> 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/mcp-server.md).

# MCP server

`agents/polypad-mcp` is a small [MCP](https://modelcontextprotocol.io) server that external agents can run to prepare a Polypad launch on Robinhood Chain. It wraps the HTTP API.

## Tools

| Tool                      | What it does                                                                                               |
| ------------------------- | ---------------------------------------------------------------------------------------------------------- |
| `polypad_validate_launch` | Checks parameters locally against the published limits. Does not sign, broadcast, or ask for a private key |
| `polypad_prepare_launch`  | Sends the parameters to `POST /api/agents/v1/simulate` and returns the unsigned `createLaunch` transaction |

The server does not sign, does not broadcast, and does not accept a private key. The operator signs `unsignedTx` in their own wallet. The HTTP API is authoritative. The local check uses the same published bounds, and the repository's CI compares the two.

## Run it

```bash
git clone https://github.com/polydash-labs/Polydash.git
cd Polydash
POLYPAD_API_BASE=https://polypad.family python agents/polypad-mcp/polypad_mcp.py
```

Set `POLYPAD_API_BASE` when the API is not at `https://polypad.family`. Do not add a trailing path. The process speaks MCP `2024-11-05` over stdio with `Content-Length` framing.

## Limits in the tool schema

| Limit                | Value                       |
| -------------------- | --------------------------- |
| Maximum creator fee  | 500 bps                     |
| Maximum social links | 10                          |
| Name and symbol      | 64 and 32 bytes             |
| Description          | 2,000 characters            |
| Launch delay         | 2,592,000 seconds           |
| Rate limit           | 20 requests per 600 seconds |

## Tool inputs

Both tools take the parameters in [Launch endpoints](https://polydash.gitbook.io/polydash-docs/agents-and-api/launch-endpoints.md). `creatorFeeBps` and `name` and `symbol` are required. `polypad_prepare_launch` also requires `from`, the address that will sign. Schemas are in `agents/polypad-mcp/schemas/tools.json`.

## Example client configuration

Most MCP clients take a command and environment. For a stdio server, the entry looks like this:

```json
{
  "mcpServers": {
    "polypad": {
      "command": "python",
      "args": ["agents/polypad-mcp/polypad_mcp.py"],
      "env": { "POLYPAD_API_BASE": "https://polypad.family" }
    }
  }
}
```

Adjust the path for your clone. Client configuration formats differ.

## Risks

The tools prepare transactions. A person or a wallet policy should review every transaction before it is signed.


---

# 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/mcp-server.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.
