with ยท practical guide
Add Zambo MCP to Langgraph: setup in 2 steps
Add Zambo to your AIOne URL. No key. Start with a real tool call.
Set it up in two steps
- Open LangGraph MCP settings. Use the documented MCP settings for LangGraph. Account availability and menu labels can vary.
- Add the Zambo endpoint. Add https://zambo.dev/mcp, save, then check that the server appears in the client before using a tool.
For the latest UI and transport support, follow the LangGraph official MCP guidance documentation. Host availability can vary by version and account.
The direct answer
To connect LangGraph to Zambo, add the single remote MCP URL https://zambo.dev/mcp using the host's current MCP settings. Then confirm the server is listed and ask for one safe, read-only action. The setup is specific to the host; Zambo does not require you to replace the rest of your AI workflow.
Connect the remote server through the LangChain MCP adapter, expose only the needed tools to the graph, and preserve the receipt URL in graph state so later nodes can report the observed result.
A practical way to apply this
- Write the user's intended outcome in one sentence.
- Identify which source, MCP tool, platform log, or human review can answer the question.
- Run the smallest safe action and preserve its returned status, timestamp, and receipt link.
- Check the receipt independently and label any evidence that is missing or outside the captured boundary.
A disciplined review separates the request, the tool execution, the saved result, and any later outcome. Ask what the system actually observed, then inspect the public receipt and its verifier. If the work changed another service, query that service directly or follow its confirmation reference. If that evidence is absent, report the outcome as unknown rather than filling the gap with an assumption.
A concrete example
A useful first check is a read-only request, such as asking the connected AI to look up a public value. The client should return a Zambo receipt link. Open that link, compare its identifier with the result in chat, and use the verifier at https://zambo.dev/verify/ to inspect the saved record.
For a work-specific review, replace the sample with the receipt generated by your own call. Match the tool name and receipt ID exactly. If the output is a proposal, a blocked action, or an unavailable response, retain that state instead of describing it as completed work.
What the record can and cannot tell you
Connect the remote server through the LangChain MCP adapter, expose only the needed tools to the graph, and preserve the receipt URL in graph state so later nodes can report the observed result.
A checkable receipt records what the connected execution service saved. It does not establish that a model's complete answer is accurate, that every possible input was tested, or that an outside service changed state. When an outside effect matters, look for a confirmation from the system that owns that state, such as a read-back, callback, or provider reference.
For sensitive work, publish only the fields needed for review. Keep access tokens, private credentials, customer data, and unrelated chat context out of a public handover. Explain what the receipt covers and what remains outside its scope.
Review checklist
- Does the record identify the specific request and tool?
- Does the receipt ID match the result being discussed?
- Can a reviewer reach the verifier without the original chat?
- Are failures, retries, and pending steps represented honestly?
- Is outside confirmation linked to its actual source?
- Are private values excluded from the public copy?
Use this checklist for add zambo mcp to langgraph: setup in 2 steps and save only the evidence relevant to the decision. A short, well-scoped record is easier to review than a large transcript with no clear boundary.
Endpoint
https://zambo.dev/mcpCommon questions
Does Add Zambo MCP to Langgraph require a separate Zambo key?
No API key is required for the public Zambo MCP URL. Your client may still require its own account or workspace access.
How can I confirm the connection worked?
Ask the client to list or use a read-only Zambo capability, then open the receipt link returned by the call at the public verifier.
Primary references
Add Zambo to your AIConnect once, then ask your AI to use the tools your task needs.