Agent Hub MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENT_HUB_DATA_DIR | No | Storage directory for Agent Hub MCP data | ~/.agent-hub |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| register_agentC | Register an agent with the hub |
| send_messageB | Send a message to another agent or broadcast to all agents |
| get_messagesC | Retrieve messages for an agent |
| get_hub_statusA | Get overview of hub activity, agents, and collaboration opportunities |
| create_featureC | Create a new feature for multi-agent collaboration |
| create_taskB | Create a task within a feature with agent delegations |
| create_subtaskC | Create implementation subtasks within a delegation |
| get_featuresC | Get list of features with optional filtering |
| get_featureB | Get complete feature data including tasks, delegations, and subtasks |
| accept_delegationC | Accept a delegation assigned to an agent |
| update_subtaskC | Update subtask status and provide output/context |
| syncA | Comprehensive sync with the hub - get messages, workload, and status in one call |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Active Agents | List of all active agents in the hub |
| Collaboration Opportunities | Current collaboration sessions and opportunities |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gilbarbara/agent-hub-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server