Skip to main content
Glama
chainfetch

ChainFETCH MCP Server

Official
by chainfetch

search_blocks_semantic

Find blockchain blocks using AI-powered semantic search that understands natural language queries about Ethereum data.

Instructions

Semantic search for blocks using AI-powered vector similarity matching

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe query to search for
limitNoThe number of results to return (default: 10)

Implementation Reference

  • Handler implementation for the 'search_blocks_semantic' tool. It proxies the tool call to the ChainFETCH API endpoint '/api/v1/ethereum/blocks/semantic_search' using a GET request with the provided arguments.
    case 'search_blocks_semantic':
      return await this.makeRequest('/api/v1/ethereum/blocks/semantic_search', 'GET', args, null, token);
  • Input schema definition for the 'search_blocks_semantic' tool, specifying required 'query' parameter and optional 'limit'.
    inputSchema: {
      type: 'object',
      properties: {
        query: {
          type: 'string',
          description: 'The query to search for',
        },
        limit: {
          type: 'integer',
          description: 'The number of results to return (default: 10)',
          default: 10,
        },
      },
      required: ['query'],
    },
  • index.js:270-287 (registration)
    Registration of the 'search_blocks_semantic' tool in the MCP tools array passed to server.setTools().
      name: 'search_blocks_semantic',
      description: 'Semantic search for blocks using AI-powered vector similarity matching',
      inputSchema: {
        type: 'object',
        properties: {
          query: {
            type: 'string',
            description: 'The query to search for',
          },
          limit: {
            type: 'integer',
            description: 'The number of results to return (default: 10)',
            default: 10,
          },
        },
        required: ['query'],
      },
    },
  • Helper function 'makeRequest' used by the handler to perform authenticated HTTP requests to the ChainFETCH API.
    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();
    }

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