--- title: "VulnCheck MCP server for AI agents - actionlake" description: "Give Claude 525 VulnCheck actions through one MCP server: backups, cpes, cves, indexes. Your agent never holds the credential. 100,000 calls a month free." canonical: https://actionlake.com/connectors/vulncheck updated: 2026-10-23 --- Connectors · Identity & security # VulnCheck MCP server for AI agents. actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to VulnCheck and the rest of your systems. It gives your agent 525 VulnCheck actions (525 reads and 0 writes) and holds the VulnCheck credential itself, so the agent never does. It paces VulnCheck's limits and records every call. [Connect VulnCheck free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) 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/mcp` the first call ``` do { action: "vulncheck.backups.list", intent: "check which VulnCheck account is connected" } # List indexes with backups · read · 1 upstream call ``` - 525 actions in one signed file - 525 read look, never change - 0 write create and update - 0 wait for a yes destructive, confirmed first Set up ## Connect VulnCheck in three steps. 1. 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` 2. 02 ### Connect VulnCheck. Bearer token. 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. - `access_token` VulnCheck API token: vulncheck.com > sign in > Settings > API Tokens (the free Community tier issues one) ``` account { op: "connections.requirements", service: "vulncheck" } # free: exactly what to paste, and what is found for you ``` 3. 03 ### Make the first call. Check before a write. Ask in plain words; Claude picks the action. Before anything changes, `check` validates the call and prices it, for free. ``` do { action: "vulncheck.backups.list" } # list indexes with backups · read · 1 upstream call ``` VulnCheck at a glance **Sign-in** Bearer token. 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** `access_token` **Limits we pace to** 300 calls a minute, per connection **API covered** VulnCheck API v3 (OpenAPI 3.1.0)`api.vulncheck.com/v3` **Built from** VulnCheck's documentation, read 23 October 2026[api.vulncheck.com](https://api.vulncheck.com/v3/openapi) [docs.vulncheck.com](https://docs.vulncheck.com/) **Service file** Version 1.0.0, signed (Ed25519) **Cached reads** 524 of 525 reads, for up to 5 minutes; a write clears what it affects **Data** Processed and stored in Sydney, Australia. No US region yet Capabilities ## What an AI agent can do in VulnCheck. 525 actions in 2 areas. Every one carries its effect, so a key can allow the reads and hold the rest. - **525** read look, never change - **0** write create and update - **0** destructive wait for a confirmation 1. ### Index 513 513 read · 0 write · 0 destructive List VulnCheck Advisories (advisories) · List VulnCheck Botnets (botnets) · List CISA KEV (Known Exploited Vulnerabilities) (cisa-kev) · List Common Weakness Enumeration Database (cwe) 2. ### Vulncheck 12 12 read · 0 write · 0 destructive List indexes with backups · Retrieve backups for an index · List CVEs for a CPE · Search CPEs Top actions ## The VulnCheck API, shaped for agents. The ids your agent types, what each does, and the one name it shares with other systems. 6 of VulnCheck's 9 action names are shared with at least one other connector, so an agent learns them once. | Action | What it does | Effect | Same name in | | --- | --- | --- | --- | | `vulncheck.backups.list` List indexes with backups | Return a list of indexes with backup and endpoint links. | read | `analytics.data_export.list` 9 connectors | | `vulncheck.backups.get` Retrieve backups for an index | Retrieve a list of backups by index. | read | `analytics.data_export.get` 11 connectors | | `vulncheck.cpes.search` Search CPEs | Return CPEs and associated CPEs by searching CPE fields. | read | this connector | | `vulncheck.cves.search` Search all indexes for a CVE | Search all indices for a CVE. | read | this connector | | `vulncheck.indexes.list` List available indexes | Return a list of available indexes with endpoint links. | read | `infra.search_index.list` 5 connectors | | `vulncheck.entitlements.list` Retrieve user entitlements | Retrieve user entitlements. | read | `platform.capability.list` 11 connectors | | `vulncheck.c2_ips.list` List VulnCheck C2 IP addresses | Retrieve a list of C2 IP addresses. | read | `security.threat.list` 7 connectors | | `vulncheck.openapi.get` Return the OpenAPI specification | Return OpenAPI specification. | read | `platform.schema.get` 24 connectors | | `vulncheck.c2_hostnames.list` List VulnCheck C2 hostnames | Retrieve a list of C2 Hostnames. | read | this connector | Try it ## Prompts to paste into Claude. Each one names the VulnCheck actions it will call, so you know what it reads and what it changes before you send it. 1. Read read List indexes with backups in VulnCheck and tell me what stands out. calls `vulncheck.backups.list` Governance for VulnCheck ## Every write can wait for a yes. None of VulnCheck'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. a key for this connector ``` account { op: "keys.create", name: "vulncheck-agent", allowed_actions: ["vulncheck.