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

# MCP for agents

> Give your agent email as native tools over the Model Context Protocol — 21 tools via npx sentvia-mcp.

SentVia ships an open **Model Context Protocol (MCP) server** —
[`sentvia-mcp` on npm](https://www.npmjs.com/package/sentvia-mcp) — so an AI agent
can use email as first-class tools: create inboxes, send and reply, search,
manage threads, webhooks and allow/block rules — without writing a single API
call. The agent simply *calls a tool*.

## Why MCP

With the REST API your code orchestrates email. With MCP, the **agent itself**
decides when to check its inbox, draft a reply, or escalate — SentVia's operations
appear directly in the model's tool list.

## Connect

All you need is an API key (`sv_live_…`) from the
[dashboard](https://console.sentvia.ai) — the same keys as the REST API
([Authentication](/authentication)).

<Tabs>
  <Tab title="Claude Code">
    ```bash theme={null}
    claude mcp add sentvia --env SENTVIA_API_KEY=sv_live_… -- npx -y sentvia-mcp
    ```
  </Tab>

  <Tab title="Claude Desktop / JSON config">
    ```json theme={null}
    {
      "mcpServers": {
        "sentvia": {
          "command": "npx",
          "args": ["-y", "sentvia-mcp"],
          "env": { "SENTVIA_API_KEY": "sv_live_…" }
        }
      }
    }
    ```
  </Tab>

  <Tab title="OpenClaw">
    ```bash theme={null}
    openclaw mcp add sentvia --command npx --arg -y --arg sentvia-mcp
    ```

    then set `SENTVIA_API_KEY` in the server's `env`. Full walkthrough:
    [OpenClaw guide](/frameworks/openclaw).
  </Tab>
</Tabs>

The server is a thin stdio wrapper over the REST API — no state of its own, and
it runs wherever your agent runs (Node 20+).

## Available tools

| Area              | Tools                                                                                       |
| ----------------- | ------------------------------------------------------------------------------------------- |
| Inboxes           | `create_inbox` · `list_inboxes` · `delete_inbox`                                            |
| Messages          | `send_message` · `reply_to_message` · `forward_message` · `get_message` · `search_messages` |
| Threads           | `list_threads` · `get_thread`                                                               |
| Drafts            | `create_draft` · `send_draft` · `list_drafts`                                               |
| Domains           | `add_domain` · `get_domain`                                                                 |
| Webhooks          | `create_webhook` · `list_webhooks` · `delete_webhook`                                       |
| Allow/block lists | `add_address_rule` · `list_address_rules` · `delete_address_rule`                           |

Because the tools map onto the same endpoints documented in the
[API reference](/api-reference/introduction), everything you read here applies —
threading, idempotency, suppression, and attachments all behave identically.

## Configuration

| Env var            | Required | Default                  |
| ------------------ | -------- | ------------------------ |
| `SENTVIA_API_KEY`  | yes      | —                        |
| `SENTVIA_BASE_URL` | no       | `https://api.sentvia.ai` |

<Note>
  Tools inherit the key's tenant scope: an agent can only see and act on its own
  tenant's inboxes, threads, and rules. Suppression and allow/block rules are
  enforced server-side, so a misbehaving agent can't mail past them.
</Note>