Organizations
OpenSSF — SAFE-MCP / AI-ML Security WG
Security layer that memory systems get attacked through.
Organization
★ 367 on GitHub · last commit Sep 3, 2026
What it is
Security layer that memory systems get attacked through.
At a glance
- Business model
- Organization
- License
- NOASSERTION
- Governing body
- OpenSSF (Linux Foundation)
- Owns
- SAFE-MCP threat taxonomy (14 tactics, ~80-85 techniques; SAFE-T1001 Tool Poisoning, SAFE-T1102 Prompt Injection)
- How to track it
- biweekly Mondays 1pm PT; openssf-sig-safe-mcp@lists.openssf.org; #sig-safe-mcp Slack
GitHub activity
This product has a public repository, so we read it nightly from the GitHub API. Stars measure developer attention, not quality or market share.
“SAF-MCP is a comprehensive security framework for documenting and mitigating threats in the AI Agent ecosystem.” (repository description)
- Stars
- 367
- Forks
- 96
- Open issues
- 52
- Last commit
- Sep 3, 2026 (68 days ago)
- License (GitHub)
- NOASSERTION
Links and sources
- Official sitesecureagenticframework.org
- GitHub repositorygithub.com/SAFE-MCP/safe-mcp