Connectors · Identity & security
Proofpoint TAP MCP server for AI agents.
actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Proofpoint TAP and the rest of your systems. It gives your agent 14 Proofpoint TAP actions (14 reads and 0 writes) and holds the Proofpoint TAP credential itself, so the agent never does. It paces Proofpoint TAP's limits and records every call.
100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.
claude mcp add --transport http actionlake https://connect.actionlake.com/mcpdo { action: "proofpoint_tap.siem.all", intent: "check which Proofpoint TAP account is connected"}# SIEM: all events · read · 1 upstream call- 14actionsin one signed file
- 14readlook, never change
- 0writecreate and update
- 0wait for a yesdestructive, confirmed first
Set up
Connect Proofpoint TAP in three steps.
- 01
Add actionlake to Claude.
Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.
https://connect.actionlake.com/mcp - 02
Connect Proofpoint TAP.
Username and secret. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.
principalTAP service principalsecretTAP service secret shown once beside the principal
account { op: "connections.requirements", service: "proofpoint_tap" } # free: exactly what to paste, and what is found for you - 03
Make the first call. Check before a write.
Ask in plain words; Claude picks the action. Before anything changes,
checkvalidates the call and prices it, for free.do { action: "proofpoint_tap.siem.all" }# siem: all events · read · 1 upstream call
Proofpoint TAP at a glance
- Sign-in
- Username and secret. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
- You provide
principalsecret- Limits we pace to
- 1,800 calls a day, per connection
- API covered
- TAP API v2 (tap-api-v2.proofpoint.com)
tap-api-v2.proofpoint.com - Built from
- Proofpoint TAP's documentation, read 23 October 2026help.proofpoint.com
- Service file
- Version 1.0.0, signed (Ed25519)
- Cached reads
- 14 of 14 reads, for up to 5 minutes; a write clears what it affects
- Shared entities
- 1, so ask can line Proofpoint TAP up with your other systems
- Data
- Processed and stored in Sydney, Australia. No US region yet
Capabilities
What an AI agent can do in Proofpoint TAP.
14 actions in 6 areas. Every one carries its effect, so a key can allow the reads and hold the rest.
- 14readlook, never change
- 0writecreate and update
- 0destructivewait for a confirmation
Siem
66 read · 0 write · 0 destructive
SIEM: all events · SIEM: blocked clicks · SIEM: permitted clicks · SIEM: issues (permitted clicks and delivered messages)
Campaigns
22 read · 0 write · 0 destructive
List campaign IDs · Get campaign
Forensics
22 read · 0 write · 0 destructive
Get forensics for a campaign · Get forensics for a threat
People
22 read · 0 write · 0 destructive
List Very Attacked People · List top clickers
Threats
11 read · 0 write · 0 destructive
Get threat summary
Urls
11 read · 0 write · 0 destructive
Decode URL Defense rewritten URLs
Top actions
The Proofpoint TAP API, shaped for agents.
The ids your agent types, what each does, and the one name it shares with other systems. 1 of Proofpoint TAP's 1 action names are shared with at least one other connector, so an agent learns them once.
| Action | What it does | Effect | Same name in |
|---|---|---|---|
proofpoint_tap.threats.getGet threat summary | Summary of one threat: type, category, status, severity, attack spread, and associated actors, families, malware, techniques and brands. | read | security.threat.get3 connectors |
proofpoint_tap.people.list_vapList Very Attacked People | Identities and attack-index breakdown of the organisation's Very Attacked People (VAPs) for the period, ordered by attack index. | read | this connector |
proofpoint_tap.siem.allSIEM: all events | All click and message events relating to known threats in the time window. | read | this connector |
proofpoint_tap.siem.issuesSIEM: issues (permitted clicks and delivered messages) | Events for permitted clicks to malicious URLs and delivered messages containing a known threat in the time window. | read | this connector |
proofpoint_tap.urls.decodeDecode URL Defense rewritten URLs | Decodes URLs rewritten by TAP URL Defense (urldefense.proofpoint.com v1/v2/v3 links) back to their original target URLs. | read | this connector |
proofpoint_tap.campaigns.list_idsList campaign IDs | IDs of campaigns active in a time window, sorted by last update. | read | this connector |
proofpoint_tap.people.list_top_clickersList top clickers | Identities and click statistics of the users most prone to clicking malicious URLs (blocked or not) in the period. | read | this connector |
proofpoint_tap.campaigns.getGet campaign | Details of a campaign: description, actors, malware families, techniques and member threat variants. | read | this connector |
proofpoint_tap.forensics.get_by_threatGet forensics for a threat | Aggregate forensic evidence (indicators of compromise) for one threat. | read | this connector |
proofpoint_tap.forensics.get_by_campaignGet forensics for a campaign | Aggregate forensic evidence (indicators of compromise) for an entire campaign. | read | this connector |
Try it
Prompts to paste into Claude.
