// MCP TOOL REFERENCE

AGENTGUARD TOOLS

24 tools from the Agentguard MCP Server, categorised by risk level.

View the Agentguard policy → Token cost: 3,232 tokens →

// ALL 24 AGENTGUARD TOOLS

READ 19 tools

Read approval_list List approval requests. Filter by status (pending/approved/denied/all), agent_id, or tool_name. Shows summa... Read audit_log_query Query the persistent audit trail. Filter by agent, tool, decision, time range. Returns signed entries with ... Read cross_tool_anomaly_check Detect anomalous tool usage patterns across an agent recent history. Checks risky tool combinations (AML-th... Read decision_explain Get a human-readable explanation of why a tool call was allowed or denied. Pass request_id from a previous ... Read emergency_kill Emergency kill-switch. Immediately terminates agent session(s), revokes pending approvals, blocks rate limi... Read guard_metrics AgentGuard operational metrics. Returns decision stats, top agents/tools, risk distribution, daily activity... Read output_safety_scan Post-execution output scanner. Checks tool output for PII leaks (email, phone, SSN, IBAN), secret exposure,... Read payload_safety_check Comprehensive safety scan for injection attacks and dangerous patterns. Detects: prompt injection, jailbrea... Read payment_policy_check Validate a payment against policy rules before execution. Checks amount limits (>100k warns, >1M blocks), r... Read policy_preflight Pre-flight security check before any tool call. Evaluates all policies, computes risk score, checks rate li... Read rate_limit_check Check if an agent has exceeded rate limits. Returns per-window usage (minute/hour/day) with percentage used... Read replay_guard_check Detect replay attacks — identical requests sent multiple times in a time window. Uses SHA256 fingerprint of... Read scope_check Check if agent has required scope for a tool. Roles: admin, compliance_officer, trader, auditor, developer,... Read secret_exposure_check Deep scan any text/payload for secrets, credentials, and PII. Detects: API keys (OpenAI, GitHub, AWS), toke... Read session_validate Create/validate/invalidate agent sessions with role, scopes, TTL and call budget. Actions: create|validate|... Read spend_limit_check Check if a payment amount stays within agent spend limits. Default limits: 10,000/call, 50,000/hr, 200,000/... Read tenant_policy_check Multi-tenant governance. Tenants: default, fintech_eu (MiCA/DORA), defi_protocol, enterprise_read. Checks t... Read threat_intel_check Check entity against threat intelligence. Auto-detects ETH addresses, IPs, domains. Checks sanctions (Torna... Read tool_manifest_verify Supply-chain verification for MCP tools. Checks publisher identity against allowlist, scans tool descriptio...

WRITE 4 tools

Write approval_required Check if a tool call requires human approval before execution. Returns requires_approval=true/false with ma... Write approval_resolve Resolve a pending approval request. Approve or deny a tool call that was flagged for human review. Updates ... Write audit_log_write Write a tool call result to the persistent, signed audit log. Call this AFTER tool execution with the outco... Write policy_register View the central policy registry. Query tiers (T1-T4), tool classifications, escalation rules. Actions: sum...

DESTRUCTIVE 1 tools

Destructive tool_risk_score Compute 0-100 risk score for any tool + input combination. 0=minimal risk (read-only), 100=critical (paymen...

// FAQ

How many tools does the Agentguard MCP server have? +

The Agentguard MCP server exposes 24 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Agentguard tools? +

Route the Agentguard 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 Agentguard tools fall into? +

Agentguard tools are categorised as Read (19), Write (4), Destructive (1). 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.