mcpField
O
Osv

Osv

Remote
pipeworx.ioSecurity0Updated 5w ago

About Osv

Osv is an MCP server for querying the OSV.dev database, intended for developers and security workflows that check open-source dependencies. It looks up package or commit vulnerabilities, retrieves full records, and supports batch queries for dependency scans.

Key features

  1. 01Find package vulnerabilities
  2. 02Look up vulnerabilities by commit
  3. 03Retrieve full vulnerability records
  4. 04Batch-query up to 1000 entries

Use cases

  1. 01Check a package and version for known issues
  2. 02Review vulnerabilities affecting a pinned commit
  3. 03Scan lockfile dependencies in batches
  4. 04Retrieve details for a vulnerability ID

MCP support

Exposes OSV.dev vulnerability queries to MCP clients through the Pipeworx gateway or a local stdio server. The gateway endpoint also includes shared Pipeworx meta-tools.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/osv/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-osv

OSV.dev (Open Source Vulnerabilities) MCP.

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

ToolDescription
query_package_vulnsFind all known vulnerabilities for an open-source package, optionally at a specific version, via the OSV.dev database. Omit version to get every vuln known for the package. Returns a compact summary array (id, summary, aliases, severity, references). Keyless.
get_vulnerabilityGet full detail for a single vulnerability by its OSV ID — e.g. "GHSA-jf85-cpcp-j695", "CVE-2021-23337", "PYSEC-2021-XXX". Returns summary, details, aliases, severity, affected packages/ranges, and references. Keyless.
query_by_commitFind vulnerabilities affecting a specific source-repository git commit via OSV.dev. Useful when you have a pinned commit hash rather than a released version. Returns the same compact vuln summary array. Keyless.
query_batchBatch vulnerability query against OSV.dev (up to 1000 entries per call) — for SBOM-style "scan every dependency in this lockfile" workflows. Pass an array of {package:{name,ecosystem}, version?} or {commit} entries. Returns the vuln IDs matched per query (use get_vulnerability for full detail per ID). Keyless.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "osv": {
      "url": "https://gateway.pipeworx.io/osv/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/osv/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/query_package_vulns \
  -H 'Content-Type: application/json' \
  -d '{"name":"lodash","ecosystem":"npm"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/query_package_vulns. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "osv": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-osv"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-osv

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Osv data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.