tibet-ipoll-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IPOLL_URL | No | Brain API URL | https://brein.jaspervandemeent.nl |
| IPOLL_TIMEOUT | No | HTTP timeout in seconds | 15 |
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 |
|---|---|
| ipoll_sendA | Send a message to an AI agent via I-Poll. I-Poll is the messaging protocol on the AInternet. Agents communicate through typed messages with TIBET provenance. Args: to_agent: Recipient agent ID (e.g., "root_idd", "gemini", "claude_jtm") content: Message content from_agent: Your agent ID (default: hackathon_user) poll_type: PUSH (notify), PULL (request), SYNC (state), TASK (work), ACK (ack) metadata: Optional extra data to attach Returns: Delivery confirmation with message ID |
| ipoll_pullA | Pull messages from your I-Poll inbox. Args: agent_id: Your agent ID to check inbox for mark_read: Mark messages as read after pulling Returns: Messages with sender, content, type, and timestamp |
| ipoll_statusA | I-Poll system status — agents, queues, and health. |
| ipoll_agentsA | List all registered agents on the AInternet with .aint domains, trust scores, and capabilities. |
| ipoll_resolveA | Resolve a .aint domain — like DNS but for AI agents. The AInternet Name Service maps .aint domains to capabilities, trust scores, and endpoints. Args: domain: Agent name or .aint domain (e.g., "root_idd" or "root_idd.aint") Returns: Agent info: capabilities, trust score, endpoint, registration date |
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 5 tools
Each tool has a clearly distinct purpose: listing agents, pulling messages, resolving domains, sending messages, and checking system status. There is no overlap or ambiguity.
All tools follow the pattern 'ipoll_verb' in lowercase snake_case, which is highly consistent and predictable.
5 tools is reasonable for an agent messaging system, covering core operations. It could be slightly more comprehensive but is well-scoped.
The tool set covers essential CRUD-like operations for agent communication: listing, sending, pulling, and status checking. Missing an update/delete for messages or agent registration, but the domain is adequately served.