> ## Documentation Index
> Fetch the complete documentation index at: https://docs.twexapi.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Docs MCP server

> Search Twexapi documentation from AI tools via a Mintlify-hosted MCP server.

Twexapi documentation is available as an MCP server at `https://docs.twexapi.io/mcp`. AI tools can search the full docs site and retrieve indexed public pages during conversations. This is separate from the [Twexapi API MCP server](/mcp/overview) at `https://api.twexapi.io/mcp`, which interacts with live Twexapi API endpoints. The docs search tools require no authentication and do not call live Twexapi APIs.

<Note>
  `https://docs.twexapi.io/mcp` is an MCP transport endpoint, not a browser page. Opening it with a normal `GET` request can return a JSON-RPC method error. MCP clients should connect to the same URL and call MCP methods such as `tools/list`.
</Note>

## Docs MCP Server

Search docs and read indexed public pages at `https://docs.twexapi.io/mcp`. No auth required. Free. Some clients may also show Mintlify's `submit_feedback` tool for documentation feedback.

## API MCP Server

Interact with X/Twitter data at `https://api.twexapi.io/mcp`. Use an API key or OAuth 2.1. Calls cost credits according to the underlying endpoint.

## Agent route checklist

### Read docs first

Use Docs MCP at `https://docs.twexapi.io/mcp` for public docs, API parameters, examples, error codes, SDK guidance, and no-auth page retrieval.

### Run account actions

Use API MCP at `https://api.twexapi.io/mcp` for live X/Twitter reads, writes, searches, trends, extractions, communities, lists, DMs, articles, or timeline jobs. Authenticate with an API key or OAuth 2.1.

### Persist outside chat

Use REST or generated SDKs when a backend must own retries, cursor storage, file downloads, queues, scheduled jobs, or batch orchestration.

### Hand off results

Store the endpoint path, request parameters, returned IDs, `has_more`, `next_cursor`, export route, charged credits, or webhook replay route before ending the agent run.

## Quick connect

Use the contextual menu at the top of any docs page to connect instantly:

* Copy MCP Server URL - copies `https://docs.twexapi.io/mcp` to your clipboard
* Copy MCP Install Command - copies the `npx add-mcp` install command
* Connect to Cursor - installs the docs MCP server in Cursor
* Connect to VS Code - installs the docs MCP server in VS Code

## Setup

### Web and terminal clients

* [Claude.ai](#claude-ai)
* [Claude Code](#claude-code)
* [Codex CLI](#codex-cli)

<a id="claude-ai" />

#### Claude.ai

1. Go to [Settings > Connectors](https://claude.ai/settings/connectors) in Claude.
2. Select **Add custom connector**.
3. Enter:
   * Name: `Twexapi Docs`
   * URL: `https://docs.twexapi.io/mcp`
4. Select **Add**.
5. In any chat, click the attachments button and select **Twexapi Docs**.

<a id="claude-code" />

#### Claude Code

Add the docs MCP server:

```bash theme={null}
claude mcp add --transport http twexapi-docs https://docs.twexapi.io/mcp
```

Verify with:

```bash theme={null}
claude mcp list
```

<a id="codex-cli" />

#### Codex CLI

Add to `~/.codex/config.toml`:

```toml theme={null}
[mcp_servers.twexapi_docs]
url = "https://docs.twexapi.io/mcp"
```

### Editor clients

* [Cursor](#cursor)
* [VS Code](#vs-code)
* [Windsurf](#windsurf)
* [OpenCode](#opencode)

<a id="cursor" />

#### Cursor

Add to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (project):

```json theme={null}
{
  "mcpServers": {
    "twexapi-docs": {
      "url": "https://docs.twexapi.io/mcp"
    }
  }
}
```

<a id="vs-code" />

#### VS Code

Add to `.vscode/mcp.json` (project) or use **MCP: Open User Configuration** (global):

```json theme={null}
{
  "servers": {
    "twexapi-docs": {
      "type": "http",
      "url": "https://docs.twexapi.io/mcp"
    }
  }
}
```

