// MCP TOOL REFERENCE

LANGCHAIN TOOLS

9 tools from the Langchain MCP Server, categorised by risk level.

// ALL 9 LANGCHAIN TOOLS

READ 9 tools

Read langgraph_get_run Get detailed trace information for a specific run, including input, output, and execution details. Read langgraph_get_thread Get detailed information about a specific thread including its current values and metadata. Read langgraph_get_thread_state Get the current state/checkpoint of a thread, including state values, pending tasks, and next nodes. Read langgraph_list_runs List runs (executions) for a specific thread. Use this to find specific runs to inspect. Read langgraph_list_threads List conversation threads from a local LangGraph dev server. Use this to find threads to debug. Requires a ... Read search_deepagents_code Search DeepAgents source code. Returns relevant code snippets. Read search_docs Search documentation, references, and tutorials about LangChain, LangGraph, LangSmith, and DeepAgents. Read search_langchain_code Search LangChain source code. Returns relevant code snippets. Read search_langgraph_code Search LangGraph source code. Returns relevant code snippets.

// RUNNING THIS SERVER

The managed route: connect Langchain through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y langchain-mcp

// FAQ

How many tools does the Langchain MCP server have? +

The Langchain MCP server exposes 9 tools across 1 categories: Read.

How do I enforce policies on Langchain tools? +

Route the Langchain server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Langchain tools fall into? +

Langchain tools are categorised as Read (9). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.