Skip to main content
Glama
Proofpoint MCP Server

Proofpoint MCP Server

README.md
# Proofpoint MCP Server

An [MCP](https://modelcontextprotocol.io) server for Proofpoint
[Targeted Attack Protection (TAP)](https://www.proofpoint.com/us/products/advanced-threat-protection/targeted-attack-protection)
and, independently, **Proofpoint Essentials** (a different Proofpoint product), used by MSPs and
security teams to investigate email threats. It lets an AI agent read the TAP SIEM feed (threat
messages delivered or blocked, malicious URL clicks), search those messages, drill into threats,
campaigns and sandbox forensics, see the most attacked people and top clickers, decode URL
Defense links, and, with a separate key, read the Dashboard reports. With its own, independent
credentials it can also read an Essentials organization's domain and user inventory, and
Essentials' own SIEM-shaped threat feed. With a third, also independent credential set
(Proofpoint Protection Server) it can list, search, release and delete quarantined messages.

- 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
- Read only: no tool changes anything in Proofpoint
- 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

Four credential sets are recognised -- **TAP**, **Proofpoint Essentials Admin**,
**Proofpoint Essentials Threat**, and **Proofpoint Protection Server (PPS)** -- and each is
independent: sending one never requires or affects the others. The gateway itself requires at
least one of the first three (TAP / Essentials Admin / Essentials Threat) to be fully present;
PPS is purely additive on top of that and only unlocks the 4 quarantine tools (see "A request to
`/mcp`..." below). A caller that only ever sends TAP headers is completely unaffected by the
other three sets existing.

| Header | Required | Type | Default | Allowed values | Description | Example |
|---|---|---|---|---|---|---|
| `X-Proofpoint-Service-Principal` | with `-Secret` | string | none | - | TAP service principal | `your-service-principal` |
| `X-Proofpoint-Service-Secret` | with `-Principal` | string | none | - | TAP service secret | `your-service-secret` |
| `X-Proofpoint-Cluster-Url` | No | string | `https://tap-api-v2.proofpoint.com` | https URL on a `proofpoint.com` host | TAP API base URL | `https://tap-api-v2.proofpoint.com` |
| `X-Proofpoint-Reports-Key` | No | string | none | - | Dashboard Reports API key (only for `reports_*` tools) | `your-reports-key` |
| `X-Proofpoint-Reports-Secret` | No | string | none | - | Dashboard Reports API secret | `your-reports-secret` |
| `X-Proofpoint-Essentials-User` | with `-Password` | string | none | - | Essentials Organization Admin username | `admin@example.com` |
| `X-Proofpoint-Essentials-Password` | with `-User` | string | none | - | Essentials Organization Admin password | `your-essentials-password` |
| `X-Proofpoint-Essentials-Admin-Url` | No | string | `https://us1.proofpointessentials.com/api/v1` | https URL on a `proofpointessentials.com` host | Essentials Admin regional stack base URL | `https://us5.proofpointessentials.com/api/v1` |
| `X-Proofpoint-Essentials-Threat-Key` | with `-Secret` | string | none | - | Essentials Threat API Integration Key | `your-threat-key` |
| `X-Proofpoint-Essentials-Threat-Secret` | with `-Key` | string | none | - | Essentials Threat API Integration Secret | `your-threat-secret` |
| `X-Proofpoint-Essentials-Threat-Url` | No | string | `https://us-siem.proofpointessentials.com` | https URL on a `proofpointessentials.com` host | Essentials Threat API host | `https://eu-siem.proofpointessentials.com` |
| `X-Proofpoint-Pps-Base-Url` | No | string | none | https URL, bare host | Proofpoint Protection Server (PPS) REST API base URL; required to use the quarantine tools | `https://tenant.pphosted.com:10000` |
| `X-Proofpoint-Pps-Username` | No | string | none | - | PPS API-role account username; required to use the quarantine tools | `your-pps-username` |
| `X-Proofpoint-Pps-Password` | No | string | none | - | PPS API-role account password; required to use the quarantine tools | `your-pps-password` |

