LangChain ships stateless MCP support and elicitation
- Source
- x.com
- Date
Today, we're making some exciting updates to MCP in LangChain, including support for the new stateless MCP spec! @SydneyRunkle with everything you need to know ⤵️ https://t.co/GhYCivYVMW
Context
LangChain's updated support lets an 's tool ask for missing information without keeping a connection open while a person answers. MCP is the interface connecting agents to external tools. Under the revised stateless protocol, the client can retry a tool request with the answer attached; LangChain exposes that exchange as a paused agent run that resumes after input. Its September 3 explanation uses a restaurant booking that needs a date as an example.
This gives developers a concrete way to keep people involved when a tool needs clarification or approval. The release introduced the integration in Python as a beta, with TypeScript support planned.
- MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Checking sign-in…
Loading comments…





