Skip to main content
Glama
chainfetch

ChainFETCH MCP Server

Official
by chainfetch

search_transactions_llm

Search Ethereum blockchain transactions using natural language queries. This tool interprets your questions to find relevant transactions from 254 available parameters.

Instructions

LLM-powered transaction search using LLaMA 3.2 3B to select from 254 parameters

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesNatural language query for transaction search

Implementation Reference

  • index.js:227-239 (registration)
    Registration of the 'search_transactions_llm' tool in the listTools response, including its description and input schema.
      name: 'search_transactions_llm',
      description: 'LLM-powered transaction search using LLaMA 3.2 3B to select from 254 parameters',
      inputSchema: {
        type: 'object',
        properties: {
          query: {
            type: 'string',
            description: 'Natural language query for transaction search',
          },
        },
        required: ['query'],
      },
    },
  • Input schema definition for the 'search_transactions_llm' tool, specifying a required 'query' string parameter.
    inputSchema: {
      type: 'object',
      properties: {
        query: {
          type: 'string',
          description: 'Natural language query for transaction search',
        },
      },
      required: ['query'],
    },
  • Handler for 'search_transactions_llm' tool: proxies the request to the ChainFetch API endpoint '/api/v1/ethereum/transactions/llm_search' using the makeRequest helper.
    case 'search_transactions_llm':
      return await this.makeRequest('/api/v1/ethereum/transactions/llm_search', 'GET', args, null, token);
  • The makeRequest helper method used by all tools, including 'search_transactions_llm', to make authenticated API calls to the ChainFetch service.
    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();
    }
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the LLM model and parameter count but doesn't describe what the search returns, how results are formatted, whether there are rate limits, authentication requirements, or any constraints on the natural language query. For a search tool with zero annotation coverage, this leaves significant gaps in understanding its behavior.

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?

The description is a single, efficient sentence that front-loads key information (LLM-powered transaction search) and includes relevant details (model, parameter count) without unnecessary words. Every element earns its place by clarifying the tool's unique approach.

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

Completeness2/5

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

Given the complexity of an LLM-powered search tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the search returns, how to interpret results, or any limitations (e.g., accuracy, speed). For a tool that likely processes complex queries, more context is needed 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?

Schema description coverage is 100%, with the single parameter 'query' documented as 'Natural language query for transaction search'. The description adds context by mentioning '254 parameters' (likely referring to searchable fields) and the LLM model, which provides some additional meaning beyond the schema. However, it doesn't elaborate on query syntax or examples, so baseline 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 performs 'LLM-powered transaction search' using a specific model (LLaMA 3.2 3B), which provides a specific verb ('search') and resource ('transactions'). It distinguishes itself from siblings like 'search_transactions_json' and 'search_transactions_semantic' by specifying the LLM-powered approach, though it doesn't explicitly contrast with all alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It mentions '254 parameters' but doesn't explain if this is an advantage over other search methods or when LLM-powered search is preferable to JSON or semantic approaches. No exclusions or prerequisites are stated.

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/chainfetch/chainfetch-mcp-server'

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