
GuardBee MCP server monorepo — pnpm workspaces + Turborepo
GuardBee MCP server monorepo — pnpm workspaces + Turborepo
·
🇬🇧 English | 🇹🇷 Türkçe | 🇨🇳 中文 | 🇯🇵 日本語 | 🇰🇷 한국어 | 🇧🇷 Português | 🇪🇸 Español | 🇩🇪 Deutsch
Security for AI agents and MCP. GuardBee puts a gateway between your agents and their tools and models that masks personal data and secrets, blocks prompt injection and toxic data flows, asks before risky calls and keeps a tamper-evident audit log, plus scanners that check your code and configs against the OWASP MCP Top 10. Open source (MIT), runs on your machine, no account needed.
The gateway and every server speak MCP 2026-07-28 and 2025-11-25 (MCP TypeScript SDK v2), so they work with clients and servers on either revision.
# Put your existing MCP servers behind the gateway (backs up your client config first)
npx -y @guardbee/mcp-security-proxy@^1 init --client claude-desktop # or cursor, claude-code
# Check a codebase against the OWASP MCP Top 10
npx -y @guardbee/mcp-owasp-scan scan . --fail-on=highnpx -y @guardbee/mcp-security-proxy@^1 init --client cursor (or claude-desktop / claude-code). Restarts the client with GuardBee in front of your MCP servers.npx -y @guardbee/mcp-owasp-scan scan . --fail-on=high for OWASP MCP Top 10; npx -y @guardbee/mcp-secret-scanner scan . --history for leaked keys (no MCP client required).Run it yourself: examples/demo (npm install && npm start).
Install anywhere: npm, a signed multi-arch container image (ghcr.io/guardbee/mcp-security-proxy), a Helm chart, coding-agent hooks (Claude Code, Cursor, Codex, Gemini CLI, Windsurf), a GitHub Action and IDEs: see INSTALL.md.
| You want to… | Install | How |
|---|---|---|
| Protect agents at runtime: mask personal data, block injection and toxic flows, approve risky calls, keep an audit log | @guardbee/mcp-security-proxy | Put it in front of your MCP servers (guardbee-proxy init imports your client config) |
| Check a codebase against the OWASP MCP Top 10 in one pass, in CI | @guardbee/mcp-owasp-scan | npx @guardbee/mcp-owasp-scan scan . --format=sarif --fail-on=high |
| Give an agent many GuardBee checks from one MCP server | @guardbee/security-suite | guardbee serve (recommended set), --tools=code,network or all |
| Find leaked keys in files, git history or agent transcripts | @guardbee/mcp-secret-scanner | npx @guardbee/mcp-secret-scanner scan . --history |
| Audit the MCP servers configured on developer machines | @guardbee/mcp-config-auditor | npx @guardbee/mcp-config-auditor discover |
| Let an agent query a database without seeing raw personal data | @guardbee/mcp-db-gateway | Point it at your database with a policy |
| Use the detectors in your own code | @guardbee/guard-core | import { maskPiiInText } from "@guardbee/guard-core" |
Every other package is a single check (one OWASP risk, one protocol, one file type); each is in security-suite too. npx @guardbee/security-suite list shows them with what they check.
Detection is measured, not claimed: packages/pii-bench is a reproducible benchmark for Turkish and international personal data, with bootstrap 95% intervals and the datasets in the repo.
| Benchmark | Result |
|---|---|
| Identifiers (TC Kimlik, IBAN, card, phone, e-mail, …), 400 documents + 160 clean | F1 97.1, recall 100%, false alarms on clean documents 8.1%, 0.04 ms per document |
| Person names with the optional NER model, same set | F1 99.5 |
| Hand-written hard cases for names (tr-names-challenge) | F1 97.1, 0 false alarms |
| KVKK Art. 6 special categories with NER (tr-special-challenge) | F1 97.5, 0 false alarms |
Bypass suite: 5 identifiers × 16 disguises (base64, hex, URL/HTML/\u escapes, other scripts' digits, separators) | 80 / 80 masked, 0 of 16 look-alike strings changed |
The identifier detectors were tuned after reading this set's misses, so the challenge sets are the fairer measure; the pii-bench README lists the limits. Any other detector can be run on the same data through its System interface.
MCP attacks: packages/mcp-bench is a public dataset (CC BY 4.0) of poisoned and benign tool definitions, injected and benign tool results, toxic and safe tool catalogs, and rug-pull sequences, in English and Turkish. Third-party baselines run on the same data, and CI fails if GuardBee's scores drop. The leaderboard covers the held-out split:
| Task (test split) | GuardBee rules | GuardBee + local judge | mcp-guardian 2.4.0 | Cisco MCP Scanner YARA 4.8.7 |
|---|---|---|---|---|
| Tool poisoning, F1 | 0.50 | 0.75 | 0.61 | 0.42 |
| Indirect injection in tool results, F1 | 0.47 | 0.83 | 0.59 | 0.27 |
| Toxic flows (lethal trifecta), F1 | 0.91 | — | — | — |
| Rug pulls (drift + content checks), F1 | 0.89 | — | — | — |
GuardBee's rules alone trail mcp-guardian on tool poisoning: no Turkish patterns yet, and narrower phrasing. The README has the per-class numbers, the settings and the limitations.
Prompt injection and jailbreaks, Turkish + English: packages/injection-bench has 2,394 samples: Turkish 576 attacks / 569 benign, English 653 / 596. They come from public datasets (Gandalf, deepset, jackhhao, OpenAssistant) and from hand-written Turkish cases, and the provenance is documented. The leaderboard covers the held-out split:
| F1 (test split) | Turkish | English |
|---|---|---|
| GuardBee rules (what the proxy blocks) | 28.6 (0% false positives) | 20.4 (0%) |
| GuardBee rules + local LLM judge (qwen2.5:7b, ~1 s) | 89.6 | 90.8 |
| ProtectAI DeBERTa-v3 prompt-injection v2 | 70.2 | 89.1 |
GuardBee rules + local classifier (@guardbee/injection-model, ~8 ms) | 93.7 | 91.6 |
The rules are precise but catch only 11–19% of attacks. GuardBee's optional classifier closes most of that gap in both languages. The English-trained ProtectAI model loses 19 F1 points in Turkish. The README explains both.
Ready-to-copy proxy policies (minimal, KVKK, coding agent, LLM gateway), client configs for Claude Desktop, Claude Code, Cursor and VS Code, and CI templates for GitHub Actions and GitLab: examples/.
| Package | npm | Description |
|---|---|---|
packages/ai-code-scanner | @guardbee/mcp-ai-code-scanner | Scans a codebase for insecure LLM/AI integration patterns (client-exposed keys, unsafe output handling, excessive agency, PII→prompt, prompt injection) |
packages/compliance-checker | @guardbee/mcp-compliance-checker | KVKK/GDPR/CCPA compliance checks |
packages/dependency-auditor | @guardbee/mcp-dependency-auditor | CVE scanning for npm/pip/cargo dependencies (OSV) |
packages/dns-intelligence | @guardbee/mcp-dns-intelligence | DNS record enumeration, misconfiguration and dangling-subdomain detection |
packages/db-gateway | @guardbee/mcp-db-gateway | KVKK/GDPR-compliant gateway between an LLM and a database (PII masking, RBAC, rate limiting, queryable audit log; Prisma/Postgres/MySQL/SQLite/MongoDB adapters; optional insert/update/delete support) |
packages/mcp-server-auditor | @guardbee/mcp-server-auditor | Scans other MCP servers' tool definitions for insecure patterns (excessive agency, shell/eval/SQL/SSRF sinks, loose schemas, hardcoded secrets, wildcard CORS) |
packages/prompt-injection-scanner | @guardbee/mcp-prompt-injection-scanner | Scans RAG content/scraped pages for indirect prompt injection (instruction override, spoofed role/chat-template tokens, hidden text, "Dear AI" direct address, data-exfiltration instructions) |
packages/llm-redteam | @guardbee/mcp-llm-redteam | Actively red-teams a live LLM endpoint/chatbot with canary-based jailbreak/extraction/obfuscation probes (OpenAI/Anthropic/webhook targets) |
packages/model-scanner | @guardbee/mcp-model-scanner | Scans ML model files (PyTorch, pickle, safetensors, Keras/H5, ONNX) for supply-chain risks — dangerous pickle deserialization globals, disguised/malformed safetensors headers, Keras Lambda-layer RCE, ONNX external-data path traversal |
packages/reverse-shield | @guardbee/mcp-reverse-shield | The defensive side of reverse-engineering MCPs: audits a shipped web build or live site, Electron app, Android APK/AAB, iOS IPA, Unity/PyInstaller/Java build or native/.NET binary for what an analyst gets for free — exposed source maps, missing minification/R8/.NET obfuscation, debug info and symbols, debuggable flags, Electron fuses, missing code signing, embedded keys; A–F grade, build-config fix diffs and CI baselines |
packages/vector-store-scanner | @guardbee/mcp-vector-store-scanner | Probes vector-database endpoints (Weaviate, Qdrant, Chroma, Elasticsearch/OpenSearch, Redis, Postgres/pgvector) for unauthenticated exposure of embeddings and RAG data |
packages/prompt-leak-scanner | @guardbee/mcp-prompt-leak-scanner | Catches leaked credentials and PII (API keys, TC Kimlik No, credit cards, IBANs) in outbound LLM prompts — as MCP scan tools, and as a live reverse proxy in front of a real LLM API |
packages/document-scanner | @guardbee/mcp-document-scanner | Finds PII and credentials inside PDFs, screenshots and scanned documents — PDF text layer plus optional OCR (Turkish and English) — before they reach an LLM |
packages/agent-graph-auditor | @guardbee/mcp-agent-graph-auditor | Builds a reachability graph across multi-agent orchestration configs (LangGraph, CrewAI, AutoGen/ag2) to find transitive excessive agency — an agent that reaches a dangerous tool only through delegation to another agent |
packages/tool-poisoning-scanner | @guardbee/mcp-tool-poisoning-scanner | Scans MCP server tool definitions for tool poisoning (hidden instructions embedded in a tool's description) and confused-deputy mismatches (a read-only-sounding tool whose handler has a shell/eval/file-write/env-dump sink) |
packages/rug-pull-detector | @guardbee/mcp-rug-pull-detector | Connects live to another MCP server (stdio/HTTP), baselines its tools/list response, and detects an "MCP rug pull" — a tool's description/schema/annotations silently changing after it was already approved |
packages/memory-poisoning-scanner | @guardbee/mcp-memory-poisoning-scanner | Scans agent code for memory poisoning — untrusted input written into persistent, cross-session memory (MemGPT-style archival/core memory, or a long-term vector store) that later gets recalled and trusted as context |
packages/oauth-auditor | @guardbee/mcp-oauth-auditor | Scans an MCP server's own authorization code for OAuth 2.1 anti-patterns named in the MCP spec's Security Considerations — token passthrough, missing audience validation, OAuth/OIDC discovery SSRF, missing PKCE, loose redirect_uri validation, hardcoded client secrets |
packages/elicitation-auditor | @guardbee/mcp-elicitation-auditor | Scans MCP server code for elicitation anti-patterns in the 2026-07-28 spec — form mode asking for secrets or payment data, URL mode pointed straight at a third-party authorize endpoint, credentials or PII embedded in the elicitation URL |
packages/toxic-flow-auditor | @guardbee/mcp-toxic-flow-auditor | Audits an MCP tool catalog for toxic flows (Simon Willison's lethal trifecta) — untrusted content + sensitive/private data + exfiltration or destruction on the same server; A–F grade, KVKK-aware heuristics, OWASP MCP10:2025 |
packages/audit-gap-auditor | @guardbee/mcp-audit-gap-auditor | Audits MCP server source for OWASP MCP08:2025 (Lack of Audit and Telemetry) — missing tool-call trails, raw args/results in logs, hard-disabled audit, silent catches, audit events without correlation ids |
packages/context-oversharing-auditor | @guardbee/mcp-context-oversharing-auditor | Audits agent/MCP source for OWASP MCP10:2025 context oversharing — full conversation dumps, unscoped memory tools, shared global session stores, system-prompt leaks via tools, cross-session tool-result bleed, unfiltered vector queries (complements toxic-flow’s catalog trifecta) |
