mcp-server MCP Server Security Report
Search, compare, and install self-evolving AI Agent Genes ranked by Arena fitness
Run it securely
Host io.github.rotifer-protocol/mcp-server in a governed environment — SSO in front, every tool call attributed and audited.
Are you the maintainer?
Verify with GitHub to get alerted whenever rotifer-protocol/rotifer-mcp-server changes score — and claim the badge for your README.
Claim this serverThe short answer
- Is mcp-server safe to use?
- mcp-server scores 92/100 (grade A) on the Canopii Trust Index — strong posture. It passes 19 of the 25 security controls that apply to it, with no confirmed security failures.
- How reliable is the security score for mcp-server?
- We could evaluate 98% of the controls that apply to mcp-server. 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.
- Does mcp-server have any security advisories?
- mcp-server has 2 non-scoring advisories — observations worth a human review that deliberately do not affect the deterministic score, since they can be noisy.
- How was mcp-server 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.
Security controlslatest scored version v0.17.0
Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.
Security controlslatest scored version v0.17.0
Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.
Model–MCP Runtime Guardrails
- WarnTool Definition Integrityguard2 tool description(s) drifted after publish (no risk signals in 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.
get_arena_rankingsarena_submitFix: Never add hidden directives or destructive scope to an already-published tool; document description changes in release notes.
- PassIndirect Prompt Injection (IPI) Defensesguardno injection markers
Tool/prompt/resource text is free of hidden instructions that could hijack the agent.
- PassStrict JSON Schema EnforcementadditionalProperties:false present
Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.
- PassUser-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
- WarnDependencies pinned (lockfile)no lockfile found
A lockfile makes installs reproducible and resistant to silent dependency swaps.
Fix: Commit a lockfile (package-lock.json / pnpm-lock.yaml / poetry.lock).
- WarnEstablished maintainersingle maintainer
Brand-new / single anonymous maintainers raise takeover and malware risk.
Fix: Publish under an established account/org; add multiple maintainers.
- WarnHas 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.
- PassNo command-injection sinksguardno sinks found
Untrusted tool input reaching a shell yields remote code execution.
- PassNo dynamic code executionguardno sinks found
eval()/exec()/Function() on tool-derived strings allows arbitrary code execution.
- PassNo path traversalguardno sinks found
Naive path checks let tools read/write outside intended directories (EscapeRoute-class).
- PassNo SSRF sinksguardno sinks found
Fetching tool-supplied URLs can pivot into internal networks and metadata services.
- PassNo unsafe deserializationguardno sinks found
pickle/yaml.load/etc. on untrusted data can execute code.
- PassNo committed secretsguardno secrets found
Hardcoded keys/tokens in published source are live credentials an attacker can use.
- PassCredentials sourced from environmentreads credentials from environment
Reading secrets from env/secret stores avoids hardcoding them.
- PassNo 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.
- PassNo install/post-install scriptsguardno install scripts
install hooks run arbitrary code on every consumer at install time.
- PassPackage name not typosquattingguarddistinct package name
Names mimicking popular packages are a common malware delivery vector.
- PassPublished with provenancepublished with provenance
Build provenance attests the artifact was built from the claimed source by CI.
- PassActively maintainedrecent commits
Unmaintained servers don't receive security fixes.
- PassRepository not archivedguardactive
Archived repositories will never be patched.
- PassDeclares a licenseApache-2.0
A clear license is required for legal enterprise use.
- PassAdoption & 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 checkedSigned releasesnot evaluated
Signed releases let consumers verify artifacts weren't tampered with.
Transport & Trust Model
- WarnExecution 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.
- PassNetwork Exposureno bind-all detected
Binding 0.0.0.0 or exposing debug inspectors widens the attack surface.
- N/ATransport Encryption (TLS)guardno remote endpoints
Plaintext HTTP exposes traffic and bearer tokens to interception.
- N/AIAM / Authentication Scopingno remote endpoints
OAuth 2.1 / Protected Resource Metadata gates who can invoke tools.
- N/ALive Endpoint Reachablenot dynamically scanned
A dynamic scan connected to the declared remote endpoint and it responded — verified live, not a dead URL.
- N/AAuthentication 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.
AI-flagged — for review
Observations from an AI review of tool descriptions. These are advisory only and do not affect the score — they can be noisy and need human judgement.
- infoTool "get_arena_rankings" description changed after publish
Benign definition drift: the description changed vs the prior version with no risk signals in the diff. Clients approve tools by name and don't re-review on update, so the change is invisible to existing grants.
- infoTool "arena_submit" description changed after publish
Benign definition drift: the description changed vs the prior version with no risk signals in the diff. Clients approve tools by name and don't re-review on update, so the change is invisible to existing grants.
Embed this score
Add the live badge to your README — it updates automatically on every rescan.
[](https://index.canopii.dev/server/io.github.rotifer-protocol/mcp-server)<a href="https://index.canopii.dev/server/io.github.rotifer-protocol/mcp-server"><img src="https://index.canopii.dev/api/badge/io.github.rotifer-protocol/mcp-server" alt="Canopii Trust Score" /></a>Versions
Wondering how this compares? The MCP Security Index tracks grade distribution, committed secrets, and missing authentication across the whole ecosystem, refreshed monthly.