Tools for a more open agent web.

The directory of tools for agents

83,073 tools · Reset filters
EXTERNAL

agent-fin

Agent Fin: finance MCP server with market data tools

MCP

Listing info 65/100

Price not supplied by publisherIndexed
EXTERNAL

agent-firewall-mcp

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

MCP

Listing info 75/100

Price not supplied by publisherIndexed
EXTERNAL

agent-gate

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

MCP

Listing info 65/100

Price not supplied by publisherIndexed
EXTERNAL

agent-gate

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

MCP

Listing info 65/100

Price not supplied by publisherIndexed
EXTERNAL

agent-gateway

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

MCP

Listing info 65/100

Price not supplied by publisherIndexed
EXTERNAL

agent-godmode

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

MCP

Listing info 65/100

Price not supplied by publisherIndexed
EXTERNAL

agent-graph-auditor

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

MCP

Listing info 75/100

Price not supplied by publisherIndexed
EXTERNAL

agent-guard

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

MCP

Listing info 75/100

Price not supplied by publisherIndexed
EXTERNAL

agent-guard

Constitutional guardrails and loop detection for AI agents

MCP

Listing info 65/100

Price not supplied by publisherIndexed
EXTERNAL

agent-guard-mcp

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

MCP

Listing info 75/100

Price not supplied by publisherIndexed
EXTERNAL

agent-guard-mcp

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

MCP

Listing info 65/100

Price not supplied by publisherIndexed
EXTERNAL

agent-guardrail

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

MCP

Listing info 75/100

Price not supplied by publisherIndexed

Indexed listings, not certifications. Prices and protocols are publisher declarations. How the index works