# Action1 MCP Server

An [MCP](https://modelcontextprotocol.io) server for the [Action1](https://www.action1.com)
API. It lets an AI agent read an MSP's Action1 data: organizations (clients), managed
endpoints, missing OS and third-party updates, and scheduled automations. All tools are
read-only.

- Transport: MCP Streamable HTTP at `POST /mcp`, health probe at `GET /health`
- Stateless and multi-tenant: credentials arrive on every request as HTTP headers and are
  never stored; the OAuth access token is obtained per request and not cached
- Python 3.12, [uv](https://docs.astral.sh/uv/), FastMCP, httpx
- License: Apache-2.0, Copyright 2026 MSPbots.ai

<div align="center">

## MSPbots Connector

**The MCP Gateway built for MSPs: visible, controlled, and your data stays where it belongs.**

[**Get started at connect.mspbots.ai →**](https://connect.mspbots.ai)

</div>

---

MSPbots Connector gives your AI clients one MCP URL to reach your entire MSP stack (RMM, PSA, documentation, security, finance), and gives you control over who can call which tool and a record of everything that was called.

**Hosted service: [connect.mspbots.ai](https://connect.mspbots.ai)** · Free to use.

### Why Connector

![MSPbots Connector](https://stgoss.mspbots.ai/files/mcp/mspbots-mcp.png)

| | |
|---|---|
| **Visible** | Every tool call is logged: who, which vendor, when. Usage dashboard, CSV export, SIEM streaming. |
| **Controlled** | Role-based, per-tool allowlist. Deny by default. |
| **Protected** | Credentials encrypted per record. AI clients never see your vendor passwords or tokens. |
| **MSP-native** | Built for the MSP stack only: RMM, PSA, documentation, security, finance. |

### Quick start

1. **Sign up** at [connect.mspbots.ai](https://connect.mspbots.ai).
2. **Connect your vendors.** Pick from 150+ connectors and authorize each one on the vendor's own page, or bring your own API keys. No extra vendor accounts needed.
3. **Set access.** Create roles and decide which tools each role may call. Nothing is allowed until you allow it.
4. **Add your MCP URL to your AI client.** Copy the URL from your Connector dashboard into Claude, ChatGPT, Cursor, VS Code, Gemini, Codex, or any MCP-capable client.
5. **Ask your AI to do real work**, and watch every call appear in the audit log.

### Features

**Unified gateway**
- One MCP URL for all your AI clients
- 150+ connectors across the MSP stack
- Custom MCP servers supported, free
- Authorization happens on each vendor's own page; the AI never sees passwords or tokens
- Bring your own credentials: use the vendor API keys you already have
- Multiple accounts per app; connect once, reuse across AI clients
- Tool search: finds the right action for the task
- One sign-in; vendor credentials are injected behind the scenes and OAuth tokens refresh automatically

**Visibility**
- Audit log for every tool call (who, which vendor, when)
- Usage dashboard: call volume, top vendors, error rate, per-user activity
- Export audit logs to CSV, or stream to Loki, Graylog, or LogScale (SIEM)
- Optional recording of tool arguments and result summaries (off by default, enabled per organization)

**Control**
- Per-role, per-tool allowlist, deny by default
- owner / admin / member roles
- SCIM provisioning with Entra ID, Okta, JumpCloud, and Google Workspace

**Security**
- Credentials encrypted one record at a time (AES-256-GCM, per-record key)
- AI clients authenticate with OAuth 2.1 + PKCE
- Vendor responses are scanned for prompt-injection patterns and returned as structured data. This is one layer of defense, not a guarantee against every attack.
- Static egress IP for customer firewall and API allowlisting

### Pricing

**Free.**

Links: [connect.mspbots.ai](https://connect.mspbots.ai) · [mspbots.ai](https://mspbots.ai)

