MCP Server for Z.AI - A Model Context Protocol server that provides AI capabilities
Nothing to run from here
mcpcut 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
38
downloads a day
local
runs on your machine
3k
downloads in 30d
What it does
mcpcut sits between your MCP client (Claude Code, Cursor, Claude Desktop) and the MCP servers you already use. In front of them it adds no tools of its own and passes theirs through; since 0.4.0 it can also give an agent folders through a built-in file server.
- Journal: every request and response goes to a local journal with secrets redacted.
mcpcut sessionsandmcpcut show <id>read it back. - Emergency brake: with a policy, a risky tool is held for your approval, denied, or confirmed by you right in the client session. An approval covers exactly that one call, while the agent waits.
- Folders: built-in file tools over the folders you declare, with rights per agent, private subfolders carved out, a trash instead of deletes and an audit of every file call.
- Proof: the journal is tamper-evident with an external anchor;
export --reportandverifycheck it offline. - Start:
npx -y mcpcut@0.4.1 adoptshows what would change,npx -y mcpcut@0.4.1 adopt --applyputs mcpcut in front of your servers. A copy of every file it touches is kept;adopt --undoputs them back. - Everything runs on your machine. Apache-2.0 · https://mcpcut.com
Quickstart
Run once first — the server needs this before it answers:
npx -y mcpcut@0.4.1 adopt# 1 — add it to Claude Code
claude mcp add --scope user rostislavmatov-mcpcut '--' npx -y mcpcut wrap --server '<server_name>' -- '<server_command>'
Put your own values in place of <server_name>, <server_command> before you run this.
mcpcut costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
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 mcpcut 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. Run once first: npx -y mcpcut@0.4.1 adopt. Put your own values in place of <server_name>, <server_command> before you run this. 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 rostislavmatov-mcpcut '--' npx -y mcpcut wrap --server '<server_name>' -- '<server_command>'Reconnect, 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
This listing has not published its tool surface here yet, so what a client will ask you to approve is whatever the manifest declares at install time.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
No tool surface on file
This listing has not published its tool list here yet. Nothing is shown here rather than another listing’s tools, which is what this page used to do.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 mcpcut 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 0.4.1 · 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 score94
Findings3 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest2039c9ed291c229c3f36c535231f8ecec05b32594f63efc9691160826b45da2d
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>".
dist/policy/approvals/queue-changes.js (5 KB) was not read: over the file-count budget.
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. | ||
reads sensitive or local data
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 digest2039c9ed291c229c
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 0.4.1. Pin a release below and the command asks for exactly that one.
0.4.1
10 Oct 2026
latest- If your agent dies while a call waits for you, the call now closes at once instead of up to a minute later; passwords with & or quotes are fully hidden in the journal; clearer messages in the first minute.
0.4.0
9 Oct 2026
- Give an agent folders instead of your whole disk: built-in file tools with per-agent rights, a trash and an audit. An approval now covers exactly the one call you see, while the agent waits. If you pinned mcpcut@0.3.1, change it to mcpcut@0.4.0.
0.3.1
6 Oct 2026
- Security fix: secret redaction can no longer hang on crafted input (URL credentials, PEM blocks, JWTs). If you pinned mcpcut@0.3.0, change it to mcpcut@0.3.1.
0.3.0
4 Oct 2026
No release note was published with this version.
0.2.4
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 mcpcut 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.