dsh
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DSH_HOME | No | DSH home directory; defaults to ~/.dsh. | ~/.dsh |
| DSH_MCP_DEBUG | No | Set to 1 to output SDK child process logs. | |
| DSH_MCP_MODEL | No | Model id; defaults to DSH settings. | |
| DEEPSEEK_API_KEY | No | DeepSeek API key; can be provided via environment variable or left in $DSH_HOME/.credentials.yaml for the bridge to read automatically. | |
| DSH_MCP_PROVIDER | No | Model provider; defaults to DSH settings. | |
| DSH_MCP_DSH_COMMAND | No | Path to the dsh executable; defaults to the desktop dsh.cmd or dsh on PATH. | |
| DSH_PERMISSION_MODE | No | DSH permission mode; defaults to workspace-write. | workspace-write |
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 |
|---|---|
| dsh_infoA | Report the DSH launcher, model route, API-key availability, live SDK runtimes, and tracked runs. Call this first when a DSH call fails. |
| dsh_startA | Queue one task for the DSH coding agent and return immediately with a sessionId. Omit sessionId to create a new session; pass a previous sessionId to continue that session. Follow with dsh_wait / dsh_get. |
| dsh_waitA | Wait up to 30 seconds for the current turn of a DSH session to finish. Returns status "running" with partial output when the budget elapses; call again with the same sessionId. |
| dsh_runA | Queue a task and wait for the turn to settle. Convenient for short tasks; long tasks should use dsh_start + dsh_wait so the MCP call does not block. Timeout leaves the turn running and returns timedOut:true. |
| dsh_getB | Read the current state and last assistant output of a DSH session without waiting. |
| dsh_sessionsA | List the runs this MCP bridge process has started, with their status and latest assistant text. |
| dsh_shutdownA | Stop every SDK runtime this bridge started. Active turns are abandoned (the SDK protocol has no per-turn cancel); the next dsh_start spawns a fresh runtime. |
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 7 tools
Each tool maps to a fairly distinct operation (start, run, wait, get, list, info, shutdown), and descriptions explicitly clarify edge cases like dsh_run vs dsh_start+dsh_wait and dsh_wait vs dsh_get. Minor overlap remains between dsh_run and dsh_start/dsh_wait, and between dsh_sessions and the run-tracking portion of dsh_info.
All tools share a consistent dsh_ snake_case prefix with terse, predictable suffixes. Slight deviation: most suffixes are verbs (wait, run, get, start, shutdown) but dsh_sessions and dsh_info are nouns, though still readable and logical.
Seven tools neatly cover the session lifecycle: start/continue, blocking run, poll, non-blocking get, list, diagnose, and shutdown. Every tool earns its place with no obvious redundancy or padding.
Create, continue, observe, list, and shutdown are all covered, so standard agent workflows are possible. The main gap is per-session or per-turn cancellation (explicitly unsupported by the SDK), meaning agents can only abandon all runtimes via dsh_shutdown.