MCP‑Use
Open‑source platform to connect LLMs with MCP servers and build custom AI agents with tool access.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for MCP‑Use, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
MCP‑Use is an open‑source library and platform that lets developers connect any LangChain‑compatible LLM to Model Context Protocol (MCP) servers. It enables creation of AI agents with tool access—like browsing, file operations, or HTTP services—supporting multi‑server setups, dynamic tool selection, streaming output, and both hosted and self‑hosted deployment options.
Key features
- LangChain integration
- tool calling
- open‑source SDK
- multi‑server support
- streaming agent output
Use cases
- Connecting language models to external tools and data sources via MCP.
- Building custom, tool-enabled AI agents with flexible workflows.
- Using multi‑server MCP setups and dynamic tool selection in AI applications.
- Deploying agents with hosted or self‑hosted infrastructure and streaming output.