mcpc
Verified Safeby mcpc-tech
Overview
A framework for building agentic Model Context Protocol (MCP) servers by composing existing MCP tools. It enables the creation of portable, interoperable AI agents with flexible execution modes and robust logging/tracing capabilities.
Installation
npx -y deno run -A jsr:@mcpc/cli/bin --config-file ./codex-fork.jsonEnvironment Variables
- GITHUB_PERSONAL_ACCESS_TOKEN
- MCPC_CONFIG_FILE
- MCPC_CONFIG_URL
- API_TOKEN
- MCPC_TRACING_ENABLED
- MCPC_TRACING_EXPORT
- MCPC_TRACING_OTLP_ENDPOINT
- GEMINI_PREFERRED_FORMAT
- HOME
- USERPROFILE
- PATH
- NODE_ENV
- PORT
Security Notes
The framework provides strong security mechanisms such as Deno's sandboxing for code execution (in `code_execution` mode, via `@mcpc-tech/handle-sandbox`), explicit permission control for the sandbox (`--allow-net`, `--allow-read`), restricted file searching (`search-tool-result` plugin enforces `allowedDir` and rejects overly-broad patterns), and clear handling of environment variables for secrets. However, the overall security highly depends on how users configure the server (e.g., granting broad `--allow-all` permissions to the sandbox) and the trustworthiness of composed third-party MCP servers. An `eval` usage is present in an example, but it's well-commented as 'Don't actually use eval!'. The use of `node:child_process.execFile` in an example for `git diff` also presents a potential risk, though in an example context.
Similar Servers
mcp-use
A full-stack framework for building Model Context Protocol (MCP) servers, MCP clients, and AI agents in both Python and TypeScript, supporting interactive UI widgets and robust debugging.
awesome-mcp-devtools
This repository provides a curated list of developer tools, SDKs, frameworks, libraries, utilities, and resources for working with Model Context Protocol (MCP) servers.
tmcp
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.
agentor
Deploy scalable AI agents with tool integrations (weather, email, GitHub, etc.) and support for A2A and MCP communication protocols.