Where to get them:

- **TAP service credentials:** create a service credential on the **Settings** page of the TAP
  (Threat Insight) Dashboard; it shows the service principal and the secret.
- **Reports API key (optional):** in the Admin Portal open **Settings -> API Key Management ->
  Threat Protection** and choose **Create New**. The TAP service principal is not accepted by
  the Reports API, so the four `reports_*` tools need this second pair.
- **Essentials Admin credentials:** a Proofpoint Essentials Organization Admin username and
  password for the organization to read.
- **Essentials Threat API credentials:** an Integration Key/Secret pair, separate from both TAP
  and Essentials Admin (see [Essentials Threat API docs](https://help.proofpoint.com/Essentials/Additional_Resources/API_Documentation/Essentials_Threat_API)).
- **PPS credentials (optional, only for the quarantine tools):** an administrator with a role
  that includes REST API access on your Proofpoint Protection Server. Cloud tenants: request
  this through a Proofpoint support ticket. On-prem: enable the API GUI in `filter.cfg` and
  create an API-type admin role in the PPS management interface.

How credentials are sent to Proofpoint: TAP calls go to the cluster URL
(`https://tap-api-v2.proofpoint.com/v2/...`) with HTTP Basic authentication
(`principal:secret`). Reports calls first get a Bearer token from
`POST https://auth.proofpoint.com/v1/token` (client credentials grant with the reports key and
secret), then call `https://threatprotection-api.proofpoint.com/api/v1/dash/reports/...`; the
token is used only within the one request. Essentials Admin calls send `X-User` / `X-Password`
as literal headers (not HTTP Basic) to the Admin base URL. Essentials Threat calls use HTTP
Basic with the Integration Key/Secret against the Threat base URL, the same way TAP does.
Quarantine calls go to the PPS base URL (`<pps-base-url>/rest/v1/quarantine`) with HTTP Basic
authentication (`pps_username:pps_password`).

A base-url header that fails its structural check does not block the request (tools/list still
works): a malformed TAP cluster URL, Essentials Admin URL or Essentials Threat URL makes every
tool call return an `invalid_argument` error before any outbound request, while a malformed PPS
base URL does the same only for the 4 quarantine tools, leaving every other tool unaffected --
so credentials can never be sent elsewhere either way. The PPS base URL has no domain-suffix
allowlist (unlike the other three): PPS cloud tenants are on `*.pphosted.com` and on-prem
tenants are on an arbitrary customer host. Values that look like unresolved templates
(`${...}`) are treated as missing.

A request to `/mcp` with none of TAP / Essentials Admin / Essentials Threat fully present gets
HTTP 401 naming all three options. Sending only TAP headers (today's behavior) is unaffected;
calling an Essentials tool without its credentials returns a `not_configured` error naming the
missing headers instead of a 401, since the gateway already let the request through on another
set. PPS is not part of this gate -- its 3 headers are purely optional: without them, the 4
quarantine tools return `not_configured`; every other tool is unaffected.

## Tools

All tools return a JSON string.

**Time windows.** The TAP SIEM API returns at most one hour per call and keeps 7 days of events.
SIEM-based tools take one of `sinceSeconds` (1-3600), `sinceTime` (ISO8601, within the last
hour) or `interval` (ISO8601, 30 seconds to 1 hour, e.g.
`2026-01-01T12:00:00Z/2026-01-01T13:00:00Z`); the default is the last hour. Search tools take
`startDate` / `endDate` instead, covering at most one hour.

