Claude
- Open Dependency Risk Audit in the Claude directory ↗
- Click Connect
- Sign in to your account

Dependency Risk Audit reads a lockfile or manifest that the user pastes or links (a public raw file address) and checks each pinned package against the OSV.dev vulnerability database.
It understands package-lock.json (v1 to v3), yarn.lock, pnpm-lock.yaml, requirements.txt, poetry.lock, Pipfile.lock, go.sum, go.mod, Cargo.lock, Gemfile.lock, composer.lock and Maven pom.xml (direct dependencies with literal versions). Each vulnerability is reported with its identifiers and aliases (CVE, GHSA), severity and CVSS score where the record carries one, affected and fixed versions, and a link to the OSV record. A licence summary from deps.dev and from the lockfile itself flags copyleft licences (GPL, AGPL, LGPL, SSPL and similar) and unknown licences.
Files with more than 500 packages are checked in parts with an offset. A project can be saved: the server re-scans it on a schedule (weekly on the free plan, daily on Pro), records an alert for each new vulnerability that affects a saved package, and emails one digest per check round.
Vulnerability records come from OSV.dev and the databases it aggregates; each source keeps its own licence (for example the GitHub Advisory Database is CC-BY 4.0). Package metadata comes from deps.dev. Licences are as declared by the package, not legal advice, and results are a screening aid rather than a guarantee that a package is safe.
https://deps.tidybutton.com/mcphttps://deps.tidybutton.com/mcpdeps.tidybutton.comaccount_statuscheck_packageget_alertsget_vulnerabilitylist_projectsactivate_licenseaudit_dependenciesrescan_nowsave_projectremove_projectNot found; the server needs sign-in so there may be skills that our scan couldn't access
Dependency Risk Audit reads a lockfile or manifest that the user pastes or links (a public raw file address) and checks each pinned package against the OSV. dev vulnerability database. It understands package-lock.
Open its listing in the app's connector directory and connect. Sign in to your account in the browser window that opens. It uses OAuth, so the AI never sees your password. Step-by-step setup for each app is on this page.
The Dependency Risk Audit MCP server URL is https://deps.tidybutton.com/mcp. Paste it as a custom connector in Claude, ChatGPT, Gemini or Grok, or add it to Claude Code, Cursor or any MCP client. Setup steps.
Yes. Dependency Risk Audit is published or run by Tidy Button, so it is the official MCP server. See other official connectors.
It is listed in 1 store: Claude. Apps where it is not listed can usually still add it as a custom connector.
It is ranked 11,167 of 11,897 in the Claude directory. A rank is the store's own order, not a usage count. How we track ranks.
It has 10 tools: 5 read data, 4 change data and 1 can delete or overwrite data. See every tool and its inputs.
Yes. 4 tools can change data and 1 tool can delete or overwrite it. Most AI apps ask before they run these. The store marks these as destructive:
None that we found. Not found; the server needs sign-in so there may be skills that our scan couldn't access.
No. Its answers come back as text in the chat. Connectors with interactive UI.
This page updates every day. To ask about Dependency Risk Audit from Claude, ChatGPT or a coding agent, connect the Agent Ready MCP server: it tracks ranks, tools and new listings across the AI plugin stores.