ZAMBO.

Direct answer

AutoGen Agent Receipts

Add verifiable receipts to AutoGen tool calls and every call your agents make leaves a record anyone can check. AutoGen conversations are multi-agent by design: agents build on each other's messages, and when the final answer is wrong, the transcript alone cannot show which agent ran what, or whether a claimed tool call happened at all. Route the agents' tool calls through the Zambo MCP at https://zambo.dev/mcp and each call returns its result plus a verifiable receipt, captured server side at execution, outside the agents' control.

See the artifact first: the live demo runs one real call and hands you its verifiable receipt in about 10 seconds, no signup. That receipt is the same object your AutoGen runs will publish.

Updated November 9, 2026.

Wire AutoGen's tools through Zambo

AutoGen reaches MCP servers through the workbench in autogen-ext: an McpWorkbench opened on a server's parameters hands that server's tools to any agent, and a remote streamable HTTP server is described by StreamableHttpServerParams. Point it at the Zambo MCP and the agent's tool calls run through the endpoint that receipts them:

pip install -U autogen-agentchat "autogen-ext[mcp]"

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.tools.mcp import McpWorkbench, StreamableHttpServerParams

params = StreamableHttpServerParams(url="https://zambo.dev/mcp")
async with McpWorkbench(params) as workbench:
    agent = AssistantAgent("researcher", model_client=model_client, workbench=workbench)
    result = await agent.run(task="Check the saved record for this job and summarize what ran")

Match the workbench shape to the AutoGen version you have installed; the route is the same either way. The Zambo MCP carries 153 tools total, 36 on the default surface, and every call through it returns its result plus a verifiable receipt, captured server side at execution. The record is made by the layer that ran the call, so no agent in the conversation gets to edit its own history. The pattern is the one described in MCP server receipts: per-call receipts answer what each agent did, in the order it did it.

In a group chat or a society-of-mind setup, give each agent the same workbench and the receipts still separate cleanly: every call is recorded with the tool, the inputs, and the result the endpoint observed, so a claim one agent makes about another agent's work can be checked against the record instead of the transcript.

Make the first call a search, under your label

A demo tour is not an onboarding. The pattern that turns a first session into a second day is a first call that searches the catalog for the job the agent actually has, carrying one pinned identity. Every Zambo tool accepts a caller label and a session id as call arguments; usage is counted under that label, and limits and any pass attach to it. Over a raw MCP session the labeled call looks like this:

result = await session.call_tool("capability_search", {
    "q": "the job you need done, in your own words",
    "_caller_label": "your-fleet-or-project-name",
    "_session_id": "your-stable-session-name",
})

Search first, run one worked call, then let the run's memory and continuity live under the same label, so the second day starts by reading the record back instead of starting over.

Check the receipts

Every receipt lives at a public URL anyone can open, and checking one is free at zambo.dev/verify with no signup: paste the receipt link or ID and the verifier recomputes the commitment from the saved bytes and compares it with the commitment fixed when the call ran. A match means the saved record is the record made at execution. A mismatch means the record was changed after the fact, and the page says so plainly.

That gives the run's owner an acceptance check with teeth, the Walk-Away Test: set the agent a countable multi-step job, walk away, and on return read the record before the summary. Claimed steps versus recorded steps is the whole audit. A step an agent claims but never ran has no receipt to point to.

Close the run with one workflow receipt

When the run finishes, call workflow_close through the same endpoint. The step receipts from the run bind into a single summary receipt whose children list names every step receipt and whose root digest is computed over them, so the whole job verifies as one record: a step added, dropped, or swapped after the fact breaks the root. Per-call receipts answer what this agent did; the closed record answers what the run did, in full, and it is the link you hand a client or auditor.

Cost stays small either way. A Day Pass is $0.99 one time and covers unlimited calls for 24 hours. The Zambo Pass is $29 for 30 days, one payment, and $19 for 30 days for $ZAMBO holders. A Lifetime Pass is $250, one payment for good. Humans pay by PayPal or card through PayPal; agents pay USDC on Base via x402. Checking stays free for anyone you hand a receipt to.

Honest limits

A receipt proves the saved result was not changed since it was saved. It does not prove the output was correct, the plan was good, or an outside outcome happened that the endpoint did not observe. It settles what ran, what it was given, and what came back, in a form the run's owner does not have to take on trust. Judge the work itself against that record.

Frequently asked questions

How do I add execution receipts to an AutoGen agent?

Open an McpWorkbench from autogen-ext on StreamableHttpServerParams for https://zambo.dev/mcp and pass that workbench to your agent. Every tool call the agent then makes runs through the Zambo endpoint, which returns the result plus a verifiable receipt at a public https://zambo.dev/run/ URL. At the end of the run, call workflow_close through the same endpoint so the step receipts bind into one chained record a client or auditor can check as a whole.

Can I verify which agent in an AutoGen conversation ran a tool?

Yes, call by call. Each call routed through the endpoint becomes its own receipt: the tool that ran, the inputs the endpoint recorded, and the output it observed, committed under a SHA-256 hash at the moment the call finished and published at a URL anyone can fetch. Recompute the commitment from the receipt's canonical bytes; a match means the saved record is the record made when the call ran. An agent that claims a call it never made has no receipt to point to, and that absence is visible in the run's record instead of hidden in the conversation.

Do AutoGen runs come with proof of what the tools did?

Not by default. AutoGen gives you the conversation and its own event logs, and both are records the run itself controls: a message can be retold, trimmed, or regenerated later and nothing in the framework marks the change. Proof appears when the call is captured at execution time by a layer outside the agents' control and committed under a hash: the result bytes saved as recorded, a digest over them, and a public URL where anyone can fetch the record and recompute the digest. That is the record the Zambo MCP route adds. It proves the saved result is the result recorded when the call ran; whether the result was any good remains a judgment the receipt does not make for you.

What does an AutoGen run receipt contain?

One receipt per call, in the AER-1 format: the tool that ran, the inputs the endpoint recorded, the result it observed and saved, a timestamp, and the SHA-256 commitments (the canonical bytes and the output hash) that make the record checkable by recompute. Receipt URLs collect as the run proceeds, and a workflow_close at the end binds the step receipts into one chained record whose children list names every step. AER-1 is an open IETF Internet-Draft, so the format is public text, not a vendor schema.

What does it cost to receipt an AutoGen run?

The free tier covers 20 calls and 1 wrap-up free every day, and picking up work in another AI is always free, so you can wire the route and see real receipts before paying anything. A Day Pass is $0.99 one time and covers unlimited calls for 24 hours. Ongoing use is the Zambo Pass at $29 for 30 days, one payment, and $19 for 30 days for $ZAMBO holders. A Lifetime Pass is $250, one payment for good. Checking a receipt is always free at https://zambo.dev/verify/ with no signup, so clients and auditors never need a plan to check your work.

Run it on a record instead

Reading about the record is one thing; having it under your own work is the point. Work run through the Zambo MCP endpoint at zambo.dev/mcp saves its result at execution and returns a verifiable AER-1 receipt for every call. The Day Pass is $0.99 for 24 hours of the full endpoint, the Pass is $29 for 30 days, one payment, and checking any receipt is always free at zambo.dev/verify.

Related

Proof works best when it travels with the work itself. The AER-1 badge kit turns verifiable receipts into an embeddable badge for project pages, docs, and profiles, so anyone who sees the claim can reach the check in one click.