# simplesat-mcp

MCP server for **Simplesat** (CSAT/NPS customer feedback survey
platform). Exposes the Simplesat **V1 API**'s answer search as an MCP
tool.

> Naming note: Simplesat has two generations of integration in MSPbots —
> a legacy 2021-era integration (`subjectCode=SIMPLESAT`, `GET
> /api/answers/`, a `token` field) and the current one this server
> targets (`subjectCode=SIMPLESATV1`, `POST /api/v1/answers/search`, an
> `apiKey` field). Only the current V1 API is covered here.

<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)

---

## Overview

- Stateless HTTP service. No credentials are ever persisted — each request
  supplies its own API key via a header, used only for the lifetime of
  that single request.
- Supports concurrent requests; per-request credential isolation is done via
  Python `contextvars`, not a global/shared client instance.
- Entry points: `POST /mcp` (MCP protocol) and `GET /health` (health check).
- Default port: `8080` (configurable via `MCP_HTTP_PORT`).

## Authentication

Simplesat uses a single static API key — no login or token exchange:

```
X-Simplesat-Token: <api key>
```

Already fully stateless by the vendor's own design; nothing is cached
across MCP calls.

### HEADER Authorization Parameters

| Header | Type | Required | Default | Allowed values | Description | Example |
|---|---|---|---|---|---|---|
| `X-Simplesat-Api-Key` | string | Yes | None | None | Simplesat API Key (generated at Account Settings -> API Keys), forwarded as-is as the upstream `X-Simplesat-Token` request header | `ssat_170927_a1b2c3d4e5f6g7h8i9j0` |

Missing the header returns `401`:
```json
{
  "error": "Missing credentials",
  "message": "This server requires the X-Simplesat-Api-Key header",
  "required_headers": ["X-Simplesat-Api-Key"],
  "optional_headers": []
}
```

An invalid key surfaces as a tool-level structured error envelope (e.g.
`{"error":{"code":"unauthorized","message":"Invalid Token.","retryable":false}}`),
not an HTTP-level error from this server — see the error envelope format
under **Tool List** below.

## Environment Variables

| Variable | Type | Required | Default | Description |
|---|---|---|---|---|
| `MCP_HTTP_PORT` | int | No | `8080` | HTTP listen port |
| `MCP_HTTP_HOST` | string | No | `0.0.0.0` | HTTP listen address |
| `SIMPLESAT_BASE_URL` | string | No | `https://api.simplesat.io` | Simplesat API base URL |

## MCP Endpoint

- `POST /mcp` — MCP protocol (streamable HTTP transport)
- `GET /health` — health check, pure local probe (does not depend on the Simplesat API), returns `{"status": "ok"}`

## Tool List

| Tool | Description | Parameters |
|---|---|---|
| `simplesat_search_answers` | Search survey answers (CSAT/NPS scores and comments), read-only | `page`, `page_size` (default/max 100, see below), `start_date`, `end_date`, `filter_key`, `filter_values`, `filter_comparison` (all optional) |

- `page_size` is clamped server-side to Simplesat's own documented maximum of
  **100** records per page (stricter than it might otherwise be) — values
  above 100 are silently capped rather than rejected upstream.
- Responses are compact JSON (no pretty-printing, `ensure_ascii=False`), and
  are truncated with `truncated`/`original_count` markers if a result would
  exceed ~20,000 characters.
- Errors are returned as a structured envelope, not a plain string:
  `{"error": {"code": "...", "message": "...", "retryable": true|false}}`.
  `code` is one of `not_configured` / `unauthorized` / `not_found` /
  `invalid_argument` / `rate_limited` / `upstream_error`.

## Test Example

```bash
# Health check
curl -s http://localhost:8080/health

# Call a tool via the MCP protocol (streamable HTTP) — requires an
# initialize handshake first per the MCP spec; abbreviated example below
# shows the tool-call request body only:
curl -s -X POST http://localhost:8080/mcp \
  -H "X-Simplesat-Api-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "mcp-session-id: <session-id-from-initialize>" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "simplesat_search_answers",
      "arguments": {}
    }
  }'
```

**Live-verified** (2026-07-31) against a real Simplesat account:
`simplesat_search_answers` called end-to-end through this running server
with the real API key returned `200` and the vendor's correctly-shaped
response (`{"next": null, "previous": null, "count": 0, "answers": []}`)
— this particular test account has zero survey answers recorded yet,
confirmed as a genuine empty result (not an auth failure) since the
response shape exactly matches the vendor's documented schema. A
separate test with a deliberately invalid API key correctly surfaced
the structured error envelope
`{"error":{"code":"unauthorized","message":"Invalid Token.","retryable":false}}`,
confirming the auth failure path works as expected (re-verified 2026-08-19
after the error format was changed from a plain string to this structured
envelope).

## API Reference

- Public, no login required: https://developer.simplesat.io/api (full V1
  API reference, including the Search Answers operation used here)

## Known Gaps

- **Scope is exactly the 1 method MSPbots' current integration uses**
  (`Search answers`) — the Simplesat V1 API also covers Customers, Team
  members, Responses, Surveys, and Questions, plus `Get answer by ID` and
  `Update answer by ID`; those are out of scope here.
- **`simplesat_search_answers` could not be verified with non-empty
  results** — the test account has zero recorded survey answers. Auth
  and request-shape correctness were confirmed via (1) a 200 response
  matching the vendor's exact documented response schema, and (2) a
  separate invalid-key test correctly returning a 403 `Invalid Token`
  error.
- **The `filter_key`/`filter_values`/`filter_comparison` parameters
  expose only a single filter object** — the vendor's API technically
  accepts an array of filter objects for compound filtering, but MSPbots'
  own usage of this integration sends no filters at all, so this server
  keeps the tool signature simple rather than exposing arbitrary
  multi-filter arrays.