# Avanan (Legacy) MCP Server

An [MCP](https://modelcontextprotocol.io) server for the legacy **Avanan SmartAPI**
(Check Point Harmony Email & Collaboration), hosted on `smart-api-production-*.avanan.net`.
It covers two areas:

- **MSP portfolio** (MSP API key): customer tenants, licenses and add-ons, monthly and daily
  usage for billing, child MSP partners and MSP portal users.
- **Security operations**: security events, secured entities such as emails, allow / block
  exception rules, and quarantine / restore actions with task tracking.

- 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 access token is requested 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-Avanan-App-Id` | Yes | string | none | - | SmartAPI client (application) id | `US:your-app-id` |
| `X-Avanan-Secret` | Yes | string | none | - | Client secret; used only to sign requests, never sent | `your-app-secret` |
| `X-Avanan-Region` | No | string | `us` | `us`, `eu`, `ca`, `ap` (`au`), `euw2` (`uk`), `aps1` (`in`), `mec1` (`uae`) | Region the key belongs to | `eu` |
| `X-Avanan-Token` | No | string | none | - | Pre-issued access token; skips the token request (app id and secret are still needed to sign) | `your-token` |

`X-Avanan-Client-Id` and `X-Avanan-Client-Secret` are accepted as alternative names for the
first two headers.

Where to get them:

- **Client id / secret**: issued by Avanan / Check Point support when the SmartAPI is enabled.
  MSPs use the MSP API key, which also works for every customer tenant in that region.
- **Region**: keys are regional; a key only works against its own region, and you need one key
  per region you manage. MSP management endpoints are not available in the UAE region.

Every request is signed: `x-av-sig` is the SHA-256 hex digest of the Base64 of
request id + app id + date (+ request path and query) + secret. A request to `/mcp` without the
required headers gets HTTP 401 listing them. An unknown region does not block `tools/list`; tool
calls then return an `invalid_argument` error naming the allowed regions.

## Tools

All tools return a JSON string. List tools return `{items, count, total, has_more, scroll_id}`;
pass `scroll_id` back as `scrollId` for the next page. The API has no page size: if a batch is too large for one response, the first records
that fit are returned without `scroll_id` (following it would skip the rest of the batch), and the note
says to narrow the query. Empty values are left out of list records.

MSP portfolio:

| Tool | Purpose | Parameters (required in **bold**) |
|---|---|---|
| `avanan_test_connection` | Check the credentials and region | - |
| `avanan_list_scopes` | farm:tenant scopes the key can access | - |
| `avanan_list_tenants` | Customer tenants | scrollId, MSPId |
| `avanan_get_tenant` | One tenant with license details | **tenant_id** |
| `avanan_create_tenant` | Create a tenant (**write**) | **adminEmail**, **tenantName**, **adminName**, **phone**, **companyName**, **tenantRegion** (`us`, `eu`, `ca`), MSPId |
| `avanan_delete_tenant` | Delete a tenant (**destructive**) | **tenant_id** |
| `avanan_list_licenses` | License packages | - |
| `avanan_list_addons` | Add-ons | - |
| `avanan_assign_license` | Set a tenant's license (**write**) | **tenant_id**, **licenseCodeName**, addonIdList, maxLicensedUsers |
| `avanan_get_monthly_usage` | Billable usage for a month | **year**, **month**, msp_ids, scrollId |
| `avanan_get_daily_usage` | Billable usage for a day | **year**, **month**, **day**, msp_ids, scrollId |
| `avanan_list_msp_partners` | Child MSPs | - |
| `avanan_create_msp_partner` | Create a child MSP (**write**) | **name**, **website**, **country**, **zip**, state |
| `avanan_delete_msp_partner` | Delete a child MSP (**destructive**) | **msp_id** |
| `avanan_list_msp_users` | MSP portal users | scrollId, MSPId |
| `avanan_get_msp_user` | One MSP user | **user_id** |
| `avanan_create_msp_user` | Create an MSP user (**write**) | **firstName**, **lastName**, **email**, **role**, **directLogin**, **samlLogin**, **viewPrivateData**, **sendAlerts**, **receiveWeeklyReports**, MSPId |
| `avanan_update_msp_user` | Replace an MSP user's settings (**write**) | **user_id** plus the same required fields |
| `avanan_delete_msp_user` | Delete an MSP user (**destructive**) | **user_id** |

