CanopiiCanopiiAll serversEnterprise →

google-drive-mcp MCP Server Security Report

piotr-agier/google-drive-mcp

A Model Context Protocol (MCP) server that provides secure integration with Google Drive, Docs, Sheets, Slides and Calendar. It allows Claude Desktop and other MCP clients to manage files in Google Drive through a standardized interface.

Security Trust Score
Grade F · Serious issues
Tier 1 · Public sourceHigh confidence · 98%latest vmaster@9509fb8 Repository
Declared MCP capabilities
ResourcesPrompts

Run it securely

This server scored F. Run it behind runtime policy enforcement so one bad tool call can't become an incident.

Are you the maintainer?

Verify with GitHub to get alerted whenever piotr-agier/google-drive-mcp changes score — and claim the badge for your README.

Claim this server
2 issues capping this score
  • highNo risky post-publish tool changes (rug-pull) — 1 risky tool-definition change(s) in version history (master@eca5a74 → master@f82461a)
  • mediumNo over-broad / destructive tools — 1 over-broad tool(s)

The short answer

Is google-drive-mcp safe to use?
google-drive-mcp scores 37/100 (grade F) on the Canopii Trust Index, and carries 2 confirmed security failures that cap its score: No risky post-publish tool changes (rug-pull) and No over-broad / destructive tools. It passes 12 of the 21 controls that apply to it.
What security issues does google-drive-mcp have?
google-drive-mcp fails 2 controls: No risky post-publish tool changes (rug-pull) and No over-broad / destructive tools. Each failure on this page carries the evidence behind it — the file and line, dependency, or CVE that decided it.
How reliable is the security score for google-drive-mcp?
We could evaluate 98% of the controls that apply to google-drive-mcp. Scores are deterministic — the same source always produces the same score — and a partially-scannable server cannot present a high one, because confidence caps the result. The scanner is open source, so this score can be reproduced independently.
How was google-drive-mcp scored?
Its published source was scanned against a fixed catalog of weighted security controls covering code safety, committed secrets, dependency vulnerabilities, tool-description integrity, authentication and transport, and maintenance. A confirmed flaw caps the score outright regardless of what else passes. The full rubric is published.
Reputation225stars115forks3open issues24d agolast commit1yage

Security controlslatest scored version vmaster@9509fb8

Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.

Model–MCP Runtime Guardrails

  • Fail
    Tool Definition Integrityguard1 risky tool-definition change(s) in version history (master@eca5a74 → master@f82461a)

    Every consecutive version pair is diffed for new injection markers or destructive scope — a risky diff anywhere in history is a rug-pull (fail, durable); benign description drift warns. How many servers fail this?

    updateGoogleDoc

    Fix: Never add hidden directives or destructive scope to an already-published tool; document description changes in release notes.

  • Fail
    User-in-the-Loop / Approval Scopeguard1 over-broad tool(s)

    No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval. How many servers fail this?

    updateGoogleDoc

    Fix: Scope tools narrowly; avoid arbitrary command execution and destructive defaults.

  • Warn
    Strict JSON Schema Enforcementschemas not strict

    Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.

    Fix: Set additionalProperties:false and require explicit parameters on every tool.

  • Pass
    Indirect Prompt Injection (IPI) Defensesguardno injection markers

    Tool/prompt/resource text is free of hidden instructions that could hijack the agent.

Application Security Checks

  • Warn
    No path traversalguard23 occurrences

    Naive path checks let tools read/write outside intended directories (EscapeRoute-class).

    src/auth/scopes.ts:54src/download-file.ts:94src/download-file.ts:164src/index.ts:431

    Fix: Resolve to a canonical path and verify containment; reject ../ and symlinks.

  • Warn
    No SSRF sinksguard3 occurrences

    Fetching tool-supplied URLs can pivot into internal networks and metadata services.

    scripts/registry-metadata.js:49src/tools/docs.ts:3405src/tools/drive.ts:2284

    Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.

  • Warn
    No known-vulnerable dependencies11 of 186 runtime deps vulnerable; worst critical

    Runtime dependencies (parsed from the lockfile) are scanned against OSV.dev for published CVEs. Advisory: flagged dependencies lower the score but don't hard-cap it, since transitive reachability is unproven.

