MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Dsh Baton is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
94/100
trust score
109
downloads a day
local
runs on your machine
6k
downloads in 30d
What it does
Hand tasks from Claude Code, Codex or any MCP client to a local DeepSeek Harness.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user dsh-baton-mcp '--' npx -y dsh-baton-mcp
# 2 — ask your agent for something these tools do
# dsh_list_workspaces, dsh_create_workspace, dsh_list_sessions and 13 more
Dsh Baton costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JIAll 1 server
JialaoLiu1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Dsh Baton as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user dsh-baton-mcp '--' npx -y dsh-baton-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
16 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
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.
No parameter schema on file.
Register a folder as a Harness workspace without starting a session (dsh_send with cwd does this too). Creates the folder unless create_dir is false; an already registered folder returns its workspace. Returns id, path, title and created. Needs the dsh-baton-host plugin.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | yes | — | |
| title | no | — | |
| create_dir | boolean | no | Create the folder if missing |
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. Sessions not in dsh_list_sessions are archived or gone: do not look for them…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cwd | no | — | |
| query | no | — | |
| limit | no | — | |
| include_subagents | boolean | no | Also list sub-agent sessions |
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.
No parameter schema on file.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | yes | — | |
| last | no | — |
Send a message to a Harness session and return at once with a run_id; then wait for the reply with dsh_wait (or the wait_command it returns, where offered). session_id continues that session; without it a new session starts in cwd or workspace_id, or, with neither, in the folder this conversation…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| message | yes | — | |
| session_id | no | — | |
| cwd | no | — | |
| workspace_id | no | — | |
| mode | string | no | followup queues after the current turn; steer injects into a running turn. Omit to follow Harness's busy-send setting |
| model | no | — | |
| reasoning_effort | no | — | |
| checks | array | no | The project's own test commands, e.g. npm test (ask Harness in the message to write tests for each requirement). Do not write check scripts yourself. dsh-baton runs them in the folder when the run end |
Look once at a run without waiting: state (queued/running/waiting/completed/failed/cancelled/interrupted), recent events, final reply, waiting_on (sub-agents or jobs still working) and human_interjections. Never a way to wait: use dsh_wait.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | yes | — | |
| tail | no | — |
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | yes | — |
Answer the questions a waiting run asked (question in dsh_wait or dsh_status). Per question: option numbers or labels in choose, text for a free answer, or skip. Pass reason when the user let you decide. The answer reaches Harness once every question has one (submitted: true; remaining lists the…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | yes | — | |
| answers | array | yes | One entry per question answered now |
| reason | no | — |
Set the title of a Harness session; nothing else changes. Returns session_id and title.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | yes | — | |
| title | yes | — |
Set the sidebar title of a workspace, by workspace_id or path; the folder is not renamed. Returns id, path and title.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workspace_id | no | — | |
| path | no | — | |
| title | yes | — |
What a session is doing now: busy, activity (running turn, sub-agents, background jobs, reminders) and bridge_runs. Read-only. Check it before dsh_send to a busy session or before dsh_cancel.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | yes | — |
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_update_queued. Safe to repeat. Returns still_busy, activity and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | no | — | |
| session_id | no | — |
Change a dsh_send message still queued behind a running turn: edit replaces its text, remove deletes it, steer sends it into the running turn now. Only while its run is queued.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| run_id | yes | — | |
| action | string | yes | edit replaces the text, remove deletes the message, steer sends it into the running turn now |
| message | no | — |
List the runs sent with dsh_send, newest first (the last 100 are kept), to recover a run_id: run_id, session_id, state, times, message_preview, final_text and error. Read-only.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| session_id | no | — | |
| limit | no | — |
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 unknown name changes nothing and returns the tools with their input schemas.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | yes | — | |
| arguments | object | no | Arguments for that tool, as its input schema describes them (see the list returned for an unknown name) |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Dsh Baton or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 94 / 100
Release 0.6.5 · scanned 3 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score94
Findings6 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digestff2774fc7ada637ac20fa646abe3b64ee58af408584a0d19dd2305592bacb044
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (16 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
1 of the 16 recovered tools are registered only when !tool holds (src/mcp.mjs:378) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 15.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
15 tools are registered unconditionally · 1 more only when !tool holds (src/mcp.mjs:378) — typically when a key or option is configured. All 16 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| dsh_list_workspaces | no tags | |
| dsh_create_workspace | no tags | |
| dsh_list_sessions | no tags | |
| dsh_list_models | no tags | |
| dsh_read_session | no tags | |
| dsh_send | no tags | |
| dsh_status | no tags | |
| dsh_wait | no tags | |
| dsh_answer | no tags | |
| dsh_rename_session | no tags | |
| dsh_rename_workspace | no tags | |
| dsh_session_activity | no tags | |
| dsh_cancel | no tags | |
| dsh_update_queued | external-sink | external-sink: keyword "send_message" |
| dsh_list_runs | no tags | |
| dsh_call conditional | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestff2774fc7ada637a
Scanned2026-11-03
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.6.5. Pin a release below and the command asks for exactly that one.
0.6.5
3 Nov 2026
latestNo release note was published with this version.
0.6.4
31 Oct 2026
No release note was published with this version.
0.6.3
29 Oct 2026
No release note was published with this version.
0.6.2
28 Oct 2026
No release note was published with this version.
0.6.1
28 Oct 2026
No release note was published with this version.
0.6.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Dsh Baton can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.