CanopiiCanopiiAll serversEnterprise →

mcp-server-neon MCP Server Security Report

neondatabase/mcp-server-neon

Neon: Postgres branch and database management.

Security Trust Score
Grade F · Serious issues
Tier 1 · Public sourceHigh confidence · 98%latest vmain@0aebcbd Repository Vendor-published
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 neondatabase/mcp-server-neon changes score — and claim the badge for your README.

Claim this server
2 issues capping this score
  • highTool descriptions free of injection markers — 1 marker(s) across 1 tool(s)
  • highNo risky post-publish tool changes (rug-pull) — 1 risky tool-definition change(s) in version history (main@2447fd1 → main@4ff1dcb)

The short answer

Is mcp-server-neon safe to use?
mcp-server-neon scores 36/100 (grade F) on the Canopii Trust Index, and carries 2 confirmed security failures that cap its score: Tool descriptions free of injection markers and No risky post-publish tool changes (rug-pull). It passes 13 of the 22 controls that apply to it.
What security issues does mcp-server-neon have?
mcp-server-neon fails 2 controls: Tool descriptions free of injection markers and No risky post-publish tool changes (rug-pull). 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 mcp-server-neon?
We could evaluate 98% of the controls that apply to mcp-server-neon. 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 mcp-server-neon 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.
Reputation663stars134forks51open issuestodaylast commit2yage

Security controlslatest scored version vmain@0aebcbd

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

Model–MCP Runtime Guardrails

  • Fail
    Indirect Prompt Injection (IPI) Defensesguard1 marker(s) across 1 tool(s)

    Tool/prompt/resource text is free of hidden instructions that could hijack the agent. How many servers fail this?

    complete_query_tuning — pre-action injection

    Fix: Remove hidden directives, HTML/comment instructions, and override phrasing from descriptions.

  • Fail
    Tool Definition Integrityguard1 risky tool-definition change(s) in version history (main@2447fd1 → main@4ff1dcb)

    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?

    complete_query_tuning

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

  • Pass
    Strict JSON Schema EnforcementadditionalProperties:false present

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

  • Pass
    In-Session Definition Integrityguardno call-gated or call-time tool definition changes

    Tool and prompt definitions stay fixed during a session — they don't change after a few calls, which is how runtime-gated rug-pulls slip past one-time review.

  • Pass
    User-in-the-Loop / Approval Scopeguardno destructive tool scope

    No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval.

Application Security Checks

  • Warn
    No path traversalguard39 occurrences

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

    e2e/docs-only-mcp.spec.ts:90e2e/oauth-register-authorize.spec.ts:340lib/oauth/client-credentials.ts:24lib/oauth/client-id-metadata-document.ts:67

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

  • Warn
    No SSRF sinksguard7 occurrences

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

    lib/oauth/client-id-metadata-document.ts:193mcp/__tests__/refresh-concurrency.bench.test.ts:575mcp/__tests__/refresh-concurrency.bench.test.ts:656mcp/neon-client.ts:137

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

  • Warn
    No known-vulnerable dependencies39 of 776 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.

    @modelcontextprotocol/[email protected] — GHSA-22jm-h49p-29qw@modelcontextprotocol/[email protected] — GHSA-345p-7cg4-v4c7@modelcontextprotocol/[email protected] — GHSA-46jr-4wx8-v453@modelcontextprotocol/[email protected] — GHSA-6prh-2h8m-c8cw

    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
    Execution Sandboxingruns natively (no container image)

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

    Fix: Ship a Dockerfile/Containerfile (or document a sandboxed run) so the server runs isolated.

  • 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.

  • 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
    No Token Passthroughguardno HTTP transport

    The client's token is never forwarded to downstream APIs — the server obtains its own, correctly-scoped credential instead.

  • N/A
    DNS-Rebinding Protectionno HTTP transport

    HTTP endpoints reject requests carrying an unlisted Origin, so a malicious web page can't drive the server through the user's browser.

  • 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/neondatabase/mcp-server-neon)](https://index.canopii.dev/server/neondatabase/mcp-server-neon)
html<a href="https://index.canopii.dev/server/neondatabase/mcp-server-neon"><img src="https://index.canopii.dev/api/badge/neondatabase/mcp-server-neon" alt="Canopii Trust Score" /></a>

Versions

VersionScoreStatus
vmain@0aebcbdlatest36Fscored
vmain@c733b9135Fscored
vmain@28840e035Fscored
vmain@3e8c7cb35Fscored
vmain@43d69f535Fscored
vmain@6c4d43b35Fscored
vmain@b1fd2ab35Fscored
vmain@cd24cc136Fscored
vmain@fd9123c36Fscored
vmain@1f341ee36Fscored
vmain@695541336Fscored
vmain@e9ef5d836Fscored
vmain@185d5ee36Fscored
vmain@00d82d436Fscored
vmain@440905d36Fscored
vmain@1bbc16136Fscored
vmain@a7b292736Fscored
vmain@912ab9a36Fscored
vmain@aed677136Fscored
vmain@857028f36Fscored
vmain@9b8928b36Fscored
vmain@be54e7836Fscored
vmain@141ebed36Fscored
vmain@c499c6d36Fscored
vmain@037978536Fscored
vmain@3c82a0636Fscored
vmain@43fd64e36Fscored
vmain@4ff1dcb36Fscored
vmain@2447fd183Bscored
vmain@e131c6f86Bscored
vmain@73ed5b486Bscored
vmain@ea9259a86Bscored
vmain@6fd710c83Bscored
vmain@30de03883Bscored
vmain@949281285Bscored

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