    @hono/[email protected] — GHSA-92pp-h63x-v22m@hono/[email protected] — GHSA-frvp-7c67-39w9@modelcontextprotocol/[email protected] — GHSA-6qxp-vccf-f47h[email protected] — GHSA-v422-hmwv-36x6

    Fix: Upgrade the flagged dependencies past their fixed versions.

  • Warn
    Has a security policyno security policy

    A SECURITY.md gives a private path to report vulnerabilities.

    Fix: Add SECURITY.md with a disclosure contact and process.

  • Pass
    No command-injection sinksguardno sinks found

    Untrusted tool input reaching a shell yields remote code execution.

  • Pass
    No dynamic code executionguardno sinks found

    eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.

  • Pass
    No unsafe deserializationguardno sinks found

    pickle/yaml.load/etc. on untrusted data can execute code.

  • Pass
    No committed secretsguardno secrets found

    Hardcoded keys/tokens in published source are live credentials an attacker can use.

  • Pass
    Credentials sourced from environmentreads credentials from environment

    Reading secrets from env/secret stores avoids hardcoding them.

  • Pass
    Dependencies pinned (lockfile)lockfile present

    A lockfile makes installs reproducible and resistant to silent dependency swaps.

  • Pass
    Actively maintainedrecent commits

    Unmaintained servers don't receive security fixes.

  • Pass
    Repository not archivedguardactive

    Archived repositories will never be patched.

  • Pass
    Declares a licenseMIT

    A clear license is required for legal enterprise use.

  • Pass
    Adoption & popularityestablished adoption

    A small, capped nudge from stars/downloads — widely-used servers get more eyes on bugs. It can never offset a real security failure.

  • Not checked
    Signed releasesnot evaluated

    Signed releases let consumers verify artifacts weren't tampered with.

  • N/A
    No install/post-install scriptsguardno published package

    install hooks run arbitrary code on every consumer at install time.

  • N/A
    Package name not typosquattingguardno published package

    Names mimicking popular packages are a common malware delivery vector.

  • N/A
    Published with provenanceno published package

    Build provenance attests the artifact was built from the claimed source by CI.

  • N/A
    Established maintainerno published package

    Brand-new / single anonymous maintainers raise takeover and malware risk.

Transport & Trust Model

  • Warn
    Network Exposurebinds 0.0.0.0

    Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.

    Fix: Bind to 127.0.0.1 by default; never ship open debug endpoints.

  • Pass
    Execution Sandboxingcontainerized

    A container/sandbox image limits blast radius; a server that runs natively has full host access.

  • N/A
    Transport Encryption (TLS)guardno remote endpoints

    Plaintext HTTP exposes traffic and bearer tokens to interception.

  • N/A
    IAM / Authentication Scopingno remote endpoints

    OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.

  • N/A
    Live Endpoint Reachablenot dynamically scanned

    A dynamic scan connected to the declared remote endpoint and it responded — verified live, not a dead URL.

  • N/A
    Authentication Enforced (live)not dynamically scanned

    If the server declares auth is required, it must actually reject anonymous clients. Serving tools to unauthenticated callers is a real exposure.

Embed this score

Add the live badge to your README — it updates automatically on every rescan.

Canopii Trust Score badge preview
markdown[![Canopii Trust Score](https://index.canopii.dev/api/badge/piotr-agier/google-drive-mcp)](https://index.canopii.dev/server/piotr-agier/google-drive-mcp)
html<a href="https://index.canopii.dev/server/piotr-agier/google-drive-mcp"><img src="https://index.canopii.dev/api/badge/piotr-agier/google-drive-mcp" alt="Canopii Trust Score" /></a>

Versions

VersionScoreStatus
vmaster@9509fb8latest37Fscored
vmaster@dee5b0938Fscored
vmaster@4a950d339Fscored
vmaster@e26e5d339Fscored
vmaster@26f9b8339Fscored
vmaster@bb1a1d139Fscored
vmaster@29b117238Fscored
vmaster@c61b1a639Fscored
vmaster@556cfb939Fscored
vmaster@0490ea239Fscored
vmaster@f82461a39Fscored
vmaster@eca5a7486Bscored
vmaster@b609d1a86Bscored
vmaster@5caff4d88Bscored
vmaster@e173b0b84Bscored
vmaster@97d1e3586Bscored
vmaster@c819dae86Bscored
vmaster@f41239b88Bscored
vmaster@4cfc58388Bscored

Wondering how this compares? The MCP Security Index tracks grade distribution, committed secrets, and missing authentication across the whole ecosystem, refreshed monthly.