secfeed
OfficialThis server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
secfeed
Security Intelligence MCP server — aggregates authoritative vulnerability, news, and threat-intel feeds into a local SQLite database and serves them to AI agents via MCP tools.
Every ingested item is auto-classified against the agent-security-manual threat taxonomy (TH-01..TH-10), so agents can pull an AI-agent-security focused feed and trace each threat to its mitigating controls (CT), requirements (REQ), and manual chapters.
Data sources
Category | Sources |
Vulnerabilities | CISA KEV, NVD CVE API 2.0, EPSS, GitHub Security Advisories, GitHub PoC search |
Threat intel | Abuse.ch ThreatFox, CISA Cybersecurity Advisories, arXiv cs.CR |
News | The Hacker News, BleepingComputer, Krebs on Security, The Record, SANS ISC |
Agent security | Simon Willison's blog, Embrace The Red |
Related MCP server: cve-mcp
MCP tools
Tool | Purpose |
| Recent CVEs sorted by EPSS exploit probability |
| Known Exploited Vulnerabilities (confirmed in-the-wild) |
| Aggregated security news |
| FTS5 full-text search across all data |
| On-demand NVD + EPSS lookup for one CVE |
| 24h threat landscape briefing + feed health |
| Items tagged with agent threat classes TH-01..TH-10 |
| Resolve TH/CT ids to controls, REQs, and manual chapters |
| Per-threat-class activity digest for posture review |
Agent threat taxonomy
Classification is a deterministic two-tier keyword classifier (taxonomy.py):
strong agent-specific patterns always tag; generic security terms tag only when
AI/agent context is present in the same text. No LLM calls — results are
reproducible and auditable.
ID | Threat class |
TH-01 | Prompt injection (direct / indirect) |
TH-02 | Tool abuse / privilege escalation |
TH-03 | RAG / knowledge-base poisoning |
TH-04 | Memory / context contamination |
TH-05 | Agent identity / authority abuse |
TH-06 | Delegation / multi-agent abuse |
TH-07 | Supply-chain / MCP / plugin compromise |
TH-08 | Data exfiltration / secret exposure |
TH-09 | Audit / evaluation evasion |
TH-10 | Model / service abuse |
Deployment
The default docker-compose.yml attaches secfeed only to the external Docker
network ai_network and does not publish host ports. Production traffic
reaches the container on port 8888 from nginx or another service on that
network (for example https://mcp.aoifuture.com/secfeed/mcp with Bearer auth).
Create the network once if it does not exist yet:
docker network create ai_network
docker compose up -d --build
docker logs --tail 80 secfeedFor local HTTP access from the host, add a ports mapping (not in the default
file), for example "127.0.0.1:8888:8888", then use
http://127.0.0.1:8888/mcp.
Streamable HTTP (in-container):
http://<host>:8888/mcp— use a reverse proxy with auth for any public exposurestdio mode:
python3 server.py --stdioData volume:
secfeed-datamounted at/data(SQLite + FTS5)
Environment variables
Variable | Purpose |
| Optional — higher NVD API rate limits |
| Optional — higher GitHub API rate limits |
| Optional — Abuse.ch ThreatFox API auth (fetcher uses the public feed when unset) |
| DB path override (default |
Secrets are injected via the compose environment block from the host
environment — never commit them.
Development
python3 -m venv venv && venv/bin/pip install -r requirements.txt
SECFEED_DB_PATH=/tmp/secfeed-dev.db venv/bin/python3 server.py --stdio
python3 -m unittest test_fetcher.pyFastMCP is pinned to <4.0.0 in requirements.txt until MCP 2026-07-28
migration is proven end-to-end; see
docs/mcp-2026-07-28-migration.md.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.
CVE lookups (NVD) and dependency-manifest audits (OSV) for AI agents. No API keys.
AI-security knowledge as MCP: standards-mapped tools (OWASP, NIST, MITRE) for AI agents.
Real-time CVE, exploit, and vulnerability intelligence for AI assistants (350K+ CVEs, 115K+ PoCs)
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceAn MCP server that exposes a 60+ tool security and threat-intel stack to AI agents, enabling secret scanning, Sigma rule generation, ransomware lookup, OSINT, and deep research.1MIT
- AlicenseAqualityCmaintenanceUnifies 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.411,150 npm32MIT
- AlicenseAqualityCmaintenanceDark web & threat intelligence for AI agents. HIBP, ThreatFox, ransomware tracking, Tor .onion access, blockchain intel, exploit search, stealer logs, malware analysis — unified into a single MCP server.66305 npm530MIT
- AlicenseNot gradedqualityDmaintenanceMCP 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.MIT