Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
GitLab 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.
93/100
trust score
39
tools declared
local
runs on your machine
—
downloads a day
What it does
Developer-ready GitLab MCP server for CE and EE instances.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'GITLAB_PERSONAL_ACCESS_TOKEN=${GITLAB_PERSONAL_ACCESS_TOKEN}' --transport stdio sumirati-gitlab-mcp '--' npx -y @sumirati/mcp-gitlab
# 2 — ask your agent for something these tools do
# search_repositories, create_repository, get_file_contents and 36 more
It needs GITLAB_PERSONAL_ACCESS_TOKEN: this reads it from your environment, so export it first.
GitLab costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
SUAll 1 server
sumirati1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts GitLab as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads GITLAB_PERSONAL_ACCESS_TOKEN (GitLab Personal Access Token with api scope) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx GITLAB_PERSONAL_ACCESS_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'GITLAB_PERSONAL_ACCESS_TOKEN=${GITLAB_PERSONAL_ACCESS_TOKEN}' --transport stdio sumirati-gitlab-mcp '--' npx -y @sumirati/mcp-gitlabReconnect, 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
It reaches a system of yours, so it needs your own credential rather than the publisher’s: GITLAB_PERSONAL_ACCESS_TOKEN — GitLab Personal Access Token with api scope. You set it in your own client’s config, on your machine — this marketplace never holds it.
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
39 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.
Search for GitLab projects and repositories
No parameter schema on file.
Create a new GitLab project/repository
No parameter schema on file.
Read file or directory content from a project repository
No parameter schema on file.
Create or update a single file in a GitLab repository
No parameter schema on file.
Commit multiple files in a single atomic commit
No parameter schema on file.
Fork a project into a user or group namespace
No parameter schema on file.
Create a new branch from a commit, tag, or branch
No parameter schema on file.
List and filter issues by state, milestone, label, assignee, or search with clean summaries
No parameter schema on file.
Get comprehensive details for a specific issue by its IID (#<iid>)
No parameter schema on file.
Create a new issue with milestone (by title or ID), labels, assignees, and due date
No parameter schema on file.
Update issue title, description, state (close/reopen), milestone, labels, or assignees
No parameter schema on file.
List discussions, comments, and activity log on an issue
No parameter schema on file.
Post a comment or progress/verification note to an issue
No parameter schema on file.
List related, blocking, or blocked-by issue dependencies
No parameter schema on file.
Create an issue dependency link (relates_to, blocks, is_blocked_by)
No parameter schema on file.
List project milestones (active, closed, all) with start and due dates
No parameter schema on file.
Get details for a specific milestone by ID
No parameter schema on file.
Create a project milestone with due dates and roadmap scope
No parameter schema on file.
Update milestone dates, title, description, or state (close/activate)
No parameter schema on file.
List labels available in the project
No parameter schema on file.
Create a project label with color and description
No parameter schema on file.
List CI/CD pipelines filtered by branch, tag, status, or commit SHA
No parameter schema on file.
Get detailed status, duration, and commit info for a pipeline
No parameter schema on file.
Trigger a new CI/CD pipeline execution for a branch or tag
No parameter schema on file.
List all jobs (build, test, lint, deploy) and their status in a pipeline
No parameter schema on file.
Get the terminal output log of a build/test job (supports tailing to diagnose test failures)
No parameter schema on file.
Get JUnit test report summary (total, passed, failed test suites and error details)
No parameter schema on file.
List published project releases and version changelogs
No parameter schema on file.
Get release details by tag name
No parameter schema on file.
Publish a formal release with tag, description/changelog, and associated milestones
No parameter schema on file.
List git tags in the repository
No parameter schema on file.
Create a git tag pointing to a branch or commit
No parameter schema on file.
List merge requests filtered by state, branches, milestone, or labels
No parameter schema on file.
Get details and status of a merge request by IID (!<iid>)
No parameter schema on file.
Create a merge request between branches with description and options
No parameter schema on file.
Update MR title, description, state (close/reopen), target branch, milestone, or labels
No parameter schema on file.
Inspect code diffs and modified files in a merge request
No parameter schema on file.
Merge an approved merge request into the target branch
No parameter schema on file.
Post a review comment or note on a merge request
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 GitLab 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 93 / 100
Release 1.0.1 · scanned 14 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 score93
Findings0 threat · 1 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digestcf2712ef1c7c486691287ea008de4fd07c207afa4630e42835ec277fda7bb3f7
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| 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 (39 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 |
|---|---|---|
| search_repositories | no tags | |
| create_repository | no tags | |
| get_file_contents | sensitive-source | sensitive-source: keyword "read_file" |
| create_or_update_file | no tags | |
| push_files | no tags | |
| fork_repository | no tags | |
| create_branch | no tags | |
| list_issues | no tags | |
| get_issue | no tags | |
| create_issue | external-sink | external-sink: keyword "create_issue" |
| update_issue | no tags | |
| list_issue_notes | no tags | |
| create_issue_note | external-sink | external-sink: keyword "create_issue" |
| list_issue_links | no tags | |
| create_issue_link | external-sink | external-sink: keyword "create_issue" |
| list_milestones | no tags | |
| get_milestone | no tags | |
| create_milestone | no tags | |
| update_milestone | no tags | |
| list_labels | no tags | |
| create_label | no tags | |
| list_pipelines | no tags | |
| get_pipeline | no tags | |
| create_pipeline | no tags | |
| list_pipeline_jobs | no tags | |
| get_job_trace | no tags | |
| get_pipeline_test_report | no tags | |
| list_releases | no tags | |
| get_release | no tags | |
| create_release | no tags | |
| list_tags | no tags | |
| create_tag | no tags | |
| list_merge_requests | no tags | |
| get_merge_request | no tags | |
| create_merge_request | no tags | |
| update_merge_request | no tags | |
| get_merge_request_changes | no tags | |
| accept_merge_request | no tags | |
| create_merge_request_note | 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.
get_file_contents → create_issue
A sensitive-source → external-sink chain exists: get_file_contents → create_issue.
Supply chain and provenance
Integrityfirst-seen
Surface digestcf2712ef1c7c4866
Scanned2026-10-14
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 1.0.1. Pin a release below and the command asks for exactly that one.
1.0.1
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 GitLab 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.