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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。