*"], cap_calls: 2000, confirm_policy: "human_for_writes" } ``` Illustrative. Scoped to VulnCheck only, capped at 2,000 upstream calls, every write confirmed. Cost ## What VulnCheck costs on actionlake. Every VulnCheck action is one upstream call, the only thing actionlake bills. Searching, `check`, `cost`, `account` and any call VulnCheck 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. - 1 upstream call per action all 525 VulnCheck actions - 525 actions page each page of a long list is one call - 524 reads can be cached a cache hit costs nothing - 100,000 calls a month, free paid plans from US$49 a month for 250,000 [See pricing](https://actionlake.com/pricing) Action index ## Every VulnCheck action. 525 actions by area: the id your agent calls, what it does, and its effect. **Index 513** - `vulncheck.index_advisories.list` List VulnCheck Advisories (advisories) read - `vulncheck.index_botnets.list` List VulnCheck Botnets (botnets) read - `vulncheck.index_cisa_kev.list` List CISA KEV (Known Exploited Vulnerabilities) (cisa-kev) read - `vulncheck.index_cwe.list` List Common Weakness Enumeration Database (cwe) read - `vulncheck.index_7zip.list` List 7Zip Security Advisories (7zip) read - `vulncheck.index_a10.list` List A10 Networks Security Advisories (a10) read - and 507 more in this area **Vulncheck 12** - `vulncheck.backups.get` Retrieve backups for an index read - `vulncheck.backups.list` List indexes with backups read - `vulncheck.cpe_cves.search` List CVEs for a CPE read - `vulncheck.cpes.search` Search CPEs read - `vulncheck.c2_hostnames.list` List VulnCheck C2 hostnames read - `vulncheck.c2_ips.list` List VulnCheck C2 IP addresses read - and 6 more in this area This index shows a sample of each area. All 525 actions, with their inputs and prices, are in the [catalogue](https://actionlake.com/console/catalogue), which a free sandbox key can search. Questions ## The VulnCheck MCP server, answered. **Is there a VulnCheck MCP server for Claude?** Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 525 VulnCheck actions across index and vulncheck, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by VulnCheck. **What do I need to connect VulnCheck?** VulnCheck API token: vulncheck.com > sign in > Settings > API Tokens (the free Community tier issues one). The free call account { op: "connections.requirements", service: "vulncheck" } lists exactly what to paste. **Will an AI agent use up my VulnCheck API limit?** actionlake paces every call to the limits in the VulnCheck service file: 300 calls a minute per connection. Repeated reads are answered from cache (524 VulnCheck actions can be), which never reaches VulnCheck. **What does a VulnCheck action cost?** One upstream call, the only unit actionlake bills. A list that pages bills one call per page (525 VulnCheck actions page). Cache hits, searches, dry runs and calls VulnCheck 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 VulnCheck API does it cover?** The VulnCheck API v3 (OpenAPI 3.1.0) at api.vulncheck.com/v3. It is built from VulnCheck's documentation as read on 23 October 2026. 525 actions in 2 areas, each one in the signed service file (version 1.0.0). **Does actionlake keep my VulnCheck 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 VulnCheck 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. ## More connectors like VulnCheck Shares the most action names with - [Google Security Operations 2](https://actionlake.com/connectors/google-security-operations) - [Mimecast 1](https://actionlake.com/connectors/mimecast) - [UpGuard 1](https://actionlake.com/connectors/upguard) - [Socket 1](https://actionlake.com/connectors/socket) - [Okta 1](https://actionlake.com/connectors/okta) Browse - [All Identity & security connectors](https://actionlake.com/connectors/category/identity-and-security) - [All connectors](https://actionlake.com/connectors) - [How actionlake compares](https://actionlake.com/compare) actionlake is independent. It is not made or endorsed by VulnCheck; the name is the vendor's own. Counts are from the VulnCheck service file, version 1.0.0. ## Give your agent VulnCheck today. [Connect VulnCheck free](https://actionlake.com/console?start=sandbox) [See pricing](https://actionlake.com/pricing) Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free. --- Source: https://actionlake.com/connectors/vulncheck More: https://actionlake.com/llms.txt