AgentAnycast MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTANYCAST_HOME | No | Data directory for daemon state. Default: ~/.agentanycast | |
| AGENTANYCAST_RELAY | No | Relay server multiaddr for cross-network P2P. Default: None (LAN only) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| 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 |
|---|---|
| get_node_infoA | Get this node's PeerID, DID, and connection status on the P2P network. |
| list_connected_peersA | List all peers currently connected to this node over the P2P network. |
| discover_agentsA | Find AI agents on the P2P network that offer a specific skill. Use this to search for agents before sending them tasks. For example, discover_agents("translate") finds agents that can translate text. Args: skill: The skill to search for (e.g. "translate", "summarize", "code-review"). |
| send_taskA | Send an encrypted task to a remote AI agent and wait for the result. The target determines how the agent is reached:
Args: target: PeerID, skill name, or HTTP URL of the target agent. message: The message or instruction to send to the agent. timeout: Maximum seconds to wait for a response (default: 30). |
| get_task_statusA | Get the current status and result of a previously sent task. Args: task_id: The task ID returned by send_task. |
| get_agent_cardA | Get the capability card (A2A Agent Card) for a peer or this node. Returns the agent's name, description, skills, PeerID, and DID. Args: peer_id: PeerID of the agent to query. Leave empty or "self" to get this node's card. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: searching for agents, retrieving agent details, getting node info, checking task status, listing peers, and sending tasks. No overlapping functionality.
All tool names follow a consistent verb_noun pattern in snake_case, such as 'discover_agents', 'get_agent_card', and 'send_task', making the API easy to predict.
6 tools cover the core workflows of agent discovery, peer interaction, and task management without being excessive or insufficient for the server's scope.
The set covers discovery, sending tasks, status tracking, and node/peer info. Missing a tool to list or cancel tasks is a minor gap but does not severely hinder agent workflows.