Connectors · Identity & security
Rapid7 InsightVM MCP server for AI agents.
actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Rapid7 InsightVM and the rest of your systems. It gives your agent 14 Rapid7 InsightVM actions (10 reads, 3 writes and 1 that wait for a confirmation) and holds the Rapid7 InsightVM credential itself, so the agent never does. It paces Rapid7 InsightVM'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: "rapid7_insightvm.scans.list", intent: "check which Rapid7 InsightVM account is connected"}# List scans · read · 1 upstream call- 14actionsin one signed file
- 10readlook, never change
- 3writecreate and update
- 1wait for a yesdestructive, confirmed first
Set up
Connect Rapid7 InsightVM 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 Rapid7 InsightVM.
API key. 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.
api_keyInsight Platform API key: insight.rapid7.com > Administration > API Key Management > New User Key (or Organization Key)regionYour Rapid7 InsightVM region
account { op: "connections.requirements", service: "rapid7_insightvm" } # 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: "rapid7_insightvm.scans.list" }# list scans · read · 1 upstream callcheck { action: "rapid7_insightvm.scans.start", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent
Rapid7 InsightVM at a glance
- Sign-in
- API key. 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
api_key- Setup fields
region- Limits we pace to
- 300 calls a minute, per connection
- API covered
- InsightVM Cloud Integrations API v4 (OpenAPI 3.1.0, 13 operations), at your own api.insight.rapid7.com address, set when you connect
- Built from
- Rapid7 InsightVM's documentation, read 22 October 2026help.rapid7.comhelp.rapid7.com
- Service file
- Version 1.0.0, signed (Ed25519)
- Cached reads
- 6 of 10 reads, for up to 5 minutes; a write clears what it affects
- Shared entities
- 1, so ask can line Rapid7 InsightVM up with your other systems
- Data
- Processed and stored in Sydney, Australia. No US region yet
Capabilities
What an AI agent can do in Rapid7 InsightVM.
14 actions in 7 areas. Every one carries its effect, so a key can allow the reads and hold the rest.
- 10readlook, never change
- 3writecreate and update
- 1destructivewait for a confirmation
Scan engines
42 read · 1 write · 1 destructive
List scan engines · Get a scan engine · Update scan engine configuration · Remove scan engine configuration properties
Scans
42 read · 2 write · 0 destructive
List scans · Start a scan · Get a scan · Stop a scan
Assets
22 read · 0 write · 0 destructive
Search assets · Get an asset
API key
11 read · 0 write · 0 destructive
Validate the API key
Health
11 read · 0 write · 0 destructive
Health check
Sites
11 read · 0 write · 0 destructive
List sites
Vulnerabilities
11 read · 0 write · 0 destructive
Search vulnerabilities
Top actions
The Rapid7 InsightVM API, shaped for agents.
The ids your agent types, what each does, and the one name it shares with other systems. 10 of Rapid7 InsightVM's 10 action names are shared with at least one other connector, so an agent learns them once.
| Action | What it does | Effect | Same name in |
|---|---|---|---|
rapid7_insightvm.api_key.validateValidate the API key | Validate the API key. | read | identity.current_user.get307 connectors |
rapid7_insightvm.scans.listList scans | List scans. | read | security.vulnerability_scan.list6 connectors |
rapid7_insightvm.scans.startStart a scan | Start a scan. | write | security.vulnerability_scan.create4 connectors |
rapid7_insightvm.vulnerabilities.searchSearch vulnerabilities | Search vulnerabilities. | read | security.vulnerability.search4 connectors |
rapid7_insightvm.assets.searchSearch assets | Search assets. | read | asset.asset.search6 connectors |
rapid7_insightvm.assets.getGet an asset | Get an asset. | read | asset.asset.get40 connectors |
rapid7_insightvm.scan_engines.listList scan engines | List scan engines. | read | device.scanner.list2 connectors |
rapid7_insightvm.scan_engines.getGet a scan engine | Get a scan engine. | read | device.scanner.get2 connectors |
rapid7_insightvm.scan_engines.update_configurationUpdate scan engine configuration | Update scan engine configuration. | write | device.scanner.update2 connectors |
rapid7_insightvm.sites.listList sites | List sites. | read | this connector |
rapid7_insightvm.scans.stopStop a scan | Stop a scan. | write | this connector |
rapid7_insightvm.scan_engines.remove_configurationRemove scan engine configuration properties | Remove scan engine configuration properties. | destructive | this connector |
Try it
Prompts to paste into Claude.
