Back to Home
paoloricciuti icon

tmcp

Verified Safe

by paoloricciuti

Overview

Build Model Context Protocol (MCP) servers for AI agents, providing schema-agnostic tools, resources, and prompts, with optional OAuth 2.1 authentication and distributed session management.

Installation

Run Command
node src/index.ts

Environment Variables

  • TMCP_DURABLE_OBJECT
  • TMCP_SESSION_INFO
  • REDIS_URL
  • PG_CONNECTION_STRING
  • OAUTH_ISSUER_URL

Security Notes

The project emphasizes a 'security-first design' with OAuth 2.1 implementation (including PKCE, Resource Indicators, token validation). CORS is configurable, and the design promotes external configuration of secrets (e.g., Redis/Postgres connection strings, Cloudflare KV bindings). Example code for quick start uses hardcoded secrets, but these are clearly for demonstration. JSON-RPC batching is explicitly disabled as per MCP 2025-06-18 requirements to reduce complexity and potential attack surface. The architecture encourages secure practices, but the overall security depends heavily on the correct implementation and configuration by the end-user (e.g., proper handling of sensitive environment variables, secure database access). No `eval` or obvious malicious patterns were found in the core library code.

Similar Servers

Stats

Interest Score68
Security Score9
Cost ClassMedium
Avg Tokens750
Stars141
Forks8
Last Update2025-12-06

Tags

MCPAI AgentsBackendAPIOAuthTypeScript