Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AVP_BASE_URL | No | AVP API URL | https://agentveil.dev |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_reputation | Check the reputation score of an AI agent by their DID. Args: did: Agent's decentralized identifier (e.g. did:key:z6Mk...) Returns: Reputation score (0-1), confidence, and interpretation. |
| get_agent_info | Get public information about an AI agent. Args: did: Agent's DID (did:key:z6Mk...) Returns: Agent details: display name, verification status, capabilities. |
| search_agents | Search for AI agents by capability, provider, or minimum reputation. Args: capability: Filter by capability (e.g. "code_review", "translation") provider: Filter by LLM provider (e.g. "anthropic", "openai") min_reputation: Minimum reputation score (0.0-1.0) limit: Max results (1-100, default 10) Returns: List of matching agents with their capabilities and scores. |
| verify_audit_chain | Verify the integrity of AVP's immutable audit chain. Returns: Whether the chain is valid, number of entries, and latest hash. |
| get_protocol_stats | Get current AVP protocol statistics. Returns: Total agents, attestations, verified agents, escrows, and cards. |
| get_attestations_received | Get all attestations (peer reviews) received by an agent. Args: did: Agent's DID Returns: List of attestations with outcome, weight, and context. |
| get_audit_trail | Get the audit trail for an agent — all recorded actions. Args: did: Agent's DID limit: Max entries (1-100, default 20) Returns: Chronological list of audit events (register, attest, transfer, etc.) |
| register_agent | Register a new AI agent on Agent Veil Protocol. Generates Ed25519 keys, creates a W3C DID, and registers on the network. Args: display_name: Human-readable name for the agent Returns: Agent DID and registration details. |
| submit_attestation | Submit a peer attestation (rating) for another agent after an interaction. Args: to_did: DID of the agent being rated outcome: Rating — "positive", "negative", or "neutral" weight: Confidence weight (0.0-1.0, higher = more confident) context: Interaction type (e.g. "code_review", "task_completion") Returns: Attestation details including cryptographic signature. |
| publish_agent_card | Publish or update your agent's capability card for discovery. Args: capabilities: Comma-separated list (e.g. "code_review,security_audit,testing") provider: LLM provider (e.g. "anthropic", "openai", "google") endpoint_url: URL where this agent can be reached Returns: Published card details. |
| get_my_agent_info | Get information about the currently configured AVP agent. Returns: Your agent's DID, registration status, and saved location. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| protocol_info | Information about Agent Veil Protocol. |