CodeInspectusBLOCK
Local-first MCP security scanner for AI-generated apps. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](LICENSE) [](package.json) [](https://www.npmjs.com/package/codeinspectus) [](https://registry.modelcontextprotocol.io/v0/servers?search=io.github.Synvoya%2Fcodeinspectus) [](https://glama.ai/mcp/servers/Synvoya/codeinspectus) [](https://github.com/Synvoya/codeinspectus)
A local-first, privacy-preserving security MCP server and CLI. Any AI coding agent (Claude Code, Cursor, Codex, Windsurf, Cline, Aider) can invoke CodeInspectus to scan AI-generated / "vibe-coded" code for real vulnerabilities, map findings to compliance frameworks as honest code-level coverage, and drive a scan → fix → rescan loop — fully on your machine, with no account and zero network egress at scan time.
Reproduce the V2.1 proof: the [email protected] package scans an immutable public Rich commit, finds one high-confidence GitHub Actions expression-injection pattern, applies GitHub's documented intermediate-env remediation in a temporary clone, confirms it as 1 resolved, 0 remaining, 0 introduced, 0 not rechecked, then creates and verifies sealed evidence for both states. Run the reproduction script or read the [scanner-derived case study](example
2f73c0879428OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add codeinspectus -- npx -y [email protected]
Exposed tools (12)
9 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
codeinspectus_apply_cleanup | write | |
codeinspectus_compliance_report | read | |
codeinspectus_explain_finding | read | |
codeinspectus_generate_sbom | read | |
codeinspectus_list_rules | read | |
codeinspectus_plan_cleanup | read | |
codeinspectus_rescan | read | |
codeinspectus_rollback_cleanup | read | |
codeinspectus_scan | read | |
codeinspectus_setup | read | |
deleteAccount | destructive | delete a user account |
transferFunds | write | move money between accounts |
Trust audit
BLOCKgrade F · trust 49/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | FAIL |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (5 observation(s))
- Shell
- declared (16 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
"-----BEGIN RSA PRIVATE KEY-----",
const RAW_SECRET = "sk_live_51Mz9KQb2eRxW7vYpL3nHsD8tA6cF0gJ4uXiZ2oP1rE5wB9mNqK7";
mixedStripe: "sk_live_51MixedLineA2b3C4d5E6f7G8h9J0k1L2m3N4",
codeinspectus-issue-payload-1.0.0.schema.json
Insecure deserialization: node-serialize unserialize() on untrusted data can
- pattern: $S.unserialize($X)
- pattern-not: $S.unserialize("...")- pattern: pickle.loads($X)
- pattern: yaml.load($X)
- pattern: eval($X)
- pattern: new Function(..., $X)
- pattern: eval($X)
- pattern: exec($X)
Math.random() is not cryptographically secure. For tokens/secrets/IDs use
["URL credentials", "const url = 'postgres://admin:[email protected]:5432/app';", "Sup3rS3cretPw"],
const SECRET = "sk_live_51Mz9KQb2eRxW7vYpL3nHsD8tA6cF0gJ4uXiZ2oP1rE5wB9mNqK7";
const SECRET = "sb_secret_A1b2C3d4E5f6G7h8I9j0K1_mN2pQ3rS";
const token = "sk_live_1234567890ABCDEFGHIJ";
const token = "sk_live_0123456789abcdefghij";
const token = "sk_live_0123456789abcdefghij";
const GH_TOKEN = "ghp_0123456789abcdefghijklmnopqrstuvwxyzAB"; // ghp_ + 38
const PEM = "-----BEGIN PRIVATE KEY-----\nMIIBVAIBADANBgkqFAKE0BAQEFAASCAT4wggE6AgEAfake1234567890\n-----END PRIVATE KEY-----";
const PEM = ["-----BEGIN RSA PRIVATE KEY-----", PEM_BODY, "ZW5kb2ZrZXlib2R5", "-----END RSA PRIVATE KEY-----"].join("\n");const pem = ["-----BEGIN PRIVATE KEY-----", PEM_BODY, "-----END PRIVATE KEY-----"].join("\n");const SLACK_TOKEN = "xoxb-1234567890-abcdefghijklmno";
Gates applied: critical_finding, no_behavioural_pass.
2f73c0879428full audit observations/trust-audit/mcp-server/synvoya__codeinspectus.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 2f73c0879428 | BLOCK | F | 49 | first audit |
Questions
What is the CodeInspectus MCP server?
Local-first MCP security scanner for AI-generated apps. Scan → fix → rescan from Claude Code, Cursor, Codex, and other agents.
What tools does CodeInspectus expose?
12 in total: 9 read-only, 2 that write, and 1 that can delete or overwrite (deleteAccount). Every one is listed on this page with its risk.
Is CodeInspectus safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (49/100) and found 13 critical or high issues in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does CodeInspectus need?
It reads AMPLITUDE_API_KEY, ANDROID_API_KEY, ANTHROPIC_API_KEY, API_SECRET, ASSERTED_SECRET, AWS_ACCESS_KEY_ID, BACKUP_SECRET, BILLING_API_SECRET, CHECK_AUTH, COMMENT_SECRET, DB_PASSWORD and DIRECT_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does CodeInspectus run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as codeinspectus at 3.3.1.
How current is this page?
The grade is for one exact copy of the source (2f73c0879428), read on 2026-10-08. The repository is watched and re-audited when it changes.