> For the complete documentation index, see [llms.txt](https://polydash.gitbook.io/polydash-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://polydash.gitbook.io/polydash-docs/agents-and-api.md).

# AI agents and API

Open-source AI agents, a non-custodial launch API, and an MCP server for Polypad.

Polypad has two kinds of automation:

* **Agents that read.** PolyCTO, Poly Agent, and PolyForge analyze tokens and staking pools. They do not hold keys.
* **An API that prepares.** The agent launch API validates parameters, simulates the call on-chain, and returns an **unsigned transaction**. Your own wallet signs and sends it.

In both cases Polypad never accepts a private key and never sends a transaction for you.

```mermaid
sequenceDiagram
  participant Agent as Agent or script
  participant API as Polypad API
  participant RPC as Robinhood Chain RPC
  participant Wallet as Operator wallet
  Agent->>API: POST /api/agents/v1/simulate (from, token params)
  API->>RPC: eth_call createLaunch
  RPC-->>API: simulation result
  API-->>Agent: unsignedTx (to, data, value, chainId)
  Agent->>Wallet: sign and broadcast
  Wallet->>RPC: createLaunch transaction
```

## In this section

| Page                                                                                                                   | What it covers                                                            |
| ---------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------- |
| [AI agents](https://polydash.gitbook.io/polydash-docs/agents-and-api/ai-agents.md)                                     | PolyCTO, Poly Agent, PolyForge                                            |
| [Agent launch API](https://polydash.gitbook.io/polydash-docs/agents-and-api/agent-launch-api.md)                       | What the API does, who it is for, a quickstart                            |
| [Endpoint reference](https://polydash.gitbook.io/polydash-docs/agents-and-api/endpoint-reference.md)                   | Every endpoint and its authentication                                     |
| [Launch endpoints](https://polydash.gitbook.io/polydash-docs/agents-and-api/launch-endpoints.md)                       | `validate`, `simulate`, parameters, and examples                          |
| [Trading and commitment endpoints](https://polydash.gitbook.io/polydash-docs/agents-and-api/trading-endpoints.md)      | Quotes and unsigned buy, sell, commit, refund, and fee-claim transactions |
| [Errors and rate limits](https://polydash.gitbook.io/polydash-docs/agents-and-api/errors-and-rate-limits.md)           | Status codes, error codes, limits                                         |
| [Agent-launched badge](https://polydash.gitbook.io/polydash-docs/agents-and-api/agent-launched-badge.md)               | How the mark works and what it means                                      |
| [MCP server](https://polydash.gitbook.io/polydash-docs/agents-and-api/mcp-server.md)                                   | Tools for MCP clients                                                     |
| [Launch from your own wallet](https://polydash.gitbook.io/polydash-docs/agents-and-api/launch-from-your-own-wallet.md) | Call the factory directly                                                 |

## Operator responsibility

The operator of an agent is responsible for what it launches: no impersonation, no trademark abuse, no misleading claims.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://polydash.gitbook.io/polydash-docs/agents-and-api.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
