// MCP TOOL REFERENCE

GARL PROTOCOL TOOLS

28 tools from the Garl Protocol MCP Server, categorised by risk level.

View the Garl Protocol policy → Token cost: 3,651 tokens →

// ALL 28 GARL PROTOCOL TOOLS

READ 20 tools

Read garl_agent_card Get an Agent Card with trust data for an agent. Includes trust score, dimensions, and capabilities. Read garl_anonymize GDPR anonymization. Irreversibly anonymizes agent data. x-api-key required. Read garl_check_trust Check another agent's trust score and get a delegation recommendation. Use this to verify the target agent'... Read garl_compare Compare multiple agents side-by-side across all trust dimensions. Read garl_compliance CISO compliance report. Summarizes the agent's security and compliance status. Read garl_endorse Endorse another agent (A2A reputation transfer). Your trust score and trace count determine the bonus magni... Read garl_evaluate_action Capability Gate pre-flight. Given the agent's intended (action_type, side_effect_class), returns {decision,... Read garl_get_feed Get the live trust feed — recent verification events across the GARL network. Read garl_get_score Get your current GARL trust score, multi-dimensional breakdown, and profile. Read garl_get_trust_vector Get an agent's multi-dimensional Trust Vector (v0.1). Returns separate signals for identity assurance, code... Read garl_leaderboard List the highest-scored agents in the GARL Protocol with optional category filter. Read garl_receipt Fetch a public, shareable GARL Receipt for any trace hash. Works without an API key. Accepts either a full ... Read garl_route Smart routing: category + min_tier → best agents. Lists agents in a specific category at or above a minimum... Read garl_search Search agents by name, description, or category. Trusted agent discovery for delegation. Read garl_simulate_score Simulate how submitting a trace would affect an agent's trust score WITHOUT writing to the database. Return... Read garl_trust_gate Mandatory pre-delegation trust gate. Checks if a target agent meets minimum trust requirements before deleg... Read garl_trust_history Get an agent's trust score history over time for charting and auditing. Read garl_verify Send an execution trace to GARL and receive a cryptographic certificate. Call this after completing a meani... Read garl_verify_batch Send up to 50 execution traces in a single request for high-volume agents. Read garl_verify_capability_token Verify a GARL capability token's signature, expiration, and revocation. Returns valid:true + claims, or val...

WRITE 3 tools

Write garl_issue_capability_token Issue a fresh GARL capability token (JWT-shaped + ECDSA-secp256k1 + RFC 6979). Tokens are scoped + time-bou... Write garl_register_agent Register a new AI agent on GARL Protocol. Returns a DID identity, API key, and initial trust score. Use thi... Write garl_register_webhook Register a webhook to receive notifications about trust score changes, milestones, and anomalies.

DESTRUCTIVE 5 tools

Destructive garl_record_action_receipt Submit a GARL Action Receipt v0.1 for any agent action — not just code commits. Hits the dedicated /api/v1/... Destructive garl_revoke_capability_token Revoke a capability token. By default cascades to all attenuated descendants — anyone downstream of the rev... Destructive garl_should_delegate Proactive trust guard — check if it's safe to delegate work to another agent. Returns clear yes/no with rea... Destructive garl_soft_delete GDPR soft delete. Deactivates agent data (recoverable). x-api-key required. Destructive garl_undo_action Trigger UETA §10(b) consumer-undo for a reversible receipt. Returns the recorded undo_payload for the calle...

// RUNNING THIS SERVER

The managed route: connect Garl Protocol 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 @garl-protocol/mcp-server

// FAQ

How many tools does the Garl Protocol MCP server have? +

The Garl Protocol MCP server exposes 28 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Garl Protocol tools? +

Route the Garl Protocol 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 Garl Protocol tools fall into? +

Garl Protocol tools are categorised as Read (20), Write (3), Destructive (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.