// MCP TOOL REFERENCE

AGENTBOND TOOLS

17 tools from the AgentBond MCP Server, categorised by risk level.

View the AgentBond policy → Token cost: 1,941 tokens →

// ALL 17 AGENTBOND TOOLS

READ 13 tools

Read agentbond_evaluate_action Evaluate an action against an authorization token and consume budget if allowed. Returns an AuthorizationDe... Read agentbond_evaluate_contract Evaluate whether a contract is valid for operations. Checks that the contract is active and all conditions ... Read agentbond_evaluate_intent_policy Evaluate intent policy for an action. Checks if an IntentRecord exists when requireReasoning is true. Recor... Read agentbond_get_audit_by_action Get audit records for a specific action ID. Read agentbond_get_audit_by_token Get audit records for a specific token ID. Read agentbond_get_audit_log Query the audit log with optional filters (layer, outcome, time range, limit). Read agentbond_get_contract Retrieve a contract by ID. Read agentbond_get_intent Retrieve an intent record by ID. Read agentbond_get_intent_by_action Retrieve an intent record by action ID. Read agentbond_get_token Retrieve an authorization token by ID. Read agentbond_reactivate_token Reactivate a suspended authorization token. Child tokens automatically become usable again. Read agentbond_record_intent Record an intent for an action — why the agent is performing this action. Evidence must be a summary (no ra... Read agentbond_transition_contract Transition a contract's status. Only the principal can transition. Valid transitions: draft→active, active→...

WRITE 3 tools

Write agentbond_create_contract Create a new inter-agent contract in draft status. Requires exactly 2 parties (one principal, one executor)... Write agentbond_issue_token Issue a new authorization token. If parentTokenId is provided, delegation constraints are validated (child ... Write agentbond_suspend_token Temporarily suspend an authorization token. Can be reactivated later. Child tokens are denied while parent ...

DESTRUCTIVE 1 tools

Destructive agentbond_revoke_token Permanently revoke an authorization token. All child tokens will be denied via cascade evaluation (their st...

// FAQ

How many tools does the AgentBond MCP server have? +

The AgentBond MCP server exposes 17 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on AgentBond tools? +

Route the AgentBond 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 AgentBond tools fall into? +

AgentBond tools are categorised as Read (13), Write (3), 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.