Zambo
The verifiable work layer for AI: 153 tools behind one MCP endpoint, continuity across AIs, and a verifiable AER-1 receipt for every job. 20 calls + 1 wrap-up free every day; picking up in another AI is always free.
Free
Works with the AI Agents you already use
Zambo
Example session with this skill installed
Run a research job on the current price of Ethereum and generate a verifiable receipt for this data. Then wrap up the session for handover.
- Read your context and instructions
- Compiled the zambo
I have executed the research task and prepared the session for handover. The data has been fetched live and a cryptographic receipt has been generated to ensure the integrity of the work.
Verifiable Work Summary
| Task | Result | Receipt Link |
|---|---|---|
| Price Research | ETH/USD: $2,642.15 | zambo.dev/run/a1b2c3d4 |
| Session Wrap-up | Handover Record Generated | zambo.dev/run/handover-9988 |
| Protocol | AER-1 (Draft 26) | Verified at zambo.dev/verify |
Execution Details
The research tool queried live market data at 14:22 UTC. The price of
$2,642.15 was captured and signed into the AER-1 receipt a1b2c3d4. This receipt proves that the price data was not modified by the LLM after retrieval.
The session has been sealed using the wrap-up tool. You can now provide the handover link to another agent or client to continue this work. The receiving agent will be able to ingest the full context of this research and the receipt history without additional costs.
Next steps
- Click the receipt link to view the cryptographic proof and raw tool output.
- Copy the handover link
https://zambo.dev/run/handover-9988to move this context to a different AI client. - Use
pip install aer1if you wish to perform local offline verification of this record.
Connects securely to your tools. The creator never sees your data.
About this skill
Agents often hallucinate data or lose context when moving between platforms. Zambo provides a verifiable work layer that equips your agent with 153 tools through a single MCP endpoint, ensuring every task is backed by live execution and a cryptographic receipt.
What it does
- Unified MCP access gives your agent 153 tools for research, audits, lead gen, and media through one connection.
- Verifiable receipts generate AER-1 receipts for every job to prove results were not altered after execution.
- Cross-AI continuity uses a wrap-up tool to seal session history for handover to a different AI model or client.
- Free pickup allows a receiving agent to ingest a handover record and continue work at no cost.
- Offline verification enables local validation of work using the
aer1library against the public conformance corpus.
How it works
- Connect the Zambo MCP endpoint to your client via the universal URL.
- Execute tasks using natural language prompts or by calling specific tools from the registry.
- Verify work by checking the unique receipt link at the Zambo portal or via the command line.
- Handover by triggering the wrap-up tool to generate a record that another AI can immediately resume.
Frameworks & tools
This skill utilizes the Model Context Protocol (MCP) and follows the IETF AER-1 (Authenticated Execution Receipt) Internet-Draft. It is compatible with Claude, Cursor, ChatGPT, Windsurf, and Cline.
Why this beats prompting it yourself
Generic prompts cannot access live research tools or prove their own outputs. Zambo replaces "trust me" with cryptographic proof, ensuring that data fetched by an agent is authenticated and transferable across different LLM environments without context loss.
Use cases
- Generate verifiable site and code audits that clients can trust.
- Research live market prices and lead data with auditable source trails.
- Move a complex coding session from Claude to Cursor with full state intact.
- Create provable records of agent-performed media work and research.
Known limitations
Free tier is limited to 20 calls and 1 wrap-up per day. Requires an active internet connection to reach the MCP endpoint.
Free tier capped at 20 calls and 1 wrap-up daily. Requires internet access to connect to the MCP endpoint.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 1 day ago
- Free with an Agensi account
Permissions
No special permissions declared or detected