agent-fin
Agent Fin: finance MCP server with market data tools
Listing info 65/100
Agent Fin: finance MCP server with market data tools
Listing info 65/100
Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
Listing info 75/100
Local mandate gate and proof trail for AI agents that take consequential actions.
Listing info 65/100
Fail-closed quality gate and hash-chained receipt ledger for AI agent workflows.
Listing info 65/100
Relux Works studio gateway: read services/pricing and submit a project inquiry to hire the team.
Listing info 65/100
Sandboxed workspace MCP: file ops, argv-only run_command, list_files; BYO LLM prompts.
Listing info 65/100
Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs
Listing info 75/100
Safety checks an agent runs before it acts: package malware, destructive command, secret leak.
Listing info 75/100
Constitutional guardrails and loop detection for AI agents
Listing info 65/100
Git-aware safe file ops for AI agents: delete anything except git-tracked source code.
Listing info 75/100
Verify-before-act safety checks for AI agents: packages, lockfiles, manifests, CI workflows.
Listing info 65/100
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
Listing info 75/100
Indexed listings, not certifications. Prices and protocols are publisher declarations. How the index works