ci-guard-mcp
Audits GitHub repository security configuration: scans GitHub Actions workflows for pwn-request patterns (pull_request_target checkout of event-derived PR head), script injection via event/head-ref interpolation in run steps, unpinned remote actions and reusable workflows, missing top-level permissions, and malformed workflow YAML. Also ships as a GitHub Action that runs the same audit in CI, emitting error/warning/finding counts, a job summary, and escaped workflow annotations, plus detection of recognizable GitHub credential shapes.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ci-guard-mcpscan my repository for risky workflows and secrets"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ci-guard-mcp
One local audit engine. A CLI, a GitHub Action, and four MCP tools.
Catch risky GitHub workflows, undocumented environment variables, possible credentials, and conflicting dependency configuration before merging. Audits are deterministic, read-only, and run without sending source code to a service. Two runtime dependencies: yaml and ignore.
Run locally
Requires Node.js 20 or later. Git is required for index scans and tracked-file selection.
# Run directly with npx:
npx ci-guard-mcp scan . --fail-on warn
npx ci-guard-mcp scan . --sandbox
npx ci-guard-mcp scan . --no-git
npx ci-guard-mcp scan . --format json
npx ci-guard-mcp scan . --format sarif > findings.sarif
npx ci-guard-mcp scan . --auditor workflows --auditor lockfile
npx ci-guard-mcp scan . --auditor secrets --staged
npx ci-guard-mcp scan . --auditor secrets --include-ignored
# Or from a local source checkout:
npm ci --ignore-scripts
npm run build
node dist/cli.js scan .Exit codes: 0 below threshold, 1 findings at or above threshold, 2 invalid arguments, configuration or I/O failure. --fail-on error is the default; warn also fails on warnings. Informational findings never fail a scan. Output formats are text, json, sarif, and github. --root PATH is equivalent to the positional scan directory. --include-ignored audits tracked files even when they match .gitignore rules (for example, a .env committed before .gitignore was added). --help lists every flag.
Staged mode is intentionally limited to secrets: it reads entire changed index blobs, including renamed/added files, so unstaged edits cannot conceal a staged credential. It applies ignore rules from the index and skips deletions, symlinks and submodules. Other audits need the repository-wide context and cannot be combined with --staged.
Related MCP server: strands-sentinel
GitHub Action
After this repository is published, use a reviewed full commit SHA in place of FULL_COMMIT_SHA:
name: Repository audit
on: [push, pull_request]
permissions:
contents: read
jobs:
audit:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: carelessdept/ci-guard-mcp@FULL_COMMIT_SHA
id: guard
with:
path: .
fail-on: warnInputs: path (default .), fail-on (error or warn, default error). Outputs: errors, warnings, findings as decimal counts. Outputs and the Markdown job summary are written before the finding threshold is evaluated. Findings become escaped workflow annotations; a failed audit exits the action with status 1. Operational failure exits 2 and does not claim complete counts.
This composite action installs its locked build dependencies with lifecycle scripts disabled into a runner-temp directory and runs the compiled CLI. It requires npm registry access, Bash, and a runner compatible with actions/setup-node@v4. The scanned repository's dependencies and scripts are never installed or executed. The self-audit workflow runs the local action and verifies its outputs. Run the CLI separately with --format sarif when uploading to a code-scanning service; the action itself does not upload reports or request write permissions.
MCP server
The stdio server uses newline-delimited JSON-RPC 2.0, negotiates MCP versions 2025-11-25, 2025-06-18, 2025-03-26 and 2024-11-05, and implements initialization, ping, tool discovery, tool calls and silent notifications. A client must send notifications/initialized after initialization. No network transport or credentials are needed.
Example MCP client configuration after npm publication:
{
"mcpServers": {
"ci-guard": {
"command": "npx",
"args": ["--yes", "ci-guard-mcp", "--mcp", "--root", "/absolute/path/to/repository"]
}
}
}For a source checkout, use "command": "node" and "args": ["/absolute/path/to/ci-guard-mcp/dist/cli.js", "--mcp", "--root", "/absolute/path/to/repository"].
Tool | Behavior | Arguments |
| All four auditors |
|
| Environment and deployment drift |
|
| Workflow security |
|
| Redacted credential findings |
|
Paths resolve inside the launch root; parent traversal and symlinks escaping it are rejected. Responses contain text JSON plus structuredContent with the same report. Invalid tool arguments are JSON-RPC errors; execution failures use isError: true. Stdout contains only protocol messages. Frames over 1 MiB are rejected, and the server recovers at the next newline. Requests are serialized to keep memory use and ordering predictable; scans complete before the next queued request, so cancellation notifications do not interrupt an active audit.
Audit rules
Rule | Severity | Detects |
| error |
|
| error | GitHub event/head-ref or GitLab MR/commit expressions directly interpolated in |
| error | Direct |
| warn | Remote actions, reusable workflows, or GitLab |
| warn | Missing top-level |
| error | Malformed workflow YAML, duplicate keys or non-mapping document |
| warn | Literal source references absent from |
| info | Template declarations without detected source or deployment use |
| error | Malformed Compose YAML |
| error | Recognizable credential shapes/private-key headers |
| error | High-entropy quoted assignments to credential-like names |
| error | Multiple recognized package-manager lockfiles in the same directory |
| error | HTTP URLs in text lockfiles |
| warn |
|
| error | Invalid JSON package manifests |
| warn | Files exceeding the configured size limit |
Environment patterns support process.env.X, bracket syntax, import.meta.env.X, Python os.environ[...] / .get(...) / os.getenv(...), Go os.Getenv(...), and Rust std::env::var(...) / env::var(...). Templates and declarations are aggregated across the scan root. Docker ENV and Compose environment entries count as consumers; deployment-only variables still require documentation when source references them. Tests/fixtures are excluded from source reference extraction.
Secrets use known prefixes and contextual entropy (at least 24 characters, Shannon entropy ≥4.3 bits/character). Values and source snippets are never included in findings, SARIF or MCP results. In a Git root, normal secret audits read tracked working-tree files; untracked files are skipped. Without Git, all eligible files are scanned. Other auditors include untracked files. .gitignore and nested ignore rules are respected by default (pass --include-ignored or includeIgnored: true to force-scan tracked files matching .gitignore), alongside built-in dependency/build-directory exclusions. Symlinks and NUL-containing binary files are skipped.
Configuration
Use .ciguardrc.json or package.json's ciguard object. The rc file takes precedence. Unknown keys and invalid types fail explicitly. Arrays replace defaults rather than merging. Patterns in ignore and secretIgnore use gitignore syntax relative to the scan root.
{
"ignore": ["generated/"],
"allowActions": ["actions/*"],
"ignoreEnv": ["NODE_ENV", "CI", "PATH", "HOME"],
"secretIgnore": ["test/", "tests/", "__tests__/", "fixtures/", "__fixtures__/", "*.test.*", "*.spec.*", ".env.example", ".env.template"],
"disabledRules": [],
"maxFileBytes": 1048576
}By default allowActions is empty: official actions also require immutable pins. Set actions/* explicitly to permit mutable official references, or list exact identities such as actions/checkout. maxFileBytes accepts 1 KiB–16 MiB; oversized text files produce warnings, which cannot be suppressed through disabledRules. The repository's own config excludes docs/ because the landing page contains instructional examples and adds GitHub's two runtime output variables to ignoreEnv.
SDK
import { scan, formatSarif } from 'ci-guard-mcp';
const report = await scan({ root: '/path/to/repo', auditors: ['workflows', 'secrets'] });
console.log(report.summary);
const sarif = formatSarif(report);Named auditor functions accept { files: [{ path, content }], config } for in-memory integrations. SDK config overrides file configuration. Reports contain version, findings, counts and files scanned; no timestamp or absolute root is included, allowing stable snapshots. filesScanned counts eligible text files collected, including files not relevant to a selected auditor.
Boundaries and limitations
This is a static heuristic auditor, not a proof of security or a credential validity checker. It does not execute code, resolve computed environment names, follow calls across files, inspect Git history, decrypt files, audit remote reusable workflow bodies, or analyze dependency vulnerabilities. YAML workflow checks inspect local structured steps and job-level reusable workflow references. Event-derived values passed through intermediate expressions or files can evade direct interpolation checks. Literal environment patterns can match commented examples or strings. Dead-template notices are advisory because external consumers and dynamic reads are invisible.
Default secret exclusions deliberately reduce noise in tests/templates; replace secretIgnore with [] for broader coverage. Synthetic tokens that look real can still be reported, and unknown/low-entropy/encoded credentials can be missed. Tracked files ignored by .gitignore are excluded in a normal scan unless --include-ignored (includeIgnored: true) is passed. Binary lockfiles are skipped as binary content. Package-specific environment scopes are not inferred; scan a package directory separately for isolated drift checks. Repository configuration is trusted local policy, so review config and ignore changes in pull requests. Do not use the MCP launch root as an OS-level sandbox against a concurrently malicious local process.
Development and release
npm ci --ignore-scripts
npm run check
node dist/cli.js scan --fail-on warn
npm pack --dry-runCI runs tests/typechecks/build/package checks on Node 20 and 22 across Linux, macOS and Windows. See CONTRIBUTING.md for regression tests and SECURITY.md for disclosure.
MIT licensed. Maintained openly through reproducible reports, focused changes and documented limitations.
Protocol references: MCP stdio, SARIF 2.1.0.
This server cannot be deployed
Maintenance
Related MCP Connectors
Audit GitHub Actions workflows for script injection, unpinned actions and missing permissions.
Statically audits MCP tool surfaces for token cost, schema quality, and design issues.
Generate SBOMs, scan vulnerabilities, and analyze dependencies from local projects or Git repos.
Audit GitHub repos for malicious and supply-chain code before you depend on them.
Related MCP Servers
- AlicenseAqualityCmaintenanceEnables agents to audit and safeguard repositories by detecting dependency pinning issues, license compliance problems, hardcoded secrets, and dead code through MCP tools.4MIT
- AlicenseAqualityAmaintenanceEnables MCP clients to run deterministic AST safety audits, secret scanning, and sandboxed test execution on codebases, with human approval required before any remediation action.5MIT
- AlicenseAqualityAmaintenanceEnables agents and CI pipelines to audit MCP servers and agent tool-chains by statically scanning repositories, local checkouts, tools/list exports, or live endpoints for risks such as destructive actions without confirmation, mismatched safety annotations, injection surfaces, credential or PII exposure, and unguarded command, path, or URL sinks. All checks are read-only and never execute the scanned code or call tools/call.3MIT
- AlicenseNot gradedqualityBmaintenanceA read-only MCP server that lets an agent audit its own environment by discovering local MCP configurations and skill folders on Windows, macOS, and Linux and running offline static checks for prompt injection, hidden instructions, hardcoded secrets, dangerous commands, unpinned packages, and excessive filesystem or transport permissions. It exposes tools to scan everything discovered, list configurations, vet a single skill, or analyze supplied text, returning text, JSON, SARIF, or HTML findings with CI-friendly severity levels.0MIT