subagent-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SUBAGENT_HOST | No | Host for HTTP transport only. | 127.0.0.1 |
| SUBAGENT_PORT | No | Port for HTTP transport only. | 8100 |
| SUBAGENT_RUNS_ROOT | No | Where per-run artefacts go. | ./runs |
| SUBAGENT_TMUX_SOCKET | No | Use a private tmux server. | |
| SUBAGENT_ALLOWED_ROOTS | No | Parent dirs a subagent cwd may live under. | ~/git,~/ATLAS-GROUP |
| SUBAGENT_CLI_ALLOWLIST | No | CLIs the server will invoke. | claude,opencode |
| SUBAGENT_RUNS_KEEP_MAX | No | Keep at most this many run dirs (0 disables). | 200 |
| SUBAGENT_MAX_CONCURRENT | No | Cap on live launched panes. | 12 |
| SUBAGENT_RUNS_MAX_AGE_DAYS | No | Delete run dirs older than this (0 disables). | 14 |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| launch_subagentA | Launch a coding-CLI subagent in a detached tmux window. |
| check_subagentA | Capture the last output from a running subagent. |
| list_subagentsA | List launched subagents and reconcile them with live tmux pane state. |
| send_to_subagentA | Send a follow-up message to a running subagent. |
| stop_subagentA | Interrupt or kill a running subagent. |
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: launch creates a subagent, check retrieves output, list enumerates subagents, send_to delivers messages, and stop terminates. No two tools overlap in function.
All tool names follow a consistent verb_noun pattern in snake_case, using common operational verbs (launch, check, list, send_to, stop). This creates a predictable and easy-to-navigate API.
With five tools, the set is well-scoped for subagent lifecycle management. Each tool covers a necessary operation without redundancy, making the count feel intentional and complete.
The set provides full lifecycle coverage for subagents: create (launch), read (check/list), update (send_to), and delete (stop). There are no obvious missing operations for the stated purpose.