gitlab-mcp (zereight/gitlab-mcp) is an MCP server listed on the M8ven Trust Index. It scores 83 out of 100, grade B. It declares 232 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
B
Caution
83/100
24 days ago

gitlab-mcp

First gitlab mcp for you, building together

→ zereight/gitlab-mcp· npm: @zereight/mcp-gitlab· listed on npm

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

zereight

Source: npm · also listed on modelscope, github_code

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

npmmodelscopeGitHub

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
🚨
Secret credentials may flow to a network call
4 flows detected: GITLAB_TOKEN. We can’t prove the destination matches the brand the credential belongs to.
🔐
You'll be asked for 5 credentials: DOWNLOAD_TOKEN_SECRET, GITLAB_OAUTH_CLIENT_SECRET, GITLAB_TOKEN, GH_TOKEN, GITHUB_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configComSpec
configDEFAULT_NULL
configDISCUSSION_ID
🔐 secretDOWNLOAD_TOKEN_SECRET
configDOWNLOAD_TOKEN_TTL
configGITLAB_ALLOWED_PROJECT_IDS
configGITLAB_API_URLapi-url - GitLab API URL (replaces )
configGITLAB_COMMIT_FILES_PER_PAGE
configGITLAB_GRAPHQL_URL
configGITLAB_OAUTH_CLIENT_IDLocal OAuth: GITLAB_USE_OAUTH=true, , GITLAB_OAUTH_REDIRECT_URI, GITLAB_API_URL
🔐 secretGITLAB_OAUTH_CLIENT_SECRET
configGITLAB_OAUTH_REDIRECT_URIis for local OAuth (GITLAB_USE_OAUTH) only. It does
configGITLAB_OAUTH_TOKEN_PATH
configGITLAB_OAUTH_TOKEN_SCRIPT
configGITLAB_OAUTH_TOKEN_SCRIPT_TIMEOUT_SECONDS
configGITLAB_PROJECT_ID
🔐 secretGITLAB_TOKEN
configISSUE_IID
configLOG_FORMAT
configLOG_LEVEL
configMAX_REQUESTS_PER_MINUTERemote multi-user HTTP: STREAMABLE_HTTP=true, REMOTE_AUTHORIZATION=true (or GITLAB_MCP_OAUTH=true), MCP_TRUST_PROXY=true (behind a reverse proxy), =300, MCP_SERVER_URL or MCP_ALLOWED_HOSTS, HOST, PORT
configMAX_SESSIONSCapacity limit: Server accepts up to concurrent sessions (default 1000)
configMCP_DANGEROUSLY_ALLOW_INSECURE_ISSUER_URLNo Set true for local HTTP dev only
configMCP_SERVER_NAMEMultiple side-by-side deployments: set a distinct per instance (e.g. gitlab-selfhosted-readonly) so clients, logs, and telemetry can tell them apart
configNOTE_ID
configOAUTH_REGISTER_RATE_LIMIT_PER_HOURDCR rate limiting: POST /register is limited to
configPROJECT_ID
configSESSION_TIMEOUT_SECONDSSession timeout: Auth tokens expire after (default 1 hour) of inactivity. After timeout, the client must send auth headers again. The transport session remains active.
configWORKSPACE_ROOT
configSTAR_HISTORY_REPO
configSTAR_HISTORY_OUT
🔐 secretGH_TOKEN
🔐 secretGITHUB_TOKEN
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

232/232 tools missing one or more hints — omg_read_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); omg_write_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); omg_delete_memory (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +229 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — omg_clear_state deletes at line 112 (fs.unlinkSync(statePath))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool inputs are validated

10/15 tool handlers declare input schemas (67%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool test coverage

146/232 tools referenced in tests (63%)

Write tests that reference each tool by name so every tool has at least one test.

Secrets not logged

4 secret values sent to console.log

Redact or omit secret values from log output.

Dependency freshness

1/19 production deps stale: node-fetch@2023-11-30 (2.7y)

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/zereight/gitlab-mcp?variant=verified)](https://m8ven.ai/mcp/zereight/gitlab-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: a09232f46c1e3c7d4c388f7540282a1d5d595d93
code hash: a7d0be5225906ea6bfd28a8322cecec1b1af66388d6d677107fa56bfde4ecc00
verified: 8/18/2026, 1:56:11 AM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client