RU
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Nothing to run from here
DSH Any Agent 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
811
downloads a day
local
runs on your machine
5k
downloads in 30d
What it does
Drive DeepSeek Harness (DSH) as a long-lived, resumable coding agent from any MCP client.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user dsh-any-agent-mcp '--' npx -y dsh-any-agent
# 2 — ask your agent for something these tools do
# dsh_start, dsh_send, dsh_list and 12 more
DSH Any Agent costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
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 Any Agent 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-any-agent-mcp '--' npx -y dsh-any-agentReconnect, 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 asks of you
Nothing is required, but it can take DSH_BIN (Path to @deepseek-ai/dsh/lib/bin.js. Leave unset to auto-detect the DeepSeek Harness desktop app, an npm global install, or the npx cache.), DSH_MCP_PERMISSION (Default permission tier for dsh_start: read-only, workspace-write, or danger-full-access (the last one also needs DSH_MCP_ALLOW_FULL_ACCESS=1).), DSH_MCP_APPROVAL (What happens when DSH asks to go beyond its sandbox: auto-allow, auto-deny, or ask (the caller decides with dsh_approval_decide). read-only sessions always use auto-deny.), DSH_MCP_LANG (Language of the tool descriptions and server instructions: en or zh. Unset follows the system locale.) if you want to set them.
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
15 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.
新建一个 DSH 会话（一个可长期共事的编码 agent）。会话活在磁盘上，进程只是缓存；进程被回收或崩溃后会自动用 ACP session/resume 复活，对话不丢。返回 conversation_id 与对话标题。建好后用 dsh_send 派活。
No parameter schema on file.
向会话派一个任务。给目标，不要给命令：DSH 自己决定用哪些文件/shell/搜索/技能/子代理/团队工具，本服务不预先加载或代理 DSH 的工具面。默认不阻塞（wait=false）：立即返回 run_id + sentinel_file，回合在后台跑，跑完自动通知你 —— 你继续做别的事，也永远不用担心任务被"超时"打断。想原地等结果就显式传 wait=true（可配 timeout_ms；到期只会转后台，不会取消回合）。【超时不会毁掉任务】wait=true 到达 timeout_ms 仍没跑完时，本工具不会报错、也不会取消回合，而是自动降级为后台：返回…
No parameter schema on file.
列出会话及其运行状态，用来掌控多个会话实例。state: running（正在跑回合）/ idle（进程活着但空闲）/ detached（进程没开，可 resume 复活）。running 的会话会带上已跑时长、当前正在执行的工具、本轮已产出字数。数据来自两路合并：本服务持有的 + DSH 磁盘上尚未打开的（DSH 的 session/list 会排除已打开的会话）。想只看正在跑的，传 only_running=true；想看某个会话当前吐出的内容，接着用 dsh_read。
No parameter schema on file.
读会话的运行期输出（游标式增量）——用它可以看到"正在跑的会话"当前吐出了什么，不必等回合结束。典型用法：dsh_list(only_running) 找到在跑的会话 → 反复 dsh_read 并回传上次的 cursor，就能像切换窗口一样轮流观察多个会话。输出缓冲只在内存里且有界（环形，满则丢最旧），服务/进程退出即消失；思考内容不进缓冲——只有 include_reasoning=true 时才会附带"当前正在跑那一轮"的实时思考。cursor 是修订号：同一条目被追加文本后会再次返回，调用方按 seq 用它替换全文（不要重复累加）。
No parameter schema on file.
查看单个会话的详情；带 run_id 时取那一次派活的最终结果（异步模式的验收入口）。不传 run_id 则取最近一次回合。返回：标题、工作区、权限档、状态、轮数、token 用量、上下文压力、待决审批，以及该回合的完整结果（正文/工具/用量/错误）和 review 审核单。run 记录只在内存、最多保留最近 20 条；服务重启或记录被挤掉后会从哨兵文件回读（它落盘且扛重启）。
No parameter schema on file.
提交对一次回合结果的调用方审核裁决。dsh_send / dsh_interject / 哨兵里的 result 会带 review 审核单（核验清单 + 证据摘要 + review_id）。在把结果当作完成之前，调用方应自己核验（读改动的文件、看 git diff、跑测试等），再调用本工具记录 pass / partial / fail。默认是建议式审核：不阻塞后续 dsh_send，也不会自动把审核意见回灌给 DSH；需要修就再 dsh_send。run 记录被内存挤出或服务重启后仍可提交（以哨兵文件为准）。
No parameter schema on file.
插话：会话正在跑某个回合时往里补一句话。两种模式——interject（默认）打断当前回合并立刻改口；queue 不打断，等本轮自然结束后紧接着说。会话空闲时按 wait=true 的普通回合执行（会阻塞到回合结束并返回完整结果，不是收据）。说明：ACP 明确拒绝并发 prompt，所以做不到"让模型在同一个回合里即时改向"；interject 是它的实用等价物（取消 + 立刻开新回合，历史完整保留）。
No parameter schema on file.
中断会话当前正在进行的回合（ACP 原生 session/cancel，走的就是用户手动按停止那条路径）。会话本身保持完好，可以立刻继续派新任务。
No parameter schema on file.
抢占会话的写锁（DSH 的写锁是跨进程内核信号量，持有者活着就不过期，没有 API 能直接夺走——唯一手段是杀掉持有者进程，所以本工具会先判定持有者是谁）：① 若锁其实空着，正常 resume 即可，不会杀任何东西；② 若持有者是本服务自己留下的孤儿进程（MCP 崩了/重启了，子进程还活着握着锁）→ 自动杀掉并接管，安全；③ 若持有者是另一个活着的 dsh-any-agent 实例 → 默认拒绝，传 force=true 才夺；④ 若持有者无法识别（多半是你自己的 DSH GUI 正开着这个会话）→…
No parameter schema on file.
释放会话占用的 DSH 进程（释放写锁，让用户能在自己的 DSH GUI 里打开同一个会话）。会话本体留在磁盘上，之后仍可 resume；forget=true 会写墓碑：从注册表移除，此后按 id 查询明确报“已被 forget”（想恢复可按错误里的路径删除墓碑文件，默认在 $DSH_HOME/.dsh-any-agent-forgotten/<id>.json）。★ 用完了想一次性腾内存就传 all=true（每个会话约 300-480MB；默认 MAX_LIVE=8 会回收最久未用者，all=true…
No parameter schema on file.
裁决一个待决审批（仅当会话的 on_approval=ask 时会出现）。用于把 DSH 的越权/提权请求交给调用方决定，既不一律放行也不一律拒绝。
No parameter schema on file.
轻量状态查询：会话是否活着、是否在忙、待决审批数、最近一次回合的结果。
No parameter schema on file.
跨会话的待决审批收件箱（dsh_status 只看单个会话）。一次列出所有会话里等你裁决的审批：会话 id/标题、审批 id、工具、原因、命令/路径摘要、等待时长。裁决用 dsh_approval_decide。没有待决审批时返回空列表。
No parameter schema on file.
查看/修改会话的待执行队列（由 dsh_send(queue=true) 产生；仅内存，重启丢失）。action=list 列出；remove 取消并写 cancelled 哨兵；update 改写排队文本；promote 提到队首。
No parameter schema on file.
只读体检：DSH 可执行文件与版本、profile 是否存在/漂移、状态文件、runs/locks 目录可写、孤儿锁、当前会话数与 RSS、生效配置。只报告不修改；ok=false 表示存在 fail 项。
No parameter schema on file.
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 Any Agent 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 0.6.9 · scanned 10 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
Findings8 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest976727589a997b58b2b5f495e3363beb45b133748f5c6b71a119848c0a514f57
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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
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.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can start a fixed program (a process-spawning capability, not arbitrary code execution)
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 digest976727589a997b58
Scanned2026-11-10
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 0.6.9. Pin a release below and the command asks for exactly that one.
0.6.9
10 Nov 2026
latestNo release note was published with this version.
0.6.8
10 Nov 2026
No release note was published with this version.
0.6.7
9 Nov 2026
No release note was published with this version.
0.6.5
9 Nov 2026
No release note was published with this version.
0.6.3
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 Any Agent 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.