The directory of tools for agents

Agent Fin: finance MCP server with market data tools

Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.

Local mandate gate and proof trail for AI agents that take consequential actions.

Fail-closed quality gate and hash-chained receipt ledger for AI agent workflows.

Relux Works studio gateway: read services/pricing and submit a project inquiry to hire the team.

Sandboxed workspace MCP: file ops, argv-only run_command, list_files; BYO LLM prompts.

Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs

Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

Constitutional guardrails and loop detection for AI agents

Git-aware safe file ops for AI agents: delete anything except git-tracked source code.

Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.