Security operations:

| Tool | Purpose | Parameters (required in **bold**) |
|---|---|---|
| `avanan_query_events` | Search security events | eventTypes, eventStates, severities, saas, eventIds, confidenceIndicator, startDate, endDate, description, scopes, scrollId |
| `avanan_get_event` | One event | **eventId** |
| `avanan_search_emails` | Search secured entities (emails) | **saas**, **startDate**, saasEntity, endDate, filters (`[{saasAttrName, saasAttrOp, saasAttrValue}]`), scopes, scrollId |
| `avanan_get_email` | One entity | **entityId** |
| `avanan_list_exceptions` | Allow / block rules | **excType** (`whitelist`, `blacklist`) |
| `avanan_get_exception` | One rule | **excType**, **excId** |
| `avanan_add_exception` | Add a rule (**write**) | **excType**, sender / recipient / subject / IP / link fields and matching modes |
| `avanan_update_exception` | Update a rule (**write**) | **excType**, **excId**, same fields |
| `avanan_delete_exception` | Delete a rule (**destructive**) | **excType**, **excId** |
| `avanan_quarantine_events` | Quarantine the emails behind events (**destructive**, reversible) | **eventIds**, scope |
| `avanan_restore_events` | Restore them (**write**) | **eventIds**, scope |
| `avanan_quarantine_emails` | Quarantine emails by entity id (**destructive**, reversible) | **entityIds**, entityType, scope |
| `avanan_restore_emails` | Restore emails (**write**) | **entityIds**, entityType, scope |
| `avanan_get_task_status` | Progress of a quarantine / restore task | **taskId**, scope |

With an MSP key, event and email queries cover all customer scopes by default; action tools
need a single `scope` (from `avanan_list_scopes`).

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

```json
{"error": {"code": "unauthorized", "message": "Avanan rejected the app id / secret for this region (token request failed)", "retryable": false}}
```

`code` is one of `not_configured`, `unauthorized`, `not_found`, `invalid_argument`,
`rate_limited`, `upstream_error`. An HTTP 200 response whose `responseEnvelope.responseCode` is
not 0 is reported as `invalid_argument` with Avanan's response text.

## Run locally

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

or with Docker:

```bash
docker build --platform linux/amd64 -t avanan-legacy-mcp:dev .
docker run --rm -p 8080:8080 avanan-legacy-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-Avanan-App-Id: US:your-app-id" \
  -H "X-Avanan-Secret: your-app-secret" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

# phishing events since a date
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-Avanan-App-Id: US:your-app-id" \
  -H "X-Avanan-Secret: your-app-secret" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"avanan_query_events","arguments":{"eventTypes":["phishing"],"startDate":"2026-01-01T00:00:00.000Z"}}}'
```

Unit tests (no network access needed):

```bash
uv run pytest
```

## Delivery notes

- **Tool count (33).** Above the suggested 20 because the tool names are an existing contract;
  none were merged or removed.
- **Header names.** The server reads `X-Avanan-App-Id` / `X-Avanan-Secret` / `X-Avanan-Region` /
  `X-Avanan-Token` as registered for this integration, and also accepts `X-Avanan-Client-Id` /
  `X-Avanan-Client-Secret`.
- **Write tools.** 15 tools change data (create, update, delete, license, quarantine, restore).
  They are annotated (`readOnlyHint=false`; delete and quarantine also `destructiveHint=true`)
  and their descriptions tell the agent to act only on an explicit request. The exception list
  and get tools are read-only.

## License

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