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

# Brain MCP Server: workspace memory as tools

> Mount your Alfera workspace brain as tools in Claude Code, Cursor, or your own agent via the MCP server at https://api.alfera.ai/v1/mcp.

The Brain MCP server exposes your Alfera workspace brain as callable tools in any MCP-compatible agent. Point Claude Code, Cursor, or your own harness at a single URL and your agent can search memory, read context, teach new facts, and ask the Alfera worker for answers.

The server is streamable HTTP and stateless: no session to open, resume, or close. Every request carries its own key, so restarting your client or load-balancing across instances changes nothing.

## Endpoint

```text theme={null}
https://api.alfera.ai/v1/mcp
```

## Key facts

* **Streamable HTTP, stateless.** No session to open or close. Every request is independent.
* **Protocol versions.** The server speaks MCP `2025-06-18` and accepts `2025-03-26` and `2024-11-05`.
* **Same brain, same keys.** It uses the same workspace brain and the same API keys as the [Brain API](/api-reference/overview). Disclosure rules are identical: an `external` key receives only `profile_fact`, `preference`, `decision`, and `observation`, and never facts about your team, `agent_inferred` facts, or facts about an end user the call did not name.

## Connect

Create a key in the Alfera app under **Settings → API Keys**, pick its scopes and audience, and export the secret:

```bash theme={null}
export ALFERA_API_KEY=ak_live_...
```

<Tabs>
  <Tab title="Claude Code">
    Add the MCP server with the `claude mcp add` command:

    ```bash theme={null}
    claude mcp add --transport http alfera-brain https://api.alfera.ai/v1/mcp \
      --header "Authorization: Bearer $ALFERA_API_KEY"
    ```
  </Tab>

  <Tab title="Cursor">
    Add the server to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (one project):

    ```json theme={null}
    {
      "mcpServers": {
        "alfera-brain": {
          "url": "https://api.alfera.ai/v1/mcp",
          "headers": { "Authorization": "Bearer ak_live_..." }
        }
      }
    }
    ```
  </Tab>

  <Tab title="Other">
    Anything that speaks Streamable HTTP can POST JSON-RPC to `https://api.alfera.ai/v1/mcp` with `Authorization: Bearer <key>` on every request. `X-Api-Key: <key>` is accepted as well.

    The endpoint is POST-only. `GET` and `DELETE` return `405 method_not_allowed`.
  </Tab>
</Tabs>

## Verify with whoami

Call `whoami` to confirm the connection. It needs no scope, so it answers for any live key and reports what the connection can do.

```bash theme={null}
curl https://api.alfera.ai/v1/mcp \
  -H "Authorization: Bearer $ALFERA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "whoami",
      "arguments": {}
    }
  }'
```

<ResponseField name="key_name" type="string">
  Human-readable name for this key, for example `support-bot`.
</ResponseField>

<ResponseField name="key_prefix" type="string">
  Prefix of the key, for example `ak_live_x7f4`.
</ResponseField>

<ResponseField name="scopes" type="array">
  Array of scopes this key is allowed to use, for example `["memory.read", "answers.write"]`.
</ResponseField>

<ResponseField name="key_audience" type="string">
  Audience for the key, for example `external`.
</ResponseField>

<ResponseField name="rate_limit" type="object">
  Object with `requests_per_window` and `window_seconds`, for example `{ "requests_per_window": 120, "window_seconds": 60 }`.
</ResponseField>

Example response:

```json theme={null}
{
  "key_name": "support-bot",
  "key_prefix": "ak_live_x7f4",
  "scopes": ["memory.read", "answers.write"],
  "key_audience": "external",
  "rate_limit": { "requests_per_window": 120, "window_seconds": 60 }
}
```

<Tip>
  `tools/list` only advertises what this key's scopes allow. A `memory.read`-only key never sees `ask_worker`. If a tool is missing from your agent's list, the key lacks its scope.
</Tip>

## Next steps

* Browse the full [Brain MCP tools reference](/api-reference/mcp/tools) for arguments, scopes, and usage patterns.
* Read the [Brain API overview](/api-reference/overview) for the REST equivalents and field-level detail.