Skip to main content
Glama
Patrowl

PatrowlIntelMCP

Official
by Patrowl
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

patrowl-intel-mcp

An MCP server that exposes PatrowlIntel vulnerability intelligence (CVEs, EPSS, CISA KEV, public exploits, trending attacks) to any MCP client. It is a thin, read-only stdio wrapper over the public PatrowlIntel API.

v0 — three tools: search_cves, get_cve, list_trending_attacks.

Tools

Tool

Purpose

search_cves

Filter/rank the CVE feed (risk score, EPSS, KEV, exploited, technology, dates).

get_cve

Full record for one CVE (CVSS, EPSS, KEV, SSVC, exploits, references).

list_trending_attacks

Recent trending threats, filterable by severity and date.

Related MCP server: cwe-search_mcp

Configuration (environment)

Variable

Default

Purpose

PATROWL_INTEL_API_BASE

https://intel.patrowl.io

Backend API base URL.

PATROWL_INTEL_WEB_BASE

= API base

Public site base used for CVE citation links.

PATROWL_INTEL_API_KEY

(unset)

Reserved for the future authenticated tier.

PATROWL_INTEL_TIMEOUT

15

Per-request timeout (seconds).

PATROWL_INTEL_MCP_TRANSPORT

stdio

stdio (local clients) or streamable-http (networked service).

PATROWL_INTEL_MCP_HOST

127.0.0.1

Bind host for streamable-http.

PATROWL_INTEL_MCP_PORT

8790

Bind port for streamable-http.

Run

# stdio (default) — for local MCP clients that launch the process
uv run patrowl-intel-mcp          # or: pip install -e . && patrowl-intel-mcp

# streamable-http — as a networked service (e.g. Docker); serves at /mcp
PATROWL_INTEL_MCP_TRANSPORT=streamable-http PATROWL_INTEL_MCP_HOST=0.0.0.0 \
  uv run patrowl-intel-mcp

Client config

{
  "mcpServers": {
    "patrowl-intel": {
      "command": "uvx",
      "args": ["patrowl-intel-mcp"],
      "env": { "PATROWL_INTEL_API_BASE": "https://<your-intel-host>" }
    }
  }
}

During local development, point command at your checkout instead:

{ "command": "uv", "args": ["--directory", "/path/to/PatrowlIntelMCP", "run", "patrowl-intel-mcp"] }

Available Tools

3 tools
get_cveA

Fetch full intelligence for a single CVE: CVSS, EPSS, CISA KEV status and dates, CISA SSVC decision, public exploit links, affected technologies, weaknesses and references.

ParametersJSON Schema
NameRequiredDescriptionDefault
cve_idYesCVE identifier, e.g. 'CVE-2024-3400'.
verboseNoInclude full CVSS vectors, CPEs, all references and the raw SSVC block.

TDQS

A4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It clearly describes what data is fetched (CVSS, EPSS, etc.), conveying a read-only intent. However, it does not mention potential side effects, rate limits, or authentication requirements, though such transparency is less critical for a simple fetch operation.

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

Conciseness5/5

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

A single sentence that front-loads the purpose and lists key data items. Every phrase adds value, with no extraneous 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?

Without an output schema, the description serves as the output specification. It lists multiple data fields (CVSS, EPSS, etc.), which is sufficient. Minor gaps include no mention of response size or pagination (not needed for a single CVE), and no explicit note about error handling for invalid CVE IDs.

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?

The input schema covers 100% of parameters with descriptions. The description adds global context but does not enhance parameter meaning beyond the schema. No additional format or constraint details are given for the required cve_id or optional verbose.

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

Purpose5/5

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

The description clearly states that the tool fetches full intelligence for a single CVE, listing specific data points like CVSS, EPSS, CISA KEV status, etc. This distinguishes it from sibling tools like search_cves which presumably handles multiple CVEs, and list_trending_attacks which focuses on trending attacks rather than individual CVEs.

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

Usage Guidelines3/5

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

The description implies usage for fetching data on a single CVE, but does not explicitly state when to use this tool versus alternatives (e.g., search_cves for bulk or list_trending_attacks for trending). No when-not or exclusion criteria are provided.

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

search_cvesA

Search the PatrowlIntel CVE feed with rich filters and return compact, ranked results. Use it to triage by risk (min_score / min_epss), surface KEV or exploited CVEs, or scope a vendor/technology. For the full record of one CVE, follow up with get_cve.

ParametersJSON Schema
NameRequiredDescriptionDefault
sortNoOrdering; default '-score' (most risky first).-score
limitNoMax results, 1-100.
queryNoFree-text match on CVE id or summary.
is_kevNoOnly CVEs in the CISA KEV catalog.
min_epssNoMinimum EPSS exploit probability (0-1).
is_remoteNoOnly remotely exploitable CVEs.
min_scoreNoMinimum Patrowl EASM risk score (0-1).
technologyNoVendor/product substring, e.g. 'Apache' or 'Fortinet FortiOS'.
has_exploitNoOnly CVEs with at least one public exploit.
published_toNoISO date upper bound on publication.
published_fromNoISO date lower bound on publication, e.g. 2026-01-01.

TDQS

A4.2/5.0
Behavior3/5

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

No annotations provided, so description carries full burden. It implies a read operation (search) but does not explicitly state read-only, no side effects, or disclose rate limits or authentication needs. The mention of 'compact, ranked results' adds some behavioral context, but more specifics would be beneficial.

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

Conciseness5/5

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

Two sentences, front-loaded with purpose, efficient use of words. No fluff.

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?

Given no output schema and no annotations, the description covers the tool's purpose, use cases, and relationship to siblings. Could mention output format or pagination but overall complete for a search tool.

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 all parameters are documented. The description does not add extra meaning beyond the schema, which is acceptable. Baseline score of 3 is appropriate as the schema carries the load.

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

Purpose5/5

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

The description clearly states it searches the PatrowlIntel CVE feed with rich filters, returning compact ranked results. It distinguishes from the sibling 'get_cve' by indicating that for full records one should use that tool.

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

Usage Guidelines5/5

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

Explicitly provides use cases: triage by risk, surface KEV/exploited CVEs, scope vendor/technology, and instructs to follow up with get_cve for full records. This gives clear when-to-use and when-not-to-use guidance.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 3 tool updatesv0.0.1
    • First observedget_cve
    • First observedlist_trending_attacks
    • First observedsearch_cves
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.3/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: get_cve retrieves full details for a single CVE, list_trending_attacks shows trending threats, and search_cves provides filtered search. No ambiguity between them.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern (get_cve, list_trending_attacks, search_cves), making them predictable and easy to understand.

Tool Count5/5

Three tools is appropriate for a focused threat intelligence server. Each tool serves a distinct, essential function (detail retrieval, trending list, search) without being too few or too many.

Completeness4/5

The tool set covers the core needs: fetching CVE details, searching with filters, and viewing trending threats. Minor gaps exist, such as lacking a direct tool for bulk listing or subscription features, but the set is largely complete for typical use cases.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • cve-mcp

    badchars
    A
    license
    A
    quality
    A
    maintenance
    Unifies NVD, EPSS, CISA KEV, GitHub Advisory, and OSV into a single MCP server, enabling AI agents to query vulnerability intelligence conversationally with 23 tools for incident response, prioritization, dependency audits, and threat monitoring.
    41
    582
    20
    MIT

  • wpscan-mcp

    sjinks
    A
    license
    A
    quality
    A
    maintenance
    Enables querying the WPScan API for WordPress plugin, theme, core vulnerabilities, and specific vulnerability lookups through MCP tools.
    4
    24
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Patrowl/PatrowlIntelMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server