5 tools from the Agent Output Guard MCP Server, categorised by risk level.
View the Agent Output Guard policy →cross_reference_check Compare data from multiple agents for consistency and detect discrepancies. Essential for multi-agent coordination. Returns consistency score and d... detect_hallucination_markers Scan agent output for common hallucination patterns, uncertainty markers, and fabrication indicators. Critical for multi-agent reliability. Returns... output_consistency_score Calculate overall consistency score for agent output including internal logic, format consistency, and reliability indicators. Returns comprehensiv... validate_data_freshness Check if data from another agent is recent and valid based on timestamps, staleness indicators, and expected update frequencies. Prevents acting on... verify_json_schema Validate JSON data from another agent against expected schema. Essential for preventing malformed data propagation in multi-agent workflows. Return... The Agent Output Guard MCP server exposes 5 tools across 1 categories: Read.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Agent Output Guard server.
Agent Output Guard tools are categorised as Read (5). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept