dsh-baton-mcp
io.github.JialaoLiu/dsh-baton · version 0.6.5 · 2,243 weekly npm downloads · audited 2026-11-03
Notes
Findings
No hidden-instruction or invisible-character findings in any tool, prompt, or resource description.
Claude Connectors Directory readiness
- ✅ Every tool has a title 10 of 10 tools
- ✅ Every tool declares readOnlyHint or destructiveHint 10 of 10 tools
- ✅ Tool names are 64 characters or fewer All within limit
- ❌ Descriptions avoid instructions about model behavior or other tools 5 of 10 descriptions reference other tools or tell the model what it must do: dsh_list_workspaces, dsh_list_models, dsh_status, dsh_wait and 1 more
- ✅ No hidden instructions or invisible characters in tool metadata None found
Checks the directory's published tool requirements that are visible from tools/list. Passing them does not guarantee acceptance.
Supply chain
- Install scripts: none
- npm provenance: yes
- Source repository linked: yes
- License: MIT
- Direct dependencies: 0
Tools (10)
| Name | Title | Hint | Description |
|---|---|---|---|
dsh_list_workspaces | List workspaces | read-only | List the DeepSeek Harness workspaces (project folders): id, path, title and session_count. The id is the workspace_id for dsh_send. Read-only. Needs the dsh-baton-host plugin. |
dsh_list_sessions | List sessions | read-only | List Harness sessions, newest first, to find a session_id: session_id, title, cwd, updated_at, running, bridge_runs and model (what its next request uses). No paging: raise limit or narrow it with cwd or query. Read-only… |
dsh_list_models | List models | read-only | List the models this DeepSeek Harness can run (provider, model id, name, reasoning efforts) and its default model, to check a name before passing model to dsh_send. Read-only. Needs the dsh-baton-host plugin. |
dsh_read_session | Read session | read-only | Read the last messages of a session (role, time, text and the names of tools called; no tool output), to catch up before continuing it. Read-only. |
dsh_send | Send message | writes | Hand a task to DeepSeek Harness, or continue a session: returns at once with a run_id and a hint saying how to wait for the reply; follow it. Call it directly, no need to list anything first. A new session starts in the … |
dsh_status | Run status | read-only | Look once at a run or a session without waiting. A run (run_id): state (queued/running/waiting/completed/failed/cancelled/interrupted), recent events, final reply, waiting_on (sub-agents or jobs still working) and human_… |
dsh_wait | Wait for run | read-only | Wait for a run sent with dsh_send to end and return its state and final reply. Prefer the background wait_command from dsh_send if your client wakes you when a background command exits: it costs no turns. It also returns… |
dsh_answer | Answer question | writes | Answer the questions a waiting run asked (needs_input: answer in dsh_wait or dsh_status). If the user told you to decide such questions yourself, choose by your own judgment of the question and the task, call dsh_answer … |
dsh_cancel | Cancel session work | destructive | Stop everything a session is doing (turn, sub-agents, background jobs, reminders), by run_id or session_id; the session is kept. Messages queued in it are dropped too (removed_from_queue); to drop one queued message use … |
dsh_call | Call dsh-baton tool by name | destructive | Call a dsh-baton tool by name, for a tool this conversation does not list (dsh-baton was updated without a restart; the update note names it). Runs the same code as a direct call, so it can do whatever that tool does. An… |
Check your own setup
npx mcpvetter scan --liveBadge
Add this to a README:
[](https://mcpvetter.com/servers/dsh-baton-mcp)Publish this server?
Get the MCPVetter verified badge, a re-audit within 24 hours of every npm release, and an email whenever tools, findings, or Claude directory readiness change. $29 per server per month. You prove ownership first, free.