// MCP TOOL REFERENCE

AGENT OUTPUT GUARD TOOLS

5 tools from the Agent Output Guard MCP Server, categorised by risk level.

View the Agent Output Guard policy → Token cost: 833 tokens →

// ALL 5 AGENT OUTPUT GUARD TOOLS

READ 5 tools

Read cross_reference_check Compare data from multiple agents for consistency and detect discrepancies. Essential for multi-agent coord... Read detect_hallucination_markers Scan agent output for common hallucination patterns, uncertainty markers, and fabrication indicators. Criti... Read output_consistency_score Calculate overall consistency score for agent output including internal logic, format consistency, and reli... Read validate_data_freshness Check if data from another agent is recent and valid based on timestamps, staleness indicators, and expecte... Read verify_json_schema Validate JSON data from another agent against expected schema. Essential for preventing malformed data prop...

// RUNNING THIS SERVER

The managed route: connect Agent Output Guard through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @agenson-horrowitz/agent-output-guard-mcp

// FAQ

How many tools does the Agent Output Guard MCP server have? +

The Agent Output Guard MCP server exposes 5 tools across 1 categories: Read.

How do I enforce policies on Agent Output Guard tools? +

Route the Agent Output Guard server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Agent Output Guard tools fall into? +

Agent Output Guard tools are categorised as Read (5). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.