Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
GitFerry 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
721
downloads a day
local
runs on your machine
3
tools declared
What it does
Pack, inspect, and apply portable Git change bundles across offline repositories.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user gitferry-mcp '--' npx -y gitferry mcp
# 2 — ask your agent for something these tools do
# pack_changes, inspect_bundle, apply_bundle
GitFerry 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 GitFerry 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 gitferry-mcp '--' npx -y gitferry 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
3 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.
Read a local Git repository and write a portable .gitferry bundle of commits, staged/unstaged changes, and untracked files. only=repo instead captures tracked files as a snapshot. Review untracked files for secrets before sharing. No network transfer is performed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cwd | string | yes | Absolute path to the git repository (or any directory inside it) |
| output | string | no | Output bundle path; defaults to <repo>-<branch>-<sha>.gitferry in cwd |
| only | string | no | Select all, uncommitted, staged, unstaged, committed, or repo (tracked-file snapshot). Default all. Include flags can further narrow the selection; repo is exclusive. |
| portable | boolean | no | Write a plain ZIP for git + unzip targets instead of the smaller Brotli-wrapped format (default false) |
| base | string | no | Ref/sha the bundle applies onto (default: merge-base with the upstream tracking branch) |
| includeCommits | boolean | no | Include unpushed commits (default true) |
| includeWorktree | boolean | no | Include staged AND unstaged changes; master switch over includeStaged/includeUnstaged (default true) |
| includeStaged | boolean | no | Include staged (index) changes (default true) |
| includeUnstaged | boolean | no | Include unstaged working-tree changes (default true) |
| includeUntracked | boolean | no | Include untracked files (default true) |
Read a local .gitferry bundle, verify checksums and manifest structure, and report its contents without modifying files. Checksums detect corruption; they do not authenticate the sender.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| bundlePath | string | yes | Absolute path to the .gitferry bundle file |
Validate and apply a trusted local .gitferry bundle: replay commits, restore staged/unstaged changes, and write untracked or snapshot files. Modifies the target unless dryRun=true. Preview first and review conflicts afterward. force bypasses repository, dirty-tree, and overwrite guards.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| cwd | string | yes | Absolute path to the target git repository |
| bundlePath | string | yes | Absolute path to the .gitferry bundle file |
| dryRun | boolean | no | Validate and report the plan without changing anything (default false) |
| force | boolean | no | Override repo-fingerprint, dirty-tree, and file-overwrite guards (default false) |
| includeUntracked | boolean | no | Write untracked files from the bundle (default true) |
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 GitFerry 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 0.4.2 · scanned 4 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 digeste4dccc8a5fd809b2eb7fbfa8177c5e7a3edeac4c899f955f636199437df83287
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 (3 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. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| pack_changes | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
| inspect_bundle | no tags | |
| apply_bundle | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
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 digeste4dccc8a5fd809b2
Scanned2026-11-04
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 0.4.2. Pin a release below and the command asks for exactly that one.
0.4.2
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 GitFerry 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.