<a id="windsurf" />

#### Windsurf

Add to `~/.codeium/windsurf/mcp_config.json`:

```json theme={null}
{
  "mcpServers": {
    "twexapi-docs": {
      "serverUrl": "https://docs.twexapi.io/mcp"
    }
  }
}
```

<a id="opencode" />

#### OpenCode

Add to `opencode.json`:

```json theme={null}
{
  "mcp": {
    "twexapi-docs": {
      "type": "remote",
      "url": "https://docs.twexapi.io/mcp"
    }
  }
}
```

## Using both MCP servers

For the best experience, connect both:

1. Docs MCP (`docs.twexapi.io/mcp`) - the AI searches documentation to understand API parameters, error codes, and usage patterns.
2. API MCP (`api.twexapi.io/mcp`) - the AI executes authenticated actions such as searches, lookups, trends, extractions, and write operations.

The AI decides which server to query based on context. A question about request parameters should hit the docs server. A request to fetch live X/Twitter data should hit the API server.

### Claude Code

```bash theme={null}
claude mcp add --transport http twexapi-docs https://docs.twexapi.io/mcp
claude mcp add --transport http twexapi https://api.twexapi.io/mcp --header "x-api-key:twexapi_YOUR_KEY_HERE"
```

### Cursor

```json theme={null}
{
  "mcpServers": {
    "twexapi-docs": {
      "url": "https://docs.twexapi.io/mcp"
    },
    "twexapi": {
      "url": "https://api.twexapi.io/mcp",
      "headers": {
        "x-api-key": "twexapi_YOUR_KEY_HERE"
      }
    }
  }
}
```

### VS Code

```json theme={null}
{
  "servers": {
    "twexapi-docs": {
      "type": "http",
      "url": "https://docs.twexapi.io/mcp"
    },
    "twexapi": {
      "type": "http",
      "url": "https://api.twexapi.io/mcp",
      "headers": {
        "x-api-key": "twexapi_YOUR_KEY_HERE"
      }
    }
  }
}
```

## Available tools

Mintlify generates docs tool names from the site name. After deploying this docs configuration with `name` set to `twexapi`, the docs MCP server exposes:

| Tool                            | Purpose                                                                                            |
| ------------------------------- | -------------------------------------------------------------------------------------------------- |
| `search_twexapi`                | Search indexed Twexapi documentation by endpoint, parameter, error code, workflow, or guide topic. |
| `query_docs_filesystem_twexapi` | Read indexed documentation files and inspect exact page content.                                   |
| `submit_feedback`               | Send page-level documentation feedback when supported by the client.                               |

<Tip>
  The current production deployment may still return `search_twexapi_io` and `query_docs_filesystem_twexapi_io` until the updated `docs.json` is deployed. After deployment, `tools/list` should return `search_twexapi` and `query_docs_filesystem_twexapi`.
</Tip>

## What gets searched

The docs MCP server indexes public Twexapi documentation:

* API reference operations and request schemas
* Authentication, rate limits, errors, and billing guidance
* MCP server setup and tools reference
* Framework guides for LangChain, CrewAI, Pydantic AI, Google ADK, Haystack, Mastra, no-code tools, and workflow platforms
* Workflow guides for search, profiles, trends, articles, communities, lists, timelines, and extractions
* `llms.txt` and other Mintlify-generated documentation indexes

## Example prompts

```txt theme={null}
Use Twexapi Docs MCP to find the authentication guide, then explain how to configure the API MCP server with x-api-key.
```

```txt theme={null}
Search the Twexapi docs for advanced search parameters, then tell me which API MCP call should be used for recent tweets about AI agents.
```

```txt theme={null}
Find the docs for article Markdown fetches and generate a minimal Python example using the documented request shape.
```