LangGraph Cloud (Stateful AI Agents)

LangGraph Cloud (Stateful AI Agents) MCP Connector for Claude

A+

Orchestrate stateful AI agents via LangGraph Cloud — manage assistants, monitor conversation threads, and handle human-in-the-loop overrides.

10 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your LangGraph Cloud account to any AI agent and take full control of your stateful multi-turn agents and complex graph-based AI workflows through natural conversation.

What you can do

  • Assistant Orchestration — List deployed assistants representing compiled LangGraph applications ready to process stateful workloads directly from your agent
  • Thread Management — Create and monitor conversation threads to maintain long-term memory buffers explicitly managed by cloud checkpoints
  • State Inspection & Override — Retrieve the exact execution state of a thread and perform manual node overrides for human-in-the-loop approvals or mid-execution adjustments
  • Run Control — Trigger fresh graph executions with specific input payloads and monitor or cancel asynchronous runs to manage system resources
  • Cron Automation Audit — List scheduled background jobs configured to autonomously trigger LangGraph execution runs periodically
  • History Tracking — Extract historical run steps indicating explicit graph invocations and internal reasoning paths within a stateful thread

How it works

  1. Subscribe to this server
  2. Enter your LangGraph API URL and API Key
  3. Start managing your agentic infrastructure from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • AI Agentic Developers — debug stateful multi-turn agents and verify graph traversal paths through natural conversation
  • AI Platform Engineers — monitor deployed assistants and manage cloud-based checkpoints across multiple team environments
  • Ops Teams — audit scheduled crons and manage execution runs to ensure reliable delivery of automated AI workflows
ai-agentsstateful-workflowsmulti-turn-conversationsgraph-based-aihuman-in-the-loopagent-deployment

10 tools expose this connector's capabilities to your AI agent.

list_assistants

List LangGraph deployed assistants (graph configurations)

cancel_run

Interrupt and cancel an ongoing graph execution run

create_thread

Create a new LangGraph thread to hold conversational state

create_run

Execute an assistant run on a specific thread with an input payload

get_run

Get complete details and status of a specific language graph run

get_thread_state

g., current messages array or structured outputs) generated by the LangGraph application. Retrieve the exact state graph and variables for a specific thread

list_crons

List active scheduled cron jobs automating agent runs

list_runs

List execution runs assigned to a specific thread

list_threads

List active LangGraph conversation threads

update_thread_state

Manually override or update a thread state graph

See how to talk to your AI agent using LangGraph Cloud (Stateful AI Agents).

List all deployed assistants in my LangGraph Cloud account

I've found 3 assistants: 'Customer-Support-Bot' (ID: asst-123), 'Sales-Agent-V2' (ID: asst-456), and 'RAG-Search-Helper' (ID: asst-789). Which one would you like to create a new thread for?

Show me the current state for thread ID 'abc-123-xyz'

Retrieving state for thread 'abc-123-xyz'… The graph is currently at the 'human_review' node. Variables: 'is_approved' (null), 'final_answer' ('Initial draft generated...'). It is waiting for a manual override to proceed to the 'send_email' node.

List all active scheduled crons in my account

I've identified 2 active scheduled jobs: 1) 'Daily-Summary-Bot' (Runs every day at 9 AM UTC), 2) 'Inventory-Monitor' (Runs every 4 hours). Both are successfully triggering runs on their respective threads. Would you like to check the last run status for the summary bot?

Yes. Use the `update_thread_state` tool to perform manual node state overrides. This is the standard way to implement human-in-the-loop (HITL) patterns, allowing you to modify or approve graph variables directly mid-execution.

Related Connectors