Tracxn MCP Server
# Tracxn MCP Server
A Model Context Protocol (MCP) server that wraps the Tracxn REST API, providing a standardized interface for LLMs to interact with Tracxn data.
## Prerequisites
- Node.js 20 or higher
- Tracxn API key
## Setup
1. Clone the repository:
```bash
git clone <repository-url>
cd tracxn-mcp
```
2. Install dependencies:
```bash
npm install
```
3. Create a `.env` file:
```bash
cp .env.example .env
```
4. Add your Tracxn API key to the `.env` file:
```
TRACXN_API_KEY=your_api_key_here
```
## Running the Server
Development mode:
```bash
npm run dev
```
Production mode:
```bash
npm run build
npm start
```
The server will start on port 3000 by default. You can change this by setting the `PORT` environment variable.
## Available Tools
- `get_company`: Fetch detailed information about a company
- More tools will be added based on Tracxn API endpoints
## Resources
- `tracxn_raw`: Access raw JSON data from any Tracxn API endpoint (read-only)
## Error Handling
The server includes:
- Rate limiting with exponential backoff and jitter
- Error classification for common HTTP status codes
- Proper error propagation to clients
## License
MIT
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools, as there are no other tools to compare it to. The tool's purpose is clearly defined and distinct by default.
The single tool follows a consistent verb_noun pattern (get_company), which is straightforward and predictable. Since there are no other tools, there is no inconsistency to evaluate.
A single tool is too few for a server named 'Tracxn MCP Server', which implies a broader scope related to company data. This minimal set feels thin and inadequate for typical agent workflows, limiting functionality to just fetching company details without supporting operations like search, update, or listing.
The tool surface is severely incomplete for a company data domain; it only provides a get operation for companies, with no support for searching, listing, creating, updating, or deleting data. This leaves significant gaps that will cause agent failures in handling common tasks.