# stellar-agentgate

> A stellar-cli plugin that lets an AI agent safely invoke Soroban contracts via MCP, gated by an on-chain policy signer.

## Docs

- [Introduction](https://acachete.mintlify.app/index.md): A stellar-cli plugin that lets an AI agent safely invoke Soroban contracts via MCP, gated by an on-chain policy signer instead of a trusted intermediary.
- [Quickstart](https://acachete.mintlify.app/quickstart.md): Build the contracts, run the test suite, and stand up a demo wallet on Stellar testnet.
- [Architecture](https://acachete.mintlify.app/concepts/architecture.md): The full call path from a natural-language request to an on-chain decision, and why each layer trusts the one below it exactly as much as it should.
- [Security Model](https://acachete.mintlify.app/concepts/security-model.md): Why the policy contract, not the MCP server or the agent's key, is the real trust boundary -- and the two protocol-level details that were wrong on first attempt.
- [MCP Tools](https://acachete.mintlify.app/concepts/mcp-tools.md): How available tools are generated from the live on-chain allow-list and each contract's own spec -- never a hardcoded list.
- [Self-Service Onboarding](https://acachete.mintlify.app/guides/self-service-onboarding.md): Wire up your own wallet against the canonical agent-policy with one command -- no cloning, no deploying your own policy contract.
- [Deploying a Policy](https://acachete.mintlify.app/guides/deploying-a-policy.md): Configure the allow-list and spend cap for your own wallet, or reset the demo environment to a pristine state.
- [Testing](https://acachete.mintlify.app/guides/testing.md): 40 unit tests (zero network, sub-second) plus 9 end-to-end tests against real, freshly-deployed Stellar testnet environments.