VulnTracker MCP

search_cves

Read-onlyIdempotent

Search the CVE list with filters. Results are newest first, up to 100 per call; when has_more is true pass next_cursor back as 'cursor' for the following page (at most 10 pages per filter set, so narrow the filters instead of walking the whole database). 'tracked_only' limits to CVEs matching the API key's team trackings.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_cves"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max results (default 20, max 100)
`query`	No	Free text matched against CVE id prefix or vulnerability name
`cursor`	No	next_cursor from the previous search_cves answer, with the same filters
`vendor`	No	Vendor name filter
`product`	No	Product name filter
`severity`	No	critical, high, medium, low
`exploited`	No	Only CVEs in CISA KEV (is_exploited). SSVC exploitation (poc / active) is a separate field on lookup_cve
`remediation`	No	Only CVEs with a published VulnTracker guide of this kind: fix, workaround, guidance
`tracked_only`	No	Only CVEs matching this account's trackings
`published_after`	No	YYYY-MM-DD
`published_before`	No	YYYY-MM-DD

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 10, 2026

addedInput schema / properties / cursor

Added value: +{
+  "description": "next_cursor from the previous search_cves answer, with the same filters",
+  "type": "string"
+}

changedInput schema / properties / exploited / description

Previous value: -"Only CVEs with known exploitation (KEV / exploit evidence)"New value: +"Only CVEs in CISA KEV (is_exploited). SSVC exploitation (poc / active) is a separate field on lookup_cve"

First observedNov 10, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds real behavior beyond the readOnlyHint/idempotentHint annotations: result ordering (newest first), per-call cap (100), a 10-page ceiling per filter set, and the has_more/next_cursor paging contract. It does not describe error or empty-result behavior, but the operational envelope is well disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences with the purpose front-loaded and no filler. The long semicolon-chained pagination sentence is slightly heavy but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 11 parameters and no output schema, the description carries the important return-shape burden by explaining has_more and next_cursor, and it explains the page cap. Filter-level details are left to the fully covered schema, which is appropriate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description reinforces cursor usage and clarifies that tracked_only is scoped to the API key's team trackings, but most of that is already in the schema and no new filter semantics are introduced.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource, 'Search the CVE list with filters', which is unambiguous about what the tool does. It does not distinguish itself from siblings such as lookup_cve or product_cves, so an agent must infer the boundary, but the core purpose is clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete operational guidance: narrow filters rather than walking the database, and the 10-page-per-filter-set ceiling. It lacks explicit when-to-use-this-vs-lookup_cve guidance, but the pagination and narrowing advice is genuinely actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All VulnTracker MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?