| Tool | Purpose | Parameters (required in **bold**) |
|---|---|---|
| `proofpoint_navigate` | Describe the tools of one area (changes nothing) | **domain** |
| `proofpoint_status` | Check that TAP accepts the credentials; which of Reports/Essentials Admin/Essentials Threat/PPS were sent; with org_domain, also probes Essentials Admin | org_domain |
| `proofpoint_tap_get_all_threats` | All threat messages and clicks in a window | sinceSeconds, sinceTime, interval, threatStatus, threatType, format, max_events |
| `proofpoint_tap_get_messages_delivered` | Threat messages that reached users | same as above |
| `proofpoint_tap_get_messages_blocked` | Threat messages blocked or quarantined | same as above |
| `proofpoint_tap_get_clicks_permitted` | Malicious URL clicks that were allowed | same as above |
| `proofpoint_tap_get_clicks_blocked` | Malicious URL clicks that were blocked | same as above |
| `proofpoint_events_list` | All events as one list, filtered by classification or outcome | sinceSeconds, sinceTime, interval, threatType (`spam`, `phish`, `malware`, `impostor`), disposition, max_events |
| `proofpoint_events_get_details` | One event by GUID, id, QID or Message-ID | **event_id**, sinceSeconds, sinceTime, interval |
| `proofpoint_events_get_stats` | Counts by event type, classification, status; top recipients and senders | sinceSeconds, sinceTime, interval |
| `proofpoint_smart_search_trace` | Find threat messages by sender, recipient, subject, Message-ID | sender, recipient, subject, message_id, startDate, endDate, status, page, per_page, offset |
| `proofpoint_smart_search_get_message` | Full TAP record of one threat message | **message_id**, sinceSeconds, sinceTime, interval |
| `proofpoint_smart_search_get_headers` | Envelope and header fields of one threat message | **message_id**, sinceSeconds, sinceTime, interval |
| `proofpoint_forensics_search_messages` | Find threat messages by sender, subject, Message-ID or threat id | sender, subject, message_id, threat_id, startDate, endDate, limit |
| `proofpoint_forensics_get_threat` | Sandbox forensics for a threat (or its whole campaign) | **threat_id**, includeCampaignForensics |
| `proofpoint_forensics_get_campaign` | Aggregate forensics for a campaign | **campaign_id** |
| `proofpoint_threat_get_by_id` | Threat summary | **threat_id** |
| `proofpoint_threat_get_campaign` | Campaign details, actors, malware, techniques | **campaign_id** |
| `proofpoint_threat_list_families` | Malware families, actors and techniques of recent campaigns | sinceTime, interval (up to 1 day), max_campaigns |
| `proofpoint_threat_get_iocs` | IOCs from a campaign's forensics, or threats in a SIEM window | campaign_id, sinceTime, interval, threat_type |
| `proofpoint_people_get_vap` | Very Attacked People | window (14, 30, 90), page, size, offset |
| `proofpoint_people_get_top_clickers` | Users who clicked the most malicious URLs | window, page, size, offset |
| `proofpoint_people_get_user_risk` | One user's VAP and top-clicker standing | **email**, window |
| `proofpoint_url_decode` | Decode URL Defense rewritten links | **urls** |
| `proofpoint_url_analyze` | Decode and break down one link | **url** |
| `proofpoint_reports_org_summary` | Inbound protection overview | window (1, 7, 14, 30, 90) |
| `proofpoint_reports_threat_summary` | Threat volume by category | window, threatType |
| `proofpoint_reports_mail_flow` | Trend of protected messages | window, granularity |
| `proofpoint_reports_executive_summary` | Threat categories, VAPs and top clickers | window (7, 14, 30, 90) |
| `proofpoint_quarantine_list` | Quarantined messages in Proofpoint Protection Server (PPS), optionally filtered | sender, recipient, subject, startDate, endDate, folder, page, per_page |
| `proofpoint_quarantine_search` | Find a quarantined message by sender, recipient or subject (one query, matched as OR) | **query**, startDate, endDate, page, per_page |
| `proofpoint_quarantine_release` | Release a quarantined message | **message_id** |
| `proofpoint_quarantine_delete` | Permanently delete a quarantined message | **message_id** |
| `proofpoint_policy_list` / `_get` / `_list_routes` | Unavailable (see below) | as before |
| `proofpoint_dlp_list_incidents` / `_get_incident` / `_list_encrypted` | Unavailable (see below) | as before |
| `proofpoint_forensics_pull_messages` | Unavailable (see below) | **message_ids**, reason |
| `proofpoint_essentials_list_domains` | Essentials: domains in an organization | **org_domain**, page, size, offset |
| `proofpoint_essentials_get_domain` | Essentials: one domain's record | **org_domain**, **domain** |
| `proofpoint_essentials_list_users` | Essentials: users in an organization | **org_domain**, page, size, offset |
| `proofpoint_essentials_get_user` | Essentials: one user's record | **org_domain**, **email** |
| `proofpoint_essentials_threat_get_messages_blocked` | Essentials: threat messages blocked or quarantined in a window | sinceSeconds, sinceTime, interval, threatStatus, threatType, format, max_events |
| `proofpoint_essentials_threat_get_messages_delivered` | Essentials: threat messages delivered in a window | same as above |
| `proofpoint_essentials_threat_get_clicks_blocked` | Essentials: malicious URL clicks blocked in a window | same as above |
| `proofpoint_essentials_threat_get_clicks_permitted` | Essentials: malicious URL clicks allowed through in a window | same as above |
| `proofpoint_essentials_threat_get_issues` | Essentials: permitted clicks and delivered messages combined | same as above |
| `proofpoint_essentials_threat_get_all` | Essentials: every threat message and click event in a window | same as above |

