OpenTrustBench MCP server
Commit Nov 9, 2026Scans AI agents and MCP servers for vulnerabilities using OWASP-mapped rules and generates verifiable trust grades.
Also known as eulogik/OpenTrustBench
- Stars
- 14
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 9, 2026
- License
- Apache-2.0
What is OpenTrustBench MCP?
OpenTrustBench scans AI agents and MCP servers for vulnerabilities using OWASP-mapped rules and generates verifiable trust grades.
Summary generated from the project's README
About OpenTrustBench MCP server
Verifying the security of autonomous AI agents and MCP servers is possible through OpenTrustBench. This platform scans codebases for vulnerabilities and maps every finding to the OWASP Agentic AI Top 10 and OWASP LLM Top 10 2025 standards. Developers can run scans locally on folders, GitHub repositories, or npm packages using the CLI, without needing an account or sending telemetry to the platform.
Users receive a machine-readable Trust Card containing a letter grade and a security score, alongside SARIF reports for GitHub integration and human-readable Markdown reports. The tool includes specific commands like attack for static-heuristic analysis and eval for workflow reliability simulation. It is designed for developers and auditors who need to enforce security gates in CI/CD pipelines using the fail-on flag or provide transparency evidence for compliance reviews.
What you can do with it
- 1Automate security gates in CI/CDDevelopers can automatically stop a deployment pipeline if the scanner detects high-severity vulnerabilities.
- 2Verify public repository securityYou can perform a security audit on any public GitHub repository by providing its URL.
- 3Audit npm package dependenciesThe tool can check specific npm packages for vulnerabilities using the npm registry.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableeulogik/opentrustbench is public and reachablegithub.com/eulogik/opentrustbench ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-09github.com/eulogik/opentrustbench ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubWhat is OpenTrustBench?
OpenTrustBench is a trust and security verification platform for autonomous AI agents and MCP (Model Context Protocol) servers. It scans your codebase for vulnerabilities, maps findings to OWASP Agentic AI Top 10 and OWASP LLM Top 10 2025, generates a verifiable Trust Card with a letter grade, and provides a shareable badge for your README.
Local analysis, no OpenTrustBench telemetry. Dependency auditing uses the npm registry. No account required.
Quick Start
# Scan a local folder, MCP server, or Agent Skill
npx @opentrustbench/cli scan ./my-mcp-server
# Scan a GitHub repository
npx @opentrustbench/cli scan https://github.com/owner/repo
# Scan an npm package
npx @opentrustbench/cli scan some-npm-package --npm
# Fail CI when findings meet a severity threshold
npx @opentrustbench/cli scan ./my-mcp-server --fail-on high
# Run the OWASP Agentic Top 10 Adversarial Attack Suite
npx @opentrustbench/cli attack ./my-mcp-server
# Evaluate workflow reliability
npx @opentrustbench/cli eval ./tests/workflow.yaml
Install
| Channel | Command | Status |
|---|---|---|
| npm | npm install -g @opentrustbench/cli |
v0.1.3 live (package) |
| npx | npx @opentrustbench/cli scan . |
No install needed |
| PyPI | pip install opentrustbench |
v0.1.3 live (package) — requires Node 18+ and the npm CLI engine |
| Homebrew | brew tap eulogik/opentrustbench && brew install opentrustbench |
v0.1.3 live (tap) |
| Docker | docker run --rm -v $(pwd):/workspace eulogik/opentrustbench scan . |
v0.1.3 + latest live (Hub) |
| VS Code | code --install-extension eulogik.opentrustbench |
v0.1.3 live (Marketplace) |
| GitHub Action | - uses: eulogik/opentrustbench-action@v0.1.3 (repo) |
v0.1.3 live (Marketplace) |
| Source | git clone https://github.com/eulogik/OpenTrustBench.git && cd OpenTrustBench && npm install |
Always current |
What You Get
| Output | Description |
|---|---|
| Trust Card | Machine-readable credential (opentrustbench/trust-card/v2) with grade, score, findings, permissions, and coverage |
| SARIF Report | Industry-standard format for GitHub Security tab integration |
| Markdown Report | Human-readable audit report for compliance and review |
| Grade Badge | Shareable SVG badge linking to a public report page (example, registry) |
Grade Badge
Embed your trust score in your README:
[](https://www.opentrustbench.com/r/self-packages-cli.html)
This tells buyers, auditors, and AI hosts that your agent has been verified.
How It Works
- Scan — Point
opentrustbenchat a local directory, GitHub repo, or npm package - Grade — Receive a Trust Card with a letter grade (A–F) and security score (0–100)
- Share — Embed your badge and link to the detailed report
Features
- 8 detection rules across shell injection, secret leaks, prompt injection, tool exploitation, and more
- OWASP mapping — Every finding tagged to OWASP Agentic Top 10 (ASI01–ASI10) and LLM Top 10 2025 (LLM01–LLM10)
- Permission manifest — Automatic extraction and scoping of agent permissions
- Dependency audit —
npm auditintegration for lockfile-based vulnerability detection - SARIF output — Native GitHub Code Scanning integration
- CI integration —
--fail-onseverity gate for pipeline enforcement - GitHub Action — Drop-in composite action for workflows
- GitHub URL detection — Scan any public repo by URL
- Compliance helpers — Permission manifests and audit trails to attach to an EU AI Act review (evidence input, not a certification)
What the scanner is (and isn't)
- 8-rule static suite, OWASP-mapped (Agentic ASI01–ASI10, LLM LLM01–LLM10). Regex-based today — no AST yet.
attackis static-heuristic: it re-analyzes scan findings + permissions. No payloads execute.evalis simulation mode: suites are parsed and validated; nothing runs, costs/durations stay 0.- Not a certification. The Trust Card is a CI-grade credential, not a pentest or legal verdict.
Expert reviews
Need a human pass over your results? Request a review — manual result triage plus a remediation plan, scoped per target. The CLI stays the product and is free forever.
| Tier | Price | What You Get |
|---|---|---|
| CLI | Free | Unlimited local scans, Trust Card, badge, OWASP findings, SARIF, CI gate |
| Expert review | Scoped per target | Everything in CLI + manual triage, remediation plan, debrief call |
| Enterprise | Custom | Everything above + custom rules, evidence helpers, priority support |
Monorepo Structure
packages/
core/ — Detection engines, OWASP rules, trust scoring, attack analysis
cli/ — Terminal CLI with SARIF export and badge generation
action/ — GitHub Action for CI/CD pipelines
web/ — Landing page and interactive demo
badges/ — Shareable grade badge SVGs
examples/ — Vulnerable and secure test fixtures
scripts/ — Verification and demo scripts
docs/ — Research, registry report, and versioned roadmap (ROADMAP.md)
Build & Test
npm install # installs + builds via prepare
npm test # build + 28 unit tests
node scripts/verify-demos.mjs # end-to-end smoke checks
Standards
- OWASP Agentic AI Top 10 (ASI01–ASI10) — Published December 2025
- OWASP LLM Top 10 2025 (LLM01–LLM10)
- EU AI Act Article 50 transparency obligations (enforceable August 2, 2026)
- SARIF 2.1.0 for GitHub Code Scanning integration
License
Apache 2.0 © 2026 Eulogik
OpenTrustBench MCP questions
Does OpenTrustBench send my data to a server?
No, the platform performs local analysis with no telemetry sent to OpenTrustBench.
Can I use this in my CI/CD pipeline?
Yes, you can fail CI builds when findings meet a specific severity threshold using the --fail-on flag.
Is this a formal security certification?
No, the Trust Card is a CI-grade credential rather than a formal pentest or legal verdict.