CanopiiCanopiiAll serversEnterprise →

deliberation MCP Server Security Report

antonbabenko/deliberation

Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures which models earn their seat.

Security Trust Score
Grade B · Moderate posture
Tier 1 · Public sourceHigh confidence · 98%latest vmaster@aeb129a Repository
Declared MCP capabilities
ResourcesPrompts

Run it securely

Host antonbabenko/deliberation in a governed environment — SSO in front, every tool call attributed and audited.

Are you the maintainer?

Verify with GitHub to get alerted whenever antonbabenko/deliberation changes score — and claim the badge for your README.

Claim this server

The short answer

Is deliberation safe to use?
deliberation scores 88/100 (grade B) on the Canopii Trust Index — good, minor gaps. It passes 16 of the 21 security controls that apply to it, with no confirmed security failures.
How reliable is the security score for deliberation?
We could evaluate 98% of the controls that apply to deliberation. 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 deliberation 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.
Reputation181stars12forks1open issues3d agolast commit<1yage

Security controlslatest scored version vmaster@aeb129a

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

Model–MCP Runtime Guardrails

  • Pass
    Indirect Prompt Injection (IPI) Defensesguardno injection markers

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

  • Pass
    Strict JSON Schema EnforcementadditionalProperties:false present

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

  • Pass
    Tool Definition Integrityguardtool definitions stable; no risky changes in version history

    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.

  • 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 command-injection sinksguard1 occurrence (build/test paths only)

    Untrusted tool input reaching a shell yields remote code execution.

    .github/release/pre-commit.js:109

    Fix: Never pass tool arguments to a shell; use argv arrays with shell disabled.

  • Warn
    No path traversalguard35 occurrences

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

    core/analyze.js:433core/analyze.js:436core/analyze.js:439core/analyze.js:514

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

  • Warn
    No SSRF sinksguard1 occurrence

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

    server/dashboard/ui/api.js:34

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

  • 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 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
    No known-vulnerable dependencies1 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
    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

  • Pass
    Execution Sandboxingcontainerized

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

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

Versions

VersionScoreStatus
vmaster@aeb129alatest88Bscored
vmaster@687bfe488Bscored
vmaster@9ecf74688Bscored
vmaster@ef84a7188Bscored
vmaster@dc4e3e188Bscored
vmaster@e4e9b9788Brunning
vmaster@e5fe39989Bscored
vmaster@7cd0ab589Bscored
vmaster@2ec856286Bscored
vmaster@5733af689Bscored
vmaster@47c501b91Ascored
vmaster@55f8fff91Ascored
vmaster@47cab9a91Ascored
vmaster@983a11c91Ascored
vmaster@1ade10991Ascored
vmaster@1ac906991Ascored
vmaster@5759b9991Ascored
vmaster@89fad4991Ascored
vmaster@e1f238891Ascored
vmaster@5d2bead91Ascored
vmaster@3be2a9191Ascored
vmaster@1cab2cb90Ascored
vmaster@8271ca390Ascored
vmaster@9d3f3fa90Ascored
vmaster@5daf66390Ascored

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