AgentHub
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AGENTHUB_HOME | No | Set this to move the whole AgentHub directory (default is ~/.agenthub). |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_agentsB | Installed agents, their permission modes, supported features and quota health. |
| askB | Run a prompt on an agent and wait for the answer (minutes). Returns reply, session_id, usage. |
| start_taskA | Start long agent work in the background; returns task_id. Use isolation='worktree' for code changes. |
| wait_taskA | Wait until a task finishes (or timeout_seconds passes) and return its result. |
| get_taskB | Task status and, once finished, its final output, session_id and usage. |
| get_task_logsB | Last lines of a task's log (readable summary of commands, edits and messages). |
| list_tasksC | Recent background tasks, newest first. |
| cancel_taskB | Stop a running task and every process it started. |
| get_task_diffB | Changes a worktree-isolated task made (file list, stat and patch). |
| apply_taskB | Apply a worktree-isolated task's changes to the user's working tree (not committed). |
| discard_taskA | Throw away a worktree-isolated task's changes (cancels it if running). |
| reviewA | Ask an agent to review a diff (read-only): uncommitted changes vs base (default HEAD), or a task's worktree changes via task_id. |
| compareB | Send one prompt to 2-5 agents in parallel (read-only) and get their answers side by side. |
| list_sessionsC | An agent's recent conversation sessions. |
| search_sessionsC | Search an agent's past sessions by keyword. |
| get_transcriptC | Turns (messages, tool calls) of one past session. |
| list_modelsB | Model IDs an agent accepts for |
| send_messageC | Send a message into an agent's live interactive session. |
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 18 tools
Most tools have clearly distinct purposes: the task lifecycle set (start/wait/get/logs/list/cancel/diff/apply/discard) is well-partitioned by resource and action, and list/search/get_transcript for sessions are clearly differentiated. Minor overlap risk exists between ask, start_task, and send_message (all send prompts, differing mainly by sync/async/interactive mode), which descriptions largely resolve.
Nearly all names follow a consistent snake_case verb_noun pattern (list_agents, get_task_diff, cancel_task, search_sessions, send_message). A few single-verb names (ask, review, compare) deviate slightly from the pattern but remain readable and unambiguous.
18 tools is on the heavier side but justified: nine tools cover the full background-task lifecycle plus agent, session, and model operations. Each tool has a distinct role, so nothing appears redundant or padded.
Coverage is strong: agent discovery, full task lifecycle (create, monitor, diff, apply, discard, cancel), session browsing/search/transcript, and model listing. Minor gaps exist around agent lifecycle management (list_agents implies installation but there's no install/remove tool) and cross-agent model discovery.