AgentDock MCP Harness
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| repo.inspectA | Inspect a local Git repository without modifying its working tree. |
| task.createA | Create an ACTIVE coding task in a clean detached Git worktree based on source HEAD. |
| task.resumeB | Resume a durable Task by task_id and return restored process metadata. |
| task.finishA | Explicitly mark an ACTIVE Task COMPLETED after processes stop and the worktree is committed. |
| task.cancelA | Cancel an ACTIVE Task, best-effort stopping its running processes while preserving the worktree. |
| task.cleanupA | Remove the worktree of a COMPLETED or CANCELLED Task while preserving durable Task metadata. |
| file.readA | Read a UTF-8 file. Relative paths use the Task worktree; absolute paths use the host OS. |
| file.searchB | Search files using deterministic text matching and a glob. Relative paths use the Task worktree; absolute paths use the host OS. |
| file.patchB | Patch an existing file if its SHA-256 still matches. Relative paths use the Task worktree; absolute paths use the host OS. |
| file.writeB | Create or replace a UTF-8 file. Relative paths use the Task worktree; absolute paths use the host OS. |
| git.diffA | Return structured Task worktree changes and unified diff, including untracked files. |
| git.commitA | Stage all Task worktree changes and create a real local Git commit without push, merge, or deploy. |
| audit.getB | Return structured persisted Task audit entries after a sequence cursor. |
| approval.getB | Return a durable approval request by Task and approval_id. |
| approval.respondC | Resolve or escalate a durable approval request. |
| process.startC | Start an asynchronous Task process using explicit argv or shell mode. |
| process.statusC | Return current status and execution metadata for a Task process. |
| process.outputA | Read process stdout/stderr incrementally from a pull cursor. |
| process.cancelA | Best-effort cancel a running Task process and its Linux process group. |
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 19 tools
Each tool is scoped to a distinct resource and action. Though process.cancel and task.cancel overlap in stopping processes, their descriptions clearly differentiate targeting a single process versus an entire task, making misselection unlikely.
All tool names follow a consistent domain.action pattern using lower_snake_case (e.g., task.create, file.read, approval.respond). The verb is always an imperative or descriptive action, and the dot prefix reliably indicates the resource domain, making the naming highly predictable.
With 19 tools, the set is slightly above the typical 3-15 range, but the variety of concerns (processes, tasks, files, git, audit, approvals) justifies the count. Each tool addresses a distinct operation without obvious redundancy, so it feels reasonably scoped rather than bloated.
The tool surface covers task lifecycle, file operations, git commit/diff, process management, audit, and approvals. However, there is no task.list or task.get endpoint to enumerate or query tasks by state; agents must know task IDs in advance, which is a notable gap in the otherwise comprehensive workflow.