code-graph-rag MCP Server Security Report
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Run it securely
Host vitali87/code-graph-rag in a governed environment — SSO in front, every tool call attributed and audited.
Are you the maintainer?
Verify with GitHub to get alerted whenever vitali87/code-graph-rag changes score — and claim the badge for your README.
Claim this serverThe short answer
- Is code-graph-rag safe to use?
- code-graph-rag scores 89/100 (grade B) on the Canopii Trust Index — good, minor gaps. It passes 13 of the 20 security controls that apply to it, with no confirmed security failures.
- How reliable is the security score for code-graph-rag?
- We could evaluate 81% of the controls that apply to code-graph-rag. 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 code-graph-rag 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 vmain@992338b
Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.
Security controlslatest scored version vmain@992338b
Each control is evaluated deterministically with evidence. The score is earned from passing controls; a failed guard caps it.
Model–MCP Runtime Guardrails
- Not checkedIndirect Prompt Injection (IPI) Defensesguardno tools extracted
Tool/prompt/resource text is free of hidden instructions that could hijack the agent.
- Not checkedStrict JSON Schema Enforcementno tool schemas found
Tool inputs are constrained (additionalProperties:false), so unexpected arguments can't be smuggled in.
- Not checkedUser-in-the-Loop / Approval Scopeguardno tools extracted
No over-broad or destructive tools (arbitrary shell, bulk-delete) that warrant human approval.
- N/ATool 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
- WarnNo SSRF sinksguard2 occurrences
Fetching tool-supplied URLs can pivot into internal networks and metadata services.
codebase_rag/readme_sections.py:201codebase_rag/stack/health.py:28Fix: Allow-list destinations; reject arbitrary/loopback/link-local URLs.
- WarnNo known-vulnerable dependencies1 of 4 runtime deps vulnerable; worst medium
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.
golang.org/x/[email protected] — GO-2026-6179golang.org/x/[email protected] — GO-2026-6180Fix: Upgrade the flagged dependencies past their fixed versions.
- 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 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.
- PassDependencies pinned (lockfile)lockfile present
A lockfile makes installs reproducible and resistant to silent dependency swaps.
- PassActively maintainedrecent commits
Unmaintained servers don't receive security fixes.
- PassRepository not archivedguardactive
Archived repositories will never be patched.
- PassDeclares a licenseMIT
A clear license is required for legal enterprise use.
- PassHas a security policySECURITY.md present
A SECURITY.md gives a private path to report vulnerabilities.
- 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.
- N/ANo install/post-install scriptsguardno published package
install hooks run arbitrary code on every consumer at install time.
- N/APackage name not typosquattingguardno published package
Names mimicking popular packages are a common malware delivery vector.
- N/APublished with provenanceno published package
Build provenance attests the artifact was built from the claimed source by CI.
- N/AEstablished maintainerno published package
Brand-new / single anonymous maintainers raise takeover and malware risk.
Transport & Trust Model
- WarnNetwork 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.
- PassExecution Sandboxingcontainerized
A container/sandbox image limits blast radius; a server that runs natively has full host access.
- 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.
Embed this score
Add the live badge to your README — it updates automatically on every rescan.
[](https://index.canopii.dev/server/vitali87/code-graph-rag)<a href="https://index.canopii.dev/server/vitali87/code-graph-rag"><img src="https://index.canopii.dev/api/badge/vitali87/code-graph-rag" alt="Canopii Trust Score" /></a>Versions
| Version | Score | Status | Published |
|---|---|---|---|
| vmain@2cee746 | 95A | scored | 9/24/2026 |
| vmain@9ca0208 | 95A | scored | 9/22/2026 |
| vmain@2abf8e3 | 95A | scored | 9/21/2026 |
| vmain@94120a6 | 95A | scored | 9/20/2026 |
| vmain@0d8d818 | 95A | scored | 9/19/2026 |
| vmain@f7cdc5f | 95A | scored | 9/16/2026 |
| vmain@941f536 | 89B | scored | 9/16/2026 |
| vmain@5b47825 | 89B | scored | 9/15/2026 |
| vmain@dee19db | 89B | scored | 9/13/2026 |
| vmain@96e017e | 89B | scored | 9/13/2026 |
| vmain@1f328f0 | 89B | scored | 9/12/2026 |
| vmain@a6d6326 | 89B | scored | 9/11/2026 |
| vmain@4f97f3e | 89B | scored | 9/10/2026 |
| vmain@f9bf820 | 89B | scored | 9/9/2026 |
| vmain@5e361a4 | 89B | scored | 9/7/2026 |
| vmain@80d556a | 89B | scored | 9/7/2026 |
| vmain@3f04db0 | 89B | scored | 9/6/2026 |
| vmain@c269fb7 | 89B | scored | 9/4/2026 |
| vmain@d555f61 | 89B | scored | 9/4/2026 |
| vmain@12996d7 | 89B | scored | 9/3/2026 |
| vmain@4b2aadd | 89B | scored | 9/2/2026 |
| vmain@f2c868e | 89B | scored | 8/31/2026 |
| vmain@991b568 | 89B | scored | 8/30/2026 |
| vmain@670c846 | 89B | scored | 8/29/2026 |
| vmain@231c311 | 89B | scored | 8/28/2026 |
| vmain@bce2d1f | 89B | scored | 8/27/2026 |
| vmain@fa97345 | 89B | scored | 8/26/2026 |
| vmain@d718e3c | 89B | scored | 8/25/2026 |
| vmain@3e2e5be | 89B | scored | 8/24/2026 |
| vmain@2b5a221 | 89B | scored | 8/23/2026 |
| vmain@a7f53b4 | 89B | scored | 8/22/2026 |
| vmain@3747ced | 89B | scored | 8/21/2026 |
| vmain@d88d8de | 89B | scored | 8/20/2026 |
| vmain@31a2f13 | 89B | scored | 8/19/2026 |
| vmain@992338blatest | 89B | scored | 8/18/2026 |
| vmain@9d71b80 | 89B | scored | 8/17/2026 |
| vmain@566a7c6 | 89B | scored | 8/16/2026 |
| vmain@3a4677c | 89B | scored | 8/15/2026 |
| vmain@27789c7 | 89B | scored | 8/14/2026 |
| vmain@bd55e78 | 95A | scored | 8/13/2026 |
| vmain@5a161a1 | 80B | scored | 8/12/2026 |
| vmain@01f2679 | 80B | scored | 8/11/2026 |
| vmain@c709600 | 80B | scored | 8/9/2026 |
Wondering how this compares? The MCP Security Index tracks grade distribution, committed secrets, and missing authentication across the whole ecosystem, refreshed monthly.