SpamTitan MCP Server

An MCP server for the SpamTitan REST API (v3), the email security gateway MSPs use to filter inbound mail. It lets an AI agent search the quarantine, inspect held messages, read the sender allow and block lists and mail flow statistics and, on explicit request, release or delete quarantined messages and change the allow / block lists.

• 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; every tool is listed from the first tools/list

• Python 3.12, uv, FastMCP, httpx

• License: Apache-2.0, Copyright 2026 MSPbots.ai

MSPbots Connector

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

Get started at connect.mspbots.ai →

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 · Free to use.

Why Connector

Quick start

1. Sign up at 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 · mspbots.ai

Related MCP server: proofpoint-essentials-mcp

Authentication headers

Where to get them:

• In the SpamTitan web interface open Settings -> User Management -> RestAPI Keys and add a token for an account with access to quarantine, allow / block lists and reports.

• The base URL is the address of the SpamTitan web interface. If SpamTitan is served under a path, include it (for example https://mail.example.com/spamtitan).

How the token is sent to SpamTitan: as Authorization: Bearer <token> to {X-SpamTitan-Base-URL}/restapi/.... Values that look like unresolved templates (${...}) are treated as missing.

A request to /mcp without both headers gets HTTP 401 listing them; a non-https base URL gets HTTP 400.

Tools

All tools return a JSON string.

sender, recipient and subject filters accept * as a wildcard. Allow / block list entries are addresses (user@example.com) or domains written as @example.com.

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

{"error": {"code": "unauthorized", "message": "SpamTitan returned HTTP 401 for quarantine: Unauthorized.", "retryable": false}}

code is one of not_configured, unauthorized, not_found, invalid_argument, rate_limited, upstream_error. Reads are retried with backoff on 429, 5xx and network errors; writes only on 429.

Run locally

uv sync
uv run python -m spamtitan_mcp          # listens on 0.0.0.0:8080

or with Docker:

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

# list tools
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-SpamTitan-API-Key: your-api-key" \
  -H "X-SpamTitan-Base-URL: https://spamtitan.example.com" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

# quarantined mail for one recipient
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-SpamTitan-API-Key: your-api-key" \
  -H "X-SpamTitan-Base-URL: https://spamtitan.example.com" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"spamtitan_get_queue","arguments":{"recipient":"jane@example.com"}}}'

Unit tests (no network access needed):

uv run pytest

Delivery notes

• Built on the documented REST API. Every call follows the SpamTitan RESTful API v3 reference (/restapi with a Bearer token): /quarantine, /quarantine/{id} (show, release with POST, delete with DELETE), /allow-list, /block-list and /reports/scan-summary.

• Release and delete need the message's secret_id; the server reads it from the message record first, so callers only pass message_id. spamtitan_release_message gained an optional forward_to.

• Removing list entries looks the sender up and deletes the matching entry ids, as the API deletes by id.

• Rolling periods (last_7_days, last_30_days, last_90_days) are sent as a start / end date range; today and yesterday use the report's named periods.

• Tool count (9). Tool names and required parameters are unchanged. reason is now the set of quarantine types the API knows.

• Write tools. Release, delete and list changes are annotated and their descriptions tell the agent to act only on explicit request; delete is irreversible. There are no other write tools.

• No interactive prompts. Older versions asked the user for a recipient before an unfiltered queue listing, which a stateless gateway cannot relay; the queue now pages instead.

• Queue paging. SpamTitan pages by number only. The queue also takes offset (a message position that overrides page) and returns next_offset: when a page is too large for one response and is cut, next_offset starts right after the last message returned, which no page number can.

License

Apache License 2.0 - see LICENSE and NOTICE.