10 actions in 7 pieces of software · ranked by words, meaning and measured trust · 558 ms
- 1AIM-Guard-MCPfound in code, not yet checkedno passport yet
- ai-safety-guard
AI Safety Guard - MCP Caution Instructions for AI Agents
- ai-safety-guard
- 2agent-guard-mcpfound in code, not yet checkedno passport yet
- check_circuit_breaker
Check if a proposed action should be allowed or blocked by the circuit breaker. Call this BEFORE executing a tool.
- register_agent
Register an agent for loop monitoring. Configure iteration limits and progress thresholds.
- detect_loop
Check if an agent is stuck in an infinite loop. Analyzes action patterns, uniqueness ratio, and repeated signatures.
- check_circuit_breaker
- 3agent-guard-mcpfound in code, not yet checkedno passport yet
MCP serverliminalpepe/agent-guard-mcp
- verify_lockfile
Scan an entire lockfile (direct + transitive deps) BEFORE npm/pip/yarn/pnpm install. Call when the user pastes or generates a lockfile, or before trusting an LLM-written package-lock.json / yarn.lock / pnpm-lock.yaml / poetry.lock / requirements.txt. Returns per-package OK | SUSPICIOUS | DANGER coun
- verify_lockfile
- 4mcp-security-guardfound in code, not yet checkedno passport yet
MCP serverpetrovicistefan/mcp-security-guard
- generate_policy
Returns a .mcp-security.json policy that approves exactly the MCP servers configured now (and their remote hosts) and requires pinned versions. Commit it to the repository so CI, session checks and audits flag any server added later that is not on the list (shadow MCP servers). Read-only: returns th
- export_bom
Inventory of everything the agent can run or read here: MCP servers, plugins, skills, commands, subagents, CLAUDE.md and hook configs, with SHA-256, pin status, scores and OWASP MCP Top 10 evidence. format=summary is a Markdown overview for audits; format=cyclonedx is a CycloneDX 1.6 JSON document.
- generate_policy
- 5MCP Injection Guardfound in code, not yet checkedno passport yet
- scan_injection
Scan untrusted text for prompt-injection patterns before passing it to an agent: instruction overrides, system-prompt
- scan_injection
- 6mcp-guardfound in code, not yet checkedno passport yet
MCP serverarunmm8335/mcp-guard
- name
description
- name
- 7aster-guardfound in code, not yet checkedno passport yet
- scan_mcp_config
Scan one MCP configuration file (e.g. .mcp.json) for security issues.
- scan_mcp_config
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.