Skip to content
MCP server

VulnTracker

Check dependencies against an affected-version ledger of CVEs and fix versions

Install
Pricing
Freemium
Platforms
API
Runs
Remotely
Version
2.5.0
Listing updated
3 days ago

About VulnTracker

VulnTracker is a freemium MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.

Where a model might guess from memory, this hosted server looks versions up. Give it name@version pairs, up to 50 per call, and it reports which are vulnerable, which CVEs apply, and which release fixes each one. Results carry flags such as fix_stated_by_source, which is false when the fix version was derived from a range bound rather than stated by the vendor, and a match_confidence so low-confidence matches are not counted as vulnerable until confirmed.

The README describes a typical session: the agent reads your lock files, calls check_dependencies, verifies hits with lookup_cve and returns a table of fix versions. Pro and Business accounts can go further and put exploited CVEs on a team board or start tracking products, vendors and keywords. In Claude Code the same procedure is exposed as a scan_dependencies prompt.

There is nothing to install; the endpoint is https://api.vulntracker.io/mcp with a bearer key that starts with vt_. A free account gets 30 read-only calls a day.

Install

Run in a terminal

claude mcp add --transport http mcp https://api.vulntracker.io/mcp

Add to Settings → Connectors → Add custom connector

https://api.vulntracker.io/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://api.vulntracker.io/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://api.vulntracker.io/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://api.vulntracker.io/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://api.vulntracker.io/mcp"
    }
  }
}

Tools this server provides (14)

Taken from the project documentation; the running server may differ.

check_dependencies
Reports which name@version pairs are vulnerable, up to 50 per call
search_products
Finds the VulnTracker slug for a product
product_versions
Lists known versions of a product with CVE and fix counts
check_version
Lists CVEs affecting a version and the version that fixes each
product_cves
Lists all CVEs recorded against a product with version ranges
lookup_cve
Returns the full record for a CVE
search_cves
Filters CVEs by vendor, product, severity, exploited status and dates
remediation_guide
Returns the published fix or workaround guide for a CVE
list_board_cards
Shows your team's CVE board with triage status
list_trackings
Shows what your team is watching
add_to_board
Puts CVEs on the team board (Pro and above)
update_board_card
Changes a card's status, resolution or notes (Pro and above)
track
Starts watching a product, vendor, CVE or keyword (Pro and above)
untrack
Stops watching an item (Pro and above)

What it does

Batch dependency check
Test up to 50 name@version pairs per call.
Per-version CVE lookup
See which CVEs affect an exact version and which version fixes each.
Full CVE records
Scores, EPSS, KEV and SSVC data, vendor advisories and exploit repos in one record.
Confidence flags
Matches are tagged exact, token or fallback, and fallbacks need confirmation.
Team board
Pro and above can add CVEs to a board with status and notes.
Tracking
Watch a product, vendor, CVE or keyword.

Good for

  • Scan a repository's lock files for vulnerable dependencies
  • Find the first safe version after a CVE hits your stack
  • Triage exploited CVEs onto a shared team board
  • Look up the vendor remediation guide for a specific CVE

Pricing

Freemium

Free account with 30 read-only calls a day; Pro and Business prices not published here

Prices change. Check vulntracker.io before you buy.

VulnTracker FAQ

What are the usage limits?

The README gives 30 read-only calls a day on a free account, 1,000 a day on Pro and 5,000 a day on Business, reset at 00:00 UTC.

How do I authenticate?

Create an API key under Settings, API keys on vulntracker.io and send it as a bearer token; keys start with vt_.

Which tools can write?

add_to_board, update_board_card, track and untrack need Pro or higher and act on the key's team.

What does an unclear fix version mean?

If fix_stated_by_source is false the fix was derived from a range bound rather than stated by the vendor.

Is VulnTracker free?

VulnTracker has a free plan, with paid plans for more usage or features.

How do I add VulnTracker to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://api.vulntracker.io/mcp

What are the best alternatives to VulnTracker?

The closest alternatives to VulnTracker are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to VulnTracker

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools