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

# MCP server

Connect Claude, ChatGPT, Codex, Cursor, VS Code, Hermes or OpenClaw to your Sigrex account and manage strategies, bots and signals in plain language.

Sigrex hosts a remote [Model Context Protocol](https://modelcontextprotocol.io/) server. MCP is an open standard that lets AI assistants use external tools. Compatible clients discover the Sigrex tools on their own and sign you in with OAuth, so there are no API keys to copy.

### Server endpoint

```
https://mcp.sigrex.io
```

The server uses Streamable HTTP. The first time you connect, your client opens the Sigrex sign-in page in your browser. Log in and approve access. 

> ⚠️ **The connection has full access to your account**, including placing live trades. Only connect clients you trust, and check every action before you approve it.

> ⚠️ **API keys can't be added through MCP.** Create your LLM and exchange API keys in the Sigrex app or through the API. Once added, your AI client can use them.

### Connect your client

In most clients, add the URL above as a remote MCP server or custom connector, then sign in.

**Claude:** go to **Customize → Connectors**, click **+**, then **Add custom connector**, and paste the URL.

**ChatGPT:** turn on **Developer mode** under **Settings → Security and login**. Then go to [chatgpt.com/plugins](https://chatgpt.com/plugins), click **+** and paste the URL.

**Claude Code:**

```bash
claude mcp add --transport http sigrex https://mcp.sigrex.io
```

**Codex:**

```bash
codex mcp add sigrex --url https://mcp.sigrex.io
```

**VS Code, Cursor and other JSON configs:**

```json
{
  "mcpServers": {
    "sigrex": {
      "type": "http",
      "url": "https://mcp.sigrex.io"
    }
  }
}
```

### Agent plugins

The Sigrex plugin bundles the MCP server with a Sigrex skill for your agent:

* [Hermes Agent](https://hermes-agent.nousresearch.com/docs/plugins/sigrex)
* [OpenClaw (ClawHub)](https://clawhub.ai/sigrex/plugins/sigrex)
* [Source on GitHub](https://github.com/sigrexio/agent-plugin)

### Manual OAuth setup

Only needed if your client asks for OAuth endpoints. The full metadata is at `https://mcp.sigrex.io/.well-known/oauth-protected-resource`.

<table><thead><tr><th width="180.3333740234375">Setting</th><th>Value</th></tr></thead><tbody><tr><td>Authorization URL</td><td><code>https://api.sigrex.io/api/auth/oauth2/authorize</code></td></tr><tr><td>Token URL</td><td><code>https://api.sigrex.io/api/auth/oauth2/token</code></td></tr><tr><td>Scopes</td><td><code>openid profile email offline_access mcp</code></td></tr><tr><td>Resource</td><td><code>https://mcp.sigrex.io</code></td></tr><tr><td>Flow</td><td>Authorization code with PKCE</td></tr></tbody></table>

### MCP directories

Also listed in these MCP directories:

* [Official MCP Registry](https://registry.modelcontextprotocol.io/?q=sigrex)
* [Glama](https://glama.ai/mcp/connectors/io.sigrex.mcp/sigrex)
* [Smithery](https://smithery.ai/servers/sigrex/sigrex)


---

# 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://docs.sigrex.io/more/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.