---

## Authentication headers

| Header | Required | Type | Default | Allowed values | Description | Example |
|---|---|---|---|---|---|---|
| `X-Action1-API-Key` | Yes | string | none | - | API credential Client ID | `api-key-xxxx@action1.com` |
| `X-Action1-Secret` | Yes | string | none | - | API credential Client Secret | `YOUR_SECRET` |
| `X-Action1-Region` | No | string | `NorthAmerica` | `NorthAmerica` (`us`, `na`), `NorthAmerica-2` (`NA-2`), `Europe` (`eu`), `UnitedKingdom` (`uk`), `Australia` (`au`); case-insensitive | Action1 data centre of the account | `Europe` |
| `X-Action1-Default-Org-Id` | No | string | none | - | Organization used when a tool call omits `organization_id` | `your-org-id` |

Where to get them:

- **Client ID / Secret**: in the Action1 console, open the **API Credentials** page and create a
  credential. The server exchanges them for a short-lived OAuth token on each request.
- **Region**: the data centre your Action1 account lives in (the console host, e.g.
  `app.eu.action1.com` = `Europe`).
- **Organization id**: returned by `action1_list_organizations`.
- **Permissions**: the credential's role needs `view_endpoints` (endpoints), `view_automations`
  (policies) and one of `approve_updates` / `view_dashboards` / `manage_automations` (missing
  updates).

A request to `/mcp` without the required headers gets HTTP 401 with the list of required
headers. An unknown region does not block `tools/list`; tools then return an `invalid_argument`
error naming the allowed regions.

## Tools

All tools return a JSON string. List tools return `{items, count, total_items, has_more,
next_offset}`; pass `next_offset` as `offset` to get the next page. `limit` defaults to 50
(max 200). `organization_id` defaults to `X-Action1-Default-Org-Id`; for endpoints and updates
the value `all` (also used when no default is set) covers every organization.

| Tool | Purpose | Parameters (required in **bold**) |
|---|---|---|
| `action1_navigate` | Show the tools of one area | **domain** (`endpoints`, `organizations`, `policies`, `updates`) |
| `action1_list_organizations` | List organizations (clients) | - |
| `action1_list_endpoints` | List managed endpoints | organization_id, limit, offset, filter, status, online_status, update_status, reboot_required |
| `action1_get_endpoint` | Full record of one endpoint | **endpoint_id**, organization_id |
| `action1_list_policies` | Scheduled automations of one organization | organization_id, limit, offset, filter |
| `action1_list_missing_updates` | Missing updates, per organization or endpoint | organization_id, limit, offset, endpoint_id, security_severity, approval_status, filter |

Errors come back as a JSON envelope instead of an exception:

```json
{"error": {"code": "unauthorized", "message": "Action1 rejected the API key / secret (token request failed)", "retryable": false}}
```

`code` is one of `not_configured`, `unauthorized`, `not_found`, `invalid_argument`,
`rate_limited`, `upstream_error`.

## Run locally

```bash
uv sync
uv run python -m action1_mcp          # listens on 0.0.0.0:8080
```

or with Docker:

```bash
docker build --platform linux/amd64 -t action1-mcp:dev .
docker run --rm -p 8080:8080 action1-mcp:dev
```

Configuration (environment variables, all optional): `MCP_HTTP_HOST` (default `0.0.0.0`),
`MCP_HTTP_PORT` (default `8080`), `LOG_LEVEL` (default `INFO`). Credentials are never read from
the environment.

## Testing example

```bash
# list tools
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-Action1-API-Key: api-key-xxxx@action1.com" \
  -H "X-Action1-Secret: YOUR_SECRET" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

# endpoints with critical updates missing, across all organizations
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-Action1-API-Key: api-key-xxxx@action1.com" \
  -H "X-Action1-Secret: YOUR_SECRET" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"action1_list_endpoints","arguments":{"organization_id":"all","update_status":"ERROR","limit":10}}}'
```

Unit tests (no network access needed):

```bash
uv run pytest
```

## Delivery notes

- **Policies = automations.** Action1 now calls policies "automations";
  `action1_list_policies` lists the scheduled automations of an organization.
- **Region values.** Both the canonical data-centre names and short codes (`us`, `eu`, `uk`,
  `au`, `NA-2`) are accepted. `UnitedKingdom` is supported.
- **List trimming.** `action1_list_endpoints` returns a summary per endpoint; use
  `action1_get_endpoint` for the full record.

## License

Apache License 2.0 - see [LICENSE](LICENSE) and [NOTICE](NOTICE).