tm-finder-mcp
MCP server that enables trademark searches through the TM Finder Public API, with support for API key authentication and idempotency for retries.
README
TM Finder MCP server
Stateless Streamable HTTP MCP adapter for the TM Finder Public API.
Configuration
API_KEY is the server's only environment variable. It is optional because clients can instead provide their own key in the Authorization or X-API-Key header. All non-secret server settings are defined in src/main.ts under MCP_CONFIG.
For multi-user deployments, do not set a shared API_KEY. Have each MCP client send its TM Finder API key in the Authorization: Bearer <api-key> header or the X-API-Key: <api-key> fallback header when calling /mcp. The credential is forwarded to the public API and is never included in tool arguments or results.
For a single-user deployment, set API_KEY through the shell or secret manager. The blank entries in the committed environment files are intentionally treated as unset; do not commit the real key.
Codex configuration
Codex's Bearer token env var setting expects the name of an environment variable, not the token itself. For example, start Codex from a shell where the credential is available:
export TM_FINDER_API_KEY='your-tm-finder-api-key'
Then configure the Streamable HTTP server with:
- URL:
https://tm-finder-mcp.vercel.app/mcp - Bearer token env var:
TM_FINDER_API_KEY
Codex will read TM_FINDER_API_KEY and send its value as
Authorization: Bearer <value>. Restart the Codex app or IDE extension after
saving the MCP configuration. Do not paste the token itself into Bearer token
env var; doing so makes Codex look for an environment variable whose name is
the token, so no authorization header is sent.
The equivalent config.toml entry is:
[mcp_servers.tm_finder]
url = "https://tm-finder-mcp.vercel.app/mcp"
bearer_token_env_var = "TM_FINDER_API_KEY"
If Codex does not forward Authorization, use the MCP settings' static
Headers section instead: X-API-Key as the key and the TM Finder API key as
the value (without a Bearer prefix). The MCP server accepts this fallback and
forwards the credential to the public API as a Bearer token. This stores the
secret in Codex configuration, so the environment-variable method is preferred.
Endpoints
POST /mcp— stateless MCP Streamable HTTP endpointGET /health— container health/liveness endpoint
The server exposes search_trademarks. Each call costs one TM Finder API credit. An idempotency key is generated automatically; clients retrying a logical operation should pass the original idempotencyKey tool argument to avoid a second debit.
Run
# Start locally with automatic restart when source files change
npm run local
# Compile TypeScript, then run the production build
npm run build
npm start
The committed environment files contain only a blank API-key placeholder. Inject the real key through the hosting platform's secret manager; never commit it.
Terminate with SIGTERM or SIGINT for graceful shutdown. Put the service behind TLS in production and keep /mcp request bodies within the configured 256 KB limit.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.