Each one names the Rapid7 InsightVM actions it will call, so you know what it reads and what it changes before you send it.
- Readread
Which Rapid7 InsightVM devices have not checked in for a week?
calls
rapid7_insightvm.assets.search - Writewrite
Start a scan in Rapid7 InsightVM. Show me exactly what you will send before you save it.
calls
rapid7_insightvm.scans.start
Governance for Rapid7 InsightVM
Destructive actions wait for a yes.
1 Rapid7 InsightVM action is destructive. This is it:
- Remove scan engine configuration properties
rapid7_insightvm.scan_engines.remove_configuration
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.
Remove scan engine configuration properties?
intent: the user asked me to remove scan engine configuration properties
account { op: "keys.create", name: "rapid7-insightvm-agent", allowed_actions: ["rapid7_insightvm.*"], cap_calls: 2000, confirm_policy: "human_for_writes", approval_rules: [ { match: "rapid7_insightvm.scan_engines.remove_configuration", approver: "[email protected]" } ]}Cost
What Rapid7 InsightVM costs on actionlake.
Every Rapid7 InsightVM action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Rapid7 InsightVM 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 Rapid7 InsightVM actions
- 14actions pageeach page of a long list is one call
- 6reads can be cacheda cache hit costs nothing
- 100,000calls a month, freepaid plans from US$49 a month for 250,000
Action index
Every Rapid7 InsightVM action.
14 actions by area: the id your agent calls, what it does, and its effect.
Scan engines4
rapid7_insightvm.scan_engines.getGet a scan enginereadrapid7_insightvm.scan_engines.listList scan enginesreadrapid7_insightvm.scan_engines.remove_configurationRemove scan engine configuration propertiesdestructiverapid7_insightvm.scan_engines.update_configurationUpdate scan engine configurationwrite
Scans4
rapid7_insightvm.scans.getGet a scanreadrapid7_insightvm.scans.listList scansreadrapid7_insightvm.scans.startStart a scanwriterapid7_insightvm.scans.stopStop a scanwrite
Assets2
rapid7_insightvm.assets.getGet an assetreadrapid7_insightvm.assets.searchSearch assetsread
API key1
rapid7_insightvm.api_key.validateValidate the API keyread
Health1
rapid7_insightvm.health.getHealth checkread
Sites1
rapid7_insightvm.sites.listList sitesread
Vulnerabilities1
rapid7_insightvm.vulnerabilities.searchSearch vulnerabilitiesread
Questions
The Rapid7 InsightVM MCP server, answered.
Is there a Rapid7 InsightVM MCP server for Claude?
Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 14 Rapid7 InsightVM actions across scan engines, scans, assets and API key, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Rapid7 InsightVM.
What do I need to connect Rapid7 InsightVM?
Insight Platform API key: insight.rapid7.com > Administration > API Key Management > New User Key (or Organization Key). Plus your region. The free call account { op: "connections.requirements", service: "rapid7_insightvm" } lists exactly what to paste.
Can an AI agent delete or change things in Rapid7 InsightVM?
Only if its key allows it, and only with an explicit confirmation. 1 Rapid7 InsightVM action is destructive, including remove scan engine configuration properties. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.
Will an AI agent use up my Rapid7 InsightVM API limit?
actionlake paces every call to the limits in the Rapid7 InsightVM service file: 300 calls a minute per connection. Repeated reads are answered from cache (6 Rapid7 InsightVM actions can be), which never reaches Rapid7 InsightVM.
What does a Rapid7 InsightVM action cost?
One upstream call, the only unit actionlake bills. A list that pages bills one call per page (14 Rapid7 InsightVM actions page). Cache hits, searches, dry runs and calls Rapid7 InsightVM 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 Rapid7 InsightVM API does it cover?
The InsightVM Cloud Integrations API v4 (OpenAPI 3.1.0, 13 operations) at your own api.insight.rapid7.com address, set when you connect. It is built from Rapid7 InsightVM's documentation as read on 22 October 2026. 14 actions in 7 areas, each one in the signed service file (version 1.0.0).
Does actionlake keep my Rapid7 InsightVM 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 Rapid7 InsightVM 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 Rapid7 InsightVM today.
Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.