packages/owasp-scan | @guardbee/mcp-owasp-scan | Unified OWASP MCP Top 10 meta-scanner — path orchestration of GuardBee auditors + live/catalog tools/list toxic-flow/poisoning, A–F grade, SARIF; optional MCP09 Shadow MCP discover |
packages/mcp-config-auditor | @guardbee/mcp-config-auditor | Audits MCP client configs (Cursor/Claude/Windsurf/VS Code) and agent SKILL.md for unpinned packages, secrets, wildcard auto-approve, unauthenticated remotes, typosquats, cross-server/skill shadowing; discover finds Shadow MCP (OWASP MCP09) vs an org allowlist |
packages/threat-rules | @guardbee/mcp-threat-rules | MCP bridge to Agent Threat Rules (ATR) — runtime detection for prompt injection, tool poisoning, and MCP attacks, with GuardBee follow-up scanner hints |
packages/a2a-auditor | @guardbee/mcp-a2a-auditor | Scans an agent's Agent2Agent (A2A) protocol implementation (TypeScript and Python) for anti-patterns found in the reference SDKs' own source — unauthenticated push-notification webhook fetches (SSRF), Agent Cards with no authentication requirement, credentials embedded in publicly-served Agent Card metadata |
packages/slopsquat-scanner | @guardbee/mcp-slopsquat-scanner | Checks every dependency declared in a project's own manifest (package.json, requirements.txt, pyproject.toml) against the real npm/PyPI registry — flags names that don't exist at all (likely LLM-hallucinated, i.e. slopsquatting) and names that exist but were only very recently published |
packages/unbounded-consumption-auditor | @guardbee/mcp-unbounded-consumption-auditor | Scans LLM/agent application code for Unbounded Consumption ("denial of wallet", OWASP LLM Top 10 2026 #6) — missing output token limits, missing timeouts on hand-rolled LLM HTTP calls, unbounded agent tool-calling/retry loops, explicitly disabled framework safety limits (LangChain max_iterations, openai-agents max_turns), and MCP tool handlers with no visible rate limiting |
packages/secret-scanner | @guardbee/mcp-secret-scanner | Scans files for leaked secrets and API keys |
packages/security-proxy | @guardbee/mcp-security-proxy | MCP security gateway: several MCP servers behind one policy, with toxic-flow (lethal trifecta) blocking, approvals, PII masking and a hash-chained audit log |
packages/security-suite | @guardbee/security-suite | Every scanner and auditor below from one install: one MCP server with the groups you pick, and a CLI that runs any package |
packages/ssl-inspector | @guardbee/mcp-ssl-inspector | TLS certificate/cipher/protocol inspection |
packages/vulnerability-scanner | @guardbee/mcp-vulnerability-scanner | Triggers GuardBee scans, queries findings, AI-assisted remediation guidance |
packages/guard-core | @guardbee/guard-core | (internal) Shared detector library — PII/secret masking, prompt injection rules, tool classification; not an MCP server on its own |
packages/telemetry | @guardbee/mcp-telemetry | (internal) Shared usage-telemetry client — not an MCP server on its own |
Found a vulnerability? Report it privately: see SECURITY.md. Contributions are welcome: CONTRIBUTING.md.
Packages can send usage telemetry to GuardBee via @guardbee/mcp-telemetry: which tool is called, how often, and how long it takes. It is off by default (opt-in); nothing is sent unless you set GUARDBEE_TELEMETRY=1. When it is on, a one-time notice is printed to stderr on first use.
GUARDBEE_TELEMETRY=1 (or true/on/yes); unset it to turn telemetry off againtable: "users", limit: 50), success/failure, durationcontent/text/data/filter/password/email/apiKey/token, and any string longer than 40 characters — all replaced with "[redacted: ...]" by redactParams() in packages/telemetry/src/redact.ts. So the full content of scanned files/code, or the real row data from an insert_row/update_row call, is never sent.Details: packages/telemetry/README.md.
pnpm install
