CanopiiCanopiiAll serversEnterprise →

shelfmark MCP Server Security Report

io.github.Dankaro-projects/shelfmark

Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.

Security Trust Score
Grade D · Weak posture
Tier 1 · Public sourceHigh confidence · 92%latest v0.4.8 Repository
Declared MCP capabilities
ResourcesPrompts

Run it securely

This server scored D. 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 Dankaro-projects/shelfmark changes score — and claim the badge for your README.

Claim this server
1 issue capping this score
  • highTool descriptions free of injection markers — 1 marker(s) across 1 tool(s)

The short answer

Is shelfmark safe to use?
shelfmark scores 42/100 (grade D) on the Canopii Trust Index, and carries 1 confirmed security failure that caps its score: Tool descriptions free of injection markers. It passes 16 of the 24 controls that apply to it.
What security issues does shelfmark have?
shelfmark fails 1 control: Tool descriptions free of injection markers. 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 shelfmark?
We could evaluate 92% of the controls that apply to shelfmark. 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 shelfmark 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.
Reputation0stars0forks0open issuestodaylast commit<1yage

Security controlslatest scored version v0.4.8

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?

    corpus_stats — exfiltration directive

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

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

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

  • N/A
    Tool Definition Integrityguardno prior version to diff

    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.

Application Security Checks

  • Warn
    Established maintainerrecently published

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

    Fix: Publish under an established account/org; add multiple maintainers.

  • Warn
    Adoption & popularitylimited adoption

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

    Fix: Adoption grows naturally with real-world use; this never gates the score.

  • 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 path traversalguardno sinks found

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

  • Pass
    No SSRF sinksguardno sinks found

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

  • 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
    No known-vulnerable dependencies58 runtime deps, no known CVEs

    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.

  • Pass
    Dependencies pinned (lockfile)lockfile present

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

  • Pass
    Package name not typosquattingguarddistinct package name

    Names mimicking popular packages are a common malware delivery vector.

  • 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
    Has a security policySECURITY.md present

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

  • Not checked
    No install/post-install scriptsguardnot determinable from PyPI metadata

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

  • Not checked
    Published with provenancenot determinable

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

  • Not checked
    Signed releasesnot evaluated

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

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.

  • Pass
    Network Exposureno bind-all detected

    Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.

  • 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/io.github.Dankaro-projects/shelfmark)](https://index.canopii.dev/server/io.github.Dankaro-projects/shelfmark)
html<a href="https://index.canopii.dev/server/io.github.Dankaro-projects/shelfmark"><img src="https://index.canopii.dev/api/badge/io.github.Dankaro-projects/shelfmark" alt="Canopii Trust Score" /></a>

Versions

VersionScoreStatus
v0.4.8latest42Dscored

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