Skills/npm/renovate-mcp

renovate-mcp@2.2.0

VERIFIED· startup only

Publisher claims: "MCP server for designing Renovate configurations interactively." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher tibuntu · publishing for 212 daysInstalls 3,230Last detonated 16 min ago
$claude mcp add renovate-mcp -- npx -y renovate-mcp
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
BITBUCKET_TOKENFORCE_CONFIRMATION_TOKENFORGEJO_TOKENGITEA_TOKENGITHUB_COM_TOKENGITHUB_TOKENGITLAB_TOKENHOST_TOKENS_ENVRENOVATE_TOKENConfiguration, not credentials: RENOVATE_ADDITIONAL_CONFIG_FILE, RENOVATE_CONFIG_FILE, RENOVATE_ENDPOINT, RENOVATE_MCP_MERGE_WORKER_ENTRY, RENOVATE_MCP_MIGRATION_WORKER_ENTRY, RENOVATE_MCP_PACKAGE_RULES_WORKER_ENTRY, RENOVATE_MCP_PRESET_FLATTEN_WORKER_ENTRY, RENOVATE_MCP_REQUIRE_CLI, RENOVATE_MCP_SCHEDULE_WORKER_ENTRY, RENOVATE_MCP_VALIDATOR_TIMEOUT_MS, RENOVATE_PLATFORM
Where it talks to
renovatebot.com (its own)Also atlassian.com, helm.sh, mend.io, osv.dev, gitea.com, forgejo.org — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names atlassian.com, helm.sh, mend.io, osv.dev, gitea.com, forgejo.org as well as its own vendor. The guard injects BITBUCKET_TOKEN, FORCE_CONFIRMATION_TOKEN, FORGEJO_TOKEN, GITEA_TOKEN, GITHUB_COM_TOKEN, GITHUB_TOKEN, GITLAB_TOKEN, HOST_TOKENS_ENV, RENOVATE_TOKEN only into requests to renovatebot.com (and its subdomains) and refuses the rest.

$vet-skills run --secrets BITBUCKET_TOKEN=renovatebot.com,FORCE_CONFIRMATION_TOKEN=renovatebot.com,FORGEJO_TOKEN=renovatebot.com,GITEA_TOKEN=renovatebot.com,GITHUB_COM_TOKEN=renovatebot.com,GITHUB_TOKEN=renovatebot.com,GITLAB_TOKEN=renovatebot.com,HOST_TOKENS_ENV=renovatebot.com,RENOVATE_TOKEN=renovatebot.com -- npx -y renovate-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 1.7.2

vet-skills diff renovate-mcp 1.7.2 2.2.0

This version reaches for something 1.7.2 did not: 1 new credential variable (HOST_TOKENS_ENV). Compared from the two recorded runs, not from source.

New credential variables
HOST_TOKENS_ENV

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 84/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 62 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
40sprocessdependency install exit 0
60sclaimedstartup only: exited (0) before answering · code: 'ERR_MODULE_NOT_FOUND', url: 'file:///tmp/ks-detonate-viYyr1/task/home/work/acme-api/.claude/skills/renovate-mcp/dist/data/presets.generated.js' } Node.js v22.23.5
60sprocessscript backend runs setup only
60sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagedist/lib/version.js:4 · npx invocation of non-well-known package — may execute untrusted code// `npm i -g`, project-local `npm i`, or `npx renovate-mcp`). Anything else —Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Process kill commanddist/lib/renovateCli.js:115 · Process kill command — agent can terminate processes// `detached` makes the child a process-group leader so a timeout can killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detecteddist/lib/configLocations.js:7 · Destructive file system command detected// is handled separately below. `.jsonc` reports format "json": that formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiondist/tools/dryRun.js:146 · File type combined with upload action — agent may exfiltrate local data files…writes the draft there over the config file Renovate would read (a new `renovate.json` when there is none; under `package.json#renovate` the other keys are kept), runs Renovate in the copy and removes it; `repoPath` is never written. Local…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandpackage.json:32 · File permission modification command — agent changes file ownership/permissions…#!')) { console.error('dist/index.js missing shebang'); process.exit(1); }\" && chmod +x dist/index.js" }, "keywords": [ "mcp", "model-context-protocol", …Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commanddist/tools/writeConfig.js:144 · File permission modification command — agent changes file ownership/permissions// A concurrent chmod between this stat and the rename is lost; benign.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actiondist/tools/dryRun.js:106 · File type combined with upload action — agent may exfiltrate local data files…und to its host.** Set tokens on the MCP server's env via `claude_desktop_config.json` / `.mcp.json`, with the same host scoping `resolve_config` uses: `GITHUB_TOKEN` / `GITLAB_TOKEN` (and the Gitea / Forgejo / Bitbucket ones) only for the…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈52 tok
1 file · 74 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.