Each one names the Proofpoint TAP actions it will call, so you know what it reads and what it changes before you send it.
- Readread
Who has access in Proofpoint TAP? List every user and their role.
calls
proofpoint_tap.people.list_vap
Governance for Proofpoint TAP
Every write can wait for a yes.
None of Proofpoint TAP's actions is destructive. A key can still be held to reads, capped, and set so a person confirms every write.
A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.
account { op: "keys.create", name: "proofpoint-tap-agent", allowed_actions: ["proofpoint_tap.*"], cap_calls: 2000, confirm_policy: "human_for_writes"}Cost
What Proofpoint TAP costs on actionlake.
Every Proofpoint TAP action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Proofpoint TAP refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.
- 1upstream call per actionall 14 Proofpoint TAP actions
- 14actions pageeach page of a long list is one call
- 14reads can be cacheda cache hit costs nothing
- 100,000calls a month, freepaid plans from US$49 a month for 250,000
Action index
Every Proofpoint TAP action.
14 actions by area: the id your agent calls, what it does, and its effect.
Siem6
proofpoint_tap.siem.allSIEM: all eventsreadproofpoint_tap.siem.clicks_blockedSIEM: blocked clicksreadproofpoint_tap.siem.clicks_permittedSIEM: permitted clicksreadproofpoint_tap.siem.issuesSIEM: issues (permitted clicks and delivered messages)readproofpoint_tap.siem.messages_blockedSIEM: blocked messagesreadproofpoint_tap.siem.messages_deliveredSIEM: delivered messagesread
Campaigns2
proofpoint_tap.campaigns.getGet campaignreadproofpoint_tap.campaigns.list_idsList campaign IDsread
Forensics2
proofpoint_tap.forensics.get_by_campaignGet forensics for a campaignreadproofpoint_tap.forensics.get_by_threatGet forensics for a threatread
People2
proofpoint_tap.people.list_top_clickersList top clickersreadproofpoint_tap.people.list_vapList Very Attacked Peopleread
Threats1
proofpoint_tap.threats.getGet threat summaryread
Urls1
proofpoint_tap.urls.decodeDecode URL Defense rewritten URLsread
Questions
The Proofpoint TAP MCP server, answered.
Is there a Proofpoint TAP MCP server for Claude?
Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 14 Proofpoint TAP actions across siem, campaigns, forensics and people, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Proofpoint TAP.
What do I need to connect Proofpoint TAP?
TAP service principal and TAP service secret shown once beside the principal. The free call account { op: "connections.requirements", service: "proofpoint_tap" } lists exactly what to paste.
Will an AI agent use up my Proofpoint TAP API limit?
actionlake paces every call to the limits in the Proofpoint TAP service file: 1,800 calls a day per connection. Repeated reads are answered from cache (14 Proofpoint TAP actions can be), which never reaches Proofpoint TAP.
What does a Proofpoint TAP action cost?
One upstream call, the only unit actionlake bills. A list that pages bills one call per page (14 Proofpoint TAP actions page). Cache hits, searches, dry runs and calls Proofpoint TAP refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.
Which Proofpoint TAP API does it cover?
The TAP API v2 (tap-api-v2.proofpoint.com) at tap-api-v2.proofpoint.com. It is built from Proofpoint TAP's documentation as read on 23 October 2026. 14 actions in 6 areas, each one in the signed service file (version 1.0.0).
Does actionlake keep my Proofpoint TAP data, and where?
actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Proofpoint TAP credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.
Which AI clients can use it?
Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.
Give your agent Proofpoint TAP today.
Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.
