Skip to main content
Glama
chainfetch

ChainFETCH MCP Server

Official
by chainfetch

search_blocks_llm

Search Ethereum blockchain blocks using natural language queries. LLM-powered tool analyzes 120+ parameters to find relevant blocks based on your search terms.

Instructions

LLM-powered block search using LLaMA 3.2 3B to select from 120+ parameters

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesNatural language query for block search

Implementation Reference

  • Schema definition for the search_blocks_llm tool, including name, description, and input schema requiring a natural language query.
    { name: 'search_blocks_llm', description: 'LLM-powered block search using LLaMA 3.2 3B to select from 120+ parameters', inputSchema: { type: 'object', properties: { query: { type: 'string', description: 'Natural language query for block search', }, }, required: ['query'], },
  • Handler implementation for search_blocks_llm tool. It calls the makeRequest helper to proxy the tool arguments to the ChainFetch API endpoint /api/v1/ethereum/blocks/llm_search.
    case 'search_blocks_llm': return await this.makeRequest('/api/v1/ethereum/blocks/llm_search', 'GET', args, null, token);
  • Shared helper method makeRequest that performs authenticated HTTP requests to the ChainFetch API, used by the search_blocks_llm handler and all other tools.
    async makeRequest(endpoint, method = 'GET', params = {}, body = null, token = null) { const chainfetchToken = token || process.env.CHAINFETCH_API_TOKEN; if (!chainfetchToken) { throw new McpError( ErrorCode.InvalidRequest, 'CHAINFETCH_API_TOKEN is required' ); } const url = new URL(`${API_BASE_URL}${endpoint}`); // Add query parameters for GET requests if (method === 'GET' && Object.keys(params).length > 0) { Object.entries(params).forEach(([key, value]) => { if (value !== undefined && value !== null) { if (Array.isArray(value)) { value.forEach(v => url.searchParams.append(`${key}[]`, v)); } else { url.searchParams.append(key, value.toString()); } } }); } const fetchOptions = { method, headers: { 'Authorization': `Bearer ${chainfetchToken}`, 'Content-Type': 'application/json', }, }; if (body && method !== 'GET') { fetchOptions.body = JSON.stringify(body); } const response = await fetch(url.toString(), fetchOptions); if (!response.ok) { const errorText = await response.text(); throw new McpError( ErrorCode.InternalError, `API request failed: ${response.status} ${response.statusText} - ${errorText}` ); } return await response.json(); }
  • index.js:612-631 (registration)
    Registration of the CallToolRequestSchema handler, which dispatches to handleToolCall based on tool name, enabling execution of search_blocks_llm.
    this.server.setRequestHandler(CallToolRequestSchema, async (request) => { const { name, arguments: args } = request.params; try { const result = await this.handleToolCall(name, args, this.currentToken); return { content: [ { type: 'text', text: JSON.stringify(result, null, 2), }, ], }; } catch (error) { throw new McpError( ErrorCode.InternalError, `Tool execution failed: ${error.message}` ); } });

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/chainfetch/chainfetch-mcp-server'

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