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

```json
{"error": {"code": "rate_limited", "message": "Proofpoint returned HTTP 429 for /v2/people/vap: the API quota for this endpoint is used up; try again later", "retryable": false}}
```

`code` is one of `not_configured`, `unauthorized`, `not_found`, `invalid_argument`,
`rate_limited`, `upstream_error`. `not_configured` from an `essentials_*` tool means that
request's credential set (Essentials Admin or Essentials Threat) was not sent -- it can still
happen alongside valid TAP credentials, since the three sets are independent.

**Quotas.** Proofpoint throttles per credential over a rolling 24 hours: SIEM 1800 calls,
People 50, Campaign 50, Forensics 50 per threat id; Reports allow 10 calls a minute and 20 a day
per report section. A 429 is therefore reported as not retryable. Reads (and URL decoding, a
pure function) are retried with backoff on 5xx and network errors.

## Run locally

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

or with Docker:

```bash
docker build --platform linux/amd64 -t proofpoint-mcp:dev .
docker run --rm -p 8080:8080 proofpoint-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-Proofpoint-Service-Principal: your-service-principal" \
  -H "X-Proofpoint-Service-Secret: your-service-secret" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

# threat messages delivered in the last 30 minutes
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-Proofpoint-Service-Principal: your-service-principal" \
  -H "X-Proofpoint-Service-Secret: your-service-secret" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"proofpoint_tap_get_messages_delivered","arguments":{"sinceSeconds":1800}}}'

# Proofpoint Essentials: domains in an organization (independent credentials, no TAP headers needed)
curl -s http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "X-Proofpoint-Essentials-User: admin@example.com" \
  -H "X-Proofpoint-Essentials-Password: your-essentials-password" \
  -d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"proofpoint_essentials_list_domains","arguments":{"org_domain":"example.com"}}}'
```

Unit tests (no network access needed):

```bash
uv run pytest
```

## Delivery notes

- **Tool count (50).** The 40 original tool names are kept as is because they are an existing
  contract; the 10 Essentials tools (PRD-21255) are additive -- no existing tool was renamed or
  removed, and no existing header became required.
- **Proofpoint Essentials is a separate v1 scope (PRD-21255).** Essentials is a different
  product from TAP (different base URL, different credentials, different API shape). This
  version ships read-only Domains, Users and the Essentials Threat API (the ticket's actual ask:
  live, read, logged access); Essentials Organization/Features/Licensing/Reporting/Package and
  any write tools are out of scope because the exact field names for the first group could not be
  confirmed from a static doc fetch, and the second would need its own destructive-tool safety
  review. See `docs/tickets/PRD-21255.md` for the full design and the `.ac.json` test cases.
- **Real endpoints only.** Earlier versions called paths that the TAP API does not have
  (`/v1/quarantine`, `/v1/policies`, `/v1/dlp/...`, `/v1/smart-search`, `/v2/events/...`,
  `/v1/reports/...`, `/v2/threat/families`, `/v2/url/analyze`, `/v2/people/{email}`). Each tool
  now uses a documented endpoint:
  - `events_*`, `smart_search_*` and `forensics_search_messages` filter SIEM events
    (`/v2/siem/all`), so they see messages that carried a TAP threat, one hour at a time.
  - `forensics_get_threat` / `_get_campaign` use `/v2/forensics?threatId=` / `?campaignId=`.
  - `threat_get_campaign` uses `/v2/campaign/{id}`; `threat_list_families` lists
    `/v2/campaign/ids` and reads the campaigns' malware, actors and techniques;
    `threat_get_iocs` extracts indicators from forensics or SIEM threats.
  - `people_get_user_risk` looks the user up in the VAP and top-clicker lists.
  - `url_analyze` decodes the link with `/v2/url/decode` and parses it; TAP has no URL scoring.
  - `reports_*` use the Dashboard Reports API, which needs its own key (optional headers).
- **Unavailable tools.** Policy, DLP / encryption and message pull belong to other Proofpoint
  products (Protection Server, Essentials, Threat Response), or -- for policy -- are not exposed
  by any Proofpoint API found during research (TAP, Essentials Interface/Threat APIs, PPS REST
  API; confirmed 2026-10-30). These 7 tools stay listed for compatibility, change nothing, and
  return `invalid_argument` naming the TAP tool that covers the nearest need.
- **Quarantine, via Proofpoint Protection Server (PRD-21254).** The 4 `quarantine_*` tools keep
  their names and parameters but now call the real PPS REST API (`<pps-base-url>/rest/v1/quarantine`,
  documented via the Cortex XSOAR "Proofpoint Protection Server v2" integration -- Proofpoint has
  no single official PPS REST reference) when PPS credentials are sent; otherwise they return
  `not_configured`. `message_id` is an opaque `folder:localguid` pair minted by `_list`/`_search`
  and consumed by `_release`/`_delete` -- callers must not construct one themselves.
  `_search`'s single `query` parameter is matched as OR across sender/recipient/subject (three
  PPS lookups, merged and de-duplicated) to keep the tool's existing single-field search promise.
- **Cluster/base URL checks.** `X-Proofpoint-Cluster-Url` is accepted only as an https URL on a
  `proofpoint.com` host, so a caller cannot redirect the TAP Basic credentials to another server.
  `X-Proofpoint-Pps-Base-Url` has the same structural check (https, bare host) but no domain
  allowlist, because PPS cloud tenants are on `*.pphosted.com` and on-prem tenants are on an
  arbitrary customer host -- the PPS admin password is supplied by the same tenant that supplies
  the base URL, so the trust boundary is unchanged, but this is a narrower check than the TAP one
  and is called out here for that reason.
- **Bounded output.** SIEM lists are capped per list (`max_events`, default 100) with the full
  counts reported; every result is capped at 20,000 characters.
- **Paging by offset.** `smart_search_trace`, `people_get_vap` and `people_get_top_clickers` page
  by page number, and a page cut to fit the size limit has its rest on no other page. They also
  take `offset` (record position, overriding `page`) and return `next_offset`, which continues
  right after the last record returned; pass it back to read every record exactly once.
  `essentials_list_domains` / `essentials_list_users` use the same offset/next_offset contract,
  but page client-side over a list fetched once per call rather than sending `page`/`size` to
  the vendor: the Essentials Admin API's own pagination contract could not be confirmed from a
  static doc fetch (no account available -- see "Proofpoint Essentials is a separate v1 scope"
  above), and this is correct regardless of what the vendor's own paging does, at the cost of
  re-fetching the full list on every page for very large organizations.
- **No interactive prompts or UI cards.** The stateless gateway cannot relay them; missing
  information is a required parameter or an error instead.

## License

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