Skip to main content
AgentsUse

LangGraph

Tools that work with LangGraph

A low level orchestration framework for building, managing and deploying long running stateful agents.

Every pairing below carries a compatibility record backed by an evidence page: the package, docs page, or MCP path that proves the connection. Pairings are grouped by connection type first, because that decides how much integration work you own. A tool missing here is unverified by AgentsUse, not incompatible. Read the LangGraph profile for setup and scope before choosing.

This hub lists 4 verified pairings. AgentsUse keeps hubs out of the search index until at least five tools have verified compatibility, so thin lists never masquerade as complete coverage.

Built into the framework

First-party support that ships with the framework itself or its vendor packages.

Observability and EvaluationLangSmithAgent and LLM observability platform from LangChain for tracing, monitoring, and evaluating applications in production. Built in by the framework vendor via LangSmith debugging and observability for LangGraph. The LangGraph repository README lists Debugging with LangSmith and pairs LangGraph with LangSmith for agent evals and observability.
LangSmith: Profile Evidence

Official adapters

Adapter packages published by the framework vendor or the tool vendor for this pairing.

Search and Retrieval APIsExaA search API for AI: natural-language queries over an index built for agents, with content returned in model-ready shapes. Official adapter package via langchain-exa ExaSearchResults and ExaFindSimilarResults used with a LangGraph agent. The LangChain Exa search page states the Exa tools can be used with a LangGraph agent to dynamically search and find similar content.Search and Retrieval APIsTavilyA web access API built for AI agents: search, extract, map, crawl, and research endpoints behind one key. Official adapter package via langchain-tavily TavilySearch used as a LangChain tool in LangGraph agents. The Tavily provider page states langchain-tavily exposes Tavily endpoints as LangChain tools; LangGraph agents consume LangChain tools, and the LangGraph repository states LangChain provides integrations and composable components.
Exa: Profile EvidenceTavily: Profile Evidence

Connected through MCP

The framework consumes the tool as an MCP server or client. Transport and config notes live on the integration page.

Browser AutomationPlaywrightA browser automation framework that drives Chromium, Firefox, and WebKit with a single API for tests, scripts, and AI agents. Connected through MCP via langchain-mcp-adapters (MultiServerMCPClient, load_mcp_tools). The fetched LangChain docs mirror shows pip install langchain-mcp-adapters and load_mcp_tools used to load remote MCP tools into an agent, which is the documented MCP path for LangChain and LangGraph agents.
Playwright: Profile Evidence

How to choose from this list

Start from the job, not the framework: find the tool whose limitations you can live with, then check how it connects. Native and official adapter paths usually mean the pairing is maintained by someone whose roadmap you can read. Community adapters and API-only options shift the maintenance to your team. When two tools both fit, prefer the one whose integration page shows a configuration you can run unchanged, and keep a person reviewing the first outputs the pairing produces.