MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
Shipfast 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.
96/100
trust score
10
tools declared
local
runs on your machine
—
downloads a day
What it does
The process follows a waveform between PO and AI: documentation framework, skills, scaffold, and a three-way merge upgrade.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user shipfast-mcp '--' uvx shipfast-mcp
# 2 — ask your agent for something these tools do
# scaffold_project, upgrade, status and 7 more
Shipfast costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
QUAll 2 servers
quoctang2 servers
2 categories
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 Shipfast 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 uv (docs.astral.sh/uv): uvx 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 shipfast-mcp '--' uvx shipfast-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
10 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.
Scaffold quy trình shipfast vào dự án: CLAUDE.md, docs/ (wave, backlog, decision log, tổ chức), skill trong .claude/skills/.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | yes | — | |
| name | string | yes | Slug dự án: chữ thường không dấu, số, gạch ngang |
| display_name | string | yes | Tên hiển thị của dự án |
| description | string | no | Mô tả sản phẩm một hai câu; để trống nếu chưa chốt |
| branch | string | no | Nhánh chính của repo |
| code_lang | string | no | Ngôn ngữ comment và commit message |
| mode | string | no | init: repo mới, kèm hồ sơ W01. adopt: dự án đang chạy |
| dry_run | boolean | no | true: chỉ báo sẽ tạo gì, không ghi file |
Nâng khung quy trình của dự án lên phiên bản shipfast đang chạy, không cần repo gốc.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | yes | — | |
| dry_run | boolean | no | true: chỉ báo thay đổi, không ghi file |
Trạng thái quy trình: phiên bản khung, bảng wave, wave đang mở và vấn đề chờ PO, backlog, quyết định giả định.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | yes | — |
Cấp mã kế tiếp (BL-012, W03-04, CR-W03-02, KT-005…) bằng cách quét hồ sơ, tránh trùng số.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | yes | — | |
| kind | string | yes | Loại mã. ISSUE, P, CR, Q, CL, QA là mã trong wave, cần wave |
| wave | string | no | Mã wave, ví dụ W03; chỉ cần cho mã trong wave |
Mở wave mới: tạo docs/04_waves/Wxx/ từ mẫu của dự án, thêm dòng vào bảng wave ở trạng thái Intake.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | yes | — | |
| title | string | yes | Tên wave |
| goal | string | yes | Một câu: sau wave này người dùng hoặc PO có được gì |
| mode | string | no | po: PO chốt từng vấn đề. direct: chốt thẳng cho wave nhỏ. delegated: delegation, cần QT-nnn |
| lead | string | no | Chủ trì: Orchestrator hoặc mã bộ phận |
Ghi quyết định mới vào docs/05_decisions/ theo mẫu của dự án, cấp mã và cập nhật mục lục.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | yes | — | |
| kind | string | yes | SP sản phẩm, KT kỹ thuật, QT quy trình |
| title | string | yes | Tên quyết định, tiếng Việt |
| short_name | string | yes | Tên ngắn tiếng Anh cho tên file, ví dụ cookie-session-auth |
| context | string | no | Bối cảnh |
| decision | string | no | Phát biểu quyết định, ngắn, kiểm được |
| status | string | no | Hiệu lực chỉ khi PO đã chốt |
| wave | string | no | Mã vấn đề nguồn, ví dụ W03-02 |
Lập bộ phận theo dự án: hồ sơ docs/departments/<mã>/, subagent .claude/agents/dept-<mã>.md, thêm vào ORGANIZATION.md.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | yes | — | |
| code | string | yes | Mã viết hoa, ví dụ PLATFORM, TRUST |
| name | string | yes | Tên bộ phận, ví dụ Nền tảng |
| domain | string | yes | Lĩnh vực phụ trách, một câu |
| owns | string | yes | Vùng thư mục sở hữu, ví dụ src/, tests/ |
| decision | string | no | Mã QT lập bộ phận nếu đã ghi |
| model | string | no | Model mặc định của subagent: inherit, sonnet, opus, haiku hoặc mã model; việc soạn tài liệu, rà soát, khảo sát nên dùng model nhẹ |
| effort | string | no | Mức suy nghĩ mặc định của subagent; để trống thì theo phiên gọi |
| discipline | string | no | Kỷ luật riêng của bộ phận, mỗi dòng một luật, ví dụ chạy test nào trước khi báo xong |
Làm mới file subagent bộ phận (.claude/agents/dept-*.md) theo mẫu hiện hành, giữ tên, mã, lĩnh vực, vùng sở hữu, model, effort, kỷ luật riêng.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | yes | — | |
| dry_run | boolean | no | true: chỉ báo file sẽ cập nhật, không ghi |
Kiểm hồ sơ: biến khung sót, link gãy, wave đóng thiếu rút kinh nghiệm hoặc còn vấn đề Chờ, bảng wave lệch, decision log lệch.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_dir | yes | — |
Đọc tài liệu hướng dẫn shipfast cho người: bắt đầu từ đâu, tổ chức, ý nghĩa, phát triển và nâng cấp.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | no | Tên bài; để trống để xem danh sách |
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 Shipfast 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 96 / 100
Release 0.2.3 · scanned 15 Oct 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 score96
Findings1 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest6fff34cedb5a9151544d7994cd465ad6327a15d4b2b89d7b5bfe7b942833f9a8
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| 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 (10 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>".
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| scaffold_project | state-write | state-write: declares readOnlyHint: false |
| upgrade | state-write | state-write: declares readOnlyHint: false |
| status | no tags | |
| next_code | no tags | |
| open_wave | state-write | state-write: declares readOnlyHint: false |
| new_decision | state-write | state-write: declares readOnlyHint: false |
| create_department | state-write | state-write: declares readOnlyHint: false |
| refresh_departments | state-write | state-write: declares readOnlyHint: false |
| check | no tags | |
| read_guide | 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 digest6fff34cedb5a9151
Scanned2026-10-15
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 0.2.3. Pin a release below and the command asks for exactly that one.
0.2.3
undated
latestNo release note was published with this version.
—
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 Shipfast 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.