t.mcpTools.openApiLookup[name], ); if (!mcpToolWithClient) { throw new Error(`Method ${name} not found`); } const operation = mcpToolWithClient.mcpTools.openApiLookup[name]; // execute try { const response = await mcpToolWithClient.client.executeOperation( operation, params, ); return { content: [ { type: "text", // currently this is the only type that seems to be used by mcp server text: JSON.stringify(response.data), // TODO: pass through the http status code text? }, ], }; } catch (error) {
  • index.js:108-126 (registration)
    Dynamically registers all tools by iterating over MCP tools derived from OpenAPI specs, constructing tool names as `${toolName}-${method.name}` (truncated), which includes 'API-get_ai_intels_api_v1_ai_intel_get'.
    for (const mcpToolWithClient of mcpToolWithClients) { for (const [toolName, def] of Object.entries( mcpToolWithClient.mcpTools.tools, )) { for (const method of def.methods) { console.error("method", method); const toolNameWithMethod = `${toolName}-${method.name}`; const truncatedToolName = toolNameWithMethod.slice(0, 64); const trimmedDescription = method.description.split("Error")[0].trim(); tools.push({ name: truncatedToolName, description: trimmedDescription, inputSchema: { type: "object", properties: {}, }, }); } }
  • Special tool 'API-get-input-schema' that provides the actual input schema for any registered tool, including the target, by looking up the corresponding method.inputSchema from OpenAPI.
    if (name === "API-get-input-schema") { for (const mcpToolWithClient of mcpToolWithClients) { for (const [toolName, def] of Object.entries( mcpToolWithClient.mcpTools.tools, )) { for (const method of def.methods) { const toolNameWithMethod = `${toolName}-${method.name}`; const truncatedToolName = toolNameWithMethod.slice(0, 64); if (truncatedToolName === params.toolName) { return { content: [ { type: "text", text: JSON.stringify(method.inputSchema) }, ], }; } } } } throw new Error(`Method ${params.toolName} not found`); }
  • Converts OpenAPI specifications to MCP tools using OpenAPIToMCPConverter.convertToMCPTools(), creating the openApiLookup and tools used for registration and execution.
    const mcpToolWithClients = converterWithClients.map((cwc) => { const mcpTools = cwc.converter.convertToMCPTools(); return { mcpTools, client: cwc.client, }; });
  • Fetches OpenAPI specifications from RSS3 endpoints (including ai.rss3.io which likely defines the /api/v1/ai-intel/get endpoint) and initializes HttpClient for execution.
    const openApiSpecs = ( await Promise.allSettled([ fetch("https://gi.rss3.io/docs/openapi.json").then(async (res) => { if (!res.ok) throw new Error(`HTTP error! status: ${res.status}`); return res.json(); }), fetch("https://ai.rss3.io/openapi.json").then(async (res) => { if (!res.ok) throw new Error(`HTTP error! status: ${res.status}`); return res.json(); }), ]).then((results) => { return results.map((result) => { if (result.status === "fulfilled") { const client = new HttpClient( { baseUrl: result.value.servers[0].url, }, result.value, ); return { spec: result.value, client, }; } console.error("Failed to fetch openapi spec", result.reason); return null; }); }) ).filter(Boolean);

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/RSS3-Network/mcp-server-rss3'

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