purify-feeds-mcp
MCP server for querying live CISA KEV, EPSS, and enriched vulnerability feeds with full provenance. Enables natural-language access to auditable security-intelligence data from Claude Desktop and other MCP clients.
README
purify-feeds-mcp
MCP server for Purify's production security-intelligence feeds. Lets Claude Desktop, Cursor and other MCP clients query live CISA KEV / EPSS / enriched vulnerability feeds — every answer carries an auditable feed version and full per-record provenance.
The feeds behind this server are continuously scheduled, quality-gated and
self-healing. Each record ships with a _purify data passport: where it was
fetched from, when, with which extractor, and the hash of the raw artifact it
came from.
Tools
| Tool | Purpose |
|---|---|
list_feeds |
List feeds with record counts and current version (dataset artifact hash) |
search_feed |
AND filters / sort / up to 50 rows, plus an exact total_matched count |
get_provenance |
Return a record's _purify passport and the feed's run chain, by CVE id |
check_feed_changed |
Incremental primitive: compare a known hash to detect new feed versions |
Feeds
| Name | Contents |
|---|---|
kev |
CISA Known Exploited Vulnerabilities catalog |
epss |
EPSS high-risk slice (exploit prediction scores) |
enriched |
EPSS + KEV joined view with risk bands |
Install
go install github.com/eason4kim-rocket/purify-feeds-mcp@latest
Or use the Docker image (no Go toolchain needed):
docker pull ghcr.io/eason4kim-rocket/purify-feeds-mcp:latest
Or build from source:
git clone https://github.com/eason4kim-rocket/purify-feeds-mcp
cd purify-feeds-mcp && go build .
Configure (Claude Desktop)
~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"purify-feeds": {
"command": "/path/to/purify-feeds-mcp",
"env": {
"PURIFY_API_URL": "https://feeds.verifly.pro/feeds-api",
"PURIFY_API_KEY": "<your-api-key>"
}
}
}
}
Or with Docker (the image defaults PURIFY_API_URL to the public gateway):
{
"mcpServers": {
"purify-feeds": {
"command": "docker",
"args": ["run", "-i", "--rm", "-e", "PURIFY_API_KEY",
"ghcr.io/eason4kim-rocket/purify-feeds-mcp:latest"],
"env": { "PURIFY_API_KEY": "<your-api-key>" }
}
}
}
The public gateway is read-only (GET only, feed whitelist, per-key rate
limits). Health check: https://feeds.verifly.pro/healthz — no key needed.
API keys are issued manually during the pilot — open an issue or
contact the maintainer to get one.
Environment variables
PURIFY_API_URL— feeds API base URL (defaulthttp://127.0.0.1:8091for local/dev use)PURIFY_API_KEY— API key, sent as a bearer token (required for the public gateway)PURIFY_FEEDS— override the built-in feed table:name=spec_id,...
Example prompts
- "Which CVEs entered CISA KEV in the last 7 days? Give vendors and remediation due dates."
- "How many CVEs have EPSS > 0.99 and are in KEV? Top 5?"
- "Where does the data for CVE-2026-45659 come from?" (
get_provenancereturns the full passport) - Agent loops: remember
artifact_hash, callcheck_feed_changedfirst on the next run, and only re-triage when the feed actually changed.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.