17 tools from the AgentBond MCP Server, categorised by risk level.
View the AgentBond policy →agentbond_evaluate_action Evaluate an action against an authorization token and consume budget if allowed. Returns an AuthorizationDecision with allowed/denied status, reaso... agentbond_evaluate_contract Evaluate whether a contract is valid for operations. Checks that the contract is active and all conditions (time_limit, budget_cap) are met. agentbond_evaluate_intent_policy Evaluate intent policy for an action. Checks if an IntentRecord exists when requireReasoning is true. Records the result in the audit log with inte... agentbond_get_audit_by_action Get audit records for a specific action ID. agentbond_get_audit_by_token Get audit records for a specific token ID. agentbond_get_audit_log Query the audit log with optional filters (layer, outcome, time range, limit). agentbond_get_contract Retrieve a contract by ID. agentbond_get_intent Retrieve an intent record by ID. agentbond_get_intent_by_action Retrieve an intent record by action ID. agentbond_get_token Retrieve an authorization token by ID. agentbond_reactivate_token Reactivate a suspended authorization token. Child tokens automatically become usable again. agentbond_record_intent Record an intent for an action — why the agent is performing this action. Evidence must be a summary (no raw logs). Required before action evaluati... agentbond_transition_contract Transition a contract's status. Only the principal can transition. Valid transitions: draft→active, active→completed, active→disputed, disputed→act... agentbond_create_contract Create a new inter-agent contract in draft status. Requires exactly 2 parties (one principal, one executor). Conditions can include budget_cap, tim... 2/5 agentbond_issue_token Issue a new authorization token. If parentTokenId is provided, delegation constraints are validated (child scope/budget/expiry must not exceed pare... 2/5 agentbond_suspend_token Temporarily suspend an authorization token. Can be reactivated later. Child tokens are denied while parent is suspended. 2/5 The AgentBond MCP server exposes 17 tools across 3 categories: Read, Write, Destructive.
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 AgentBond server.
AgentBond tools are categorised as Read (13), Write (3), Destructive (1). Each category has a recommended default policy.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept