# agent-sec

> agent-sec, an MCP server by kernora.ai, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.

- Canonical: https://www.anchorterminal.com/tools/kernora-agent-sec
- Markdown: https://www.anchorterminal.com/tools/kernora-agent-sec.md (~650 tokens)
- Slim: https://www.anchorterminal.com/tools/kernora-agent-sec.min.md (~580 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/kernora-agent-sec.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

# agent-sec

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by kernora.ai (https://agentsec.kernora.ai)
- Listed because: It's published in the registry under kernora.ai, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.

## Facts

- MCP registry: `ai.kernora/agent-sec` 0.1.0
- Endpoint: https://agentsec.kernora.ai/mcp (streamable HTTP)
- Source: https://github.com/kernora-ai/agent-sec
- Website: https://agentsec.kernora.ai
- GitHub stars: 1
- Registry entry updated: 2026-07-31

## Tools

- Tools it lists (2, about 252 tokens of context, `tools/list` without credentials, checked 2026-10-04 22:20 UTC):
  - `get_security_baseline`: Return Kernora Agent Security's curated security baseline — the known-good rules an AI coding agent should follow (secrets, injection, supply-chain,…
  - `check_action`: Advisory check: given a described action or command the agent is about to take, return the baseline security factlets that plausibly apply, so the agent can…
- How its tools read to an agent (0 errors, 2 warnings, 1 note, about 252 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC16 check_action: no readOnlyHint or destructiveHint
  - warn TC16 get_security_baseline: no readOnlyHint or destructiveHint
  - note TC24 server: 2 of 2 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/kernora-agent-sec.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming