dsh-mcp
by Moer2831
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DSH_BIN | No | Path to @deepseek-ai/dsh/lib/bin.js | auto-detected |
| DSH_MCP_LOG | No | silent / info / debug | silent |
| DSH_MCP_STATE | No | Conversation registry, survives restarts | <repo>/.state/conversations.json |
| DSH_MCP_PROFILE | No | DSH profile to drive | dsh-mcp |
| DSH_MCP_MAX_LIVE | No | How many conversation processes to keep alive at once (0 = unlimited). Going over the cap reaps the least recently used one (a running turn is never reaped) — bounded memory, locks kept where it matters. Use 4 when memory is tight, 0 on a big machine. To free everything at once: dsh_release(all=true) | 8 |
| DSH_MCP_RUNS_DIR | No | Root for async completion sentinels (<this>/<conversation_id>/<run_id>.json) | <state file dir>/runs |
| DSH_MCP_LOCKS_DIR | No | Holder registrations for the write lock. All instances must agree on this value, or they cannot see each other's registrations and will misread each other as an unidentifiable holder (a GUI) and refuse to preempt | <state file dir>/locks |
| DSH_MCP_LOG_STDERR | No | 1 forwards DSH's raw stderr | |
| DSH_MCP_PERMISSION | No | Default tier for dsh_start | danger-full-access |
| DSH_MCP_IDLE_TTL_MS | No | How long a conversation may sit idle before its DSH process is reaped. 0 means never reap (the default): the server keeps holding the write lock, so the GUI cannot take it — opening the conversation there is read-only and still works. Cost: one resident DSH process per conversation (measured ~120 MB). Set a millisecond value (e.g. 300000) to save memory and accept that the lock can be taken | 0 |
| DSH_MCP_LOCK_STALE_MS | No | How long without a heartbeat before a holder counts as lost (and becomes auto-preemptible by dsh_takeover) | 90000 |
| DSH_MCP_SENTINEL_TTL_MS | No | Startup pruning age for sentinels; 0 disables pruning | 604800000 |
| DSH_MCP_REASONING_EFFORT | No | Default reasoning effort | max |
| DSH_MCP_LIST_PROBE_TTL_MS | No | Cache lifetime for dsh_list's on-disk probe (the probe spawns a DSH process and takes ~1 s) | 10000 |
| DSH_MCP_PROMPT_TIMEOUT_MS | No | Wait bound for wait=true only; on expiry the turn merely moves to the background | 0 |
| DSH_MCP_REGISTER_WORKSPACE | No | project / all / 0 | project |
| DSH_MCP_APPROVAL_TIMEOUT_MS | No | How long a pending approval waits | 300000 |
| DSH_MCP_SENTINEL_INCLUDE_REASONING | No | 1 writes result.thinking into the sentinel (breaks the never-on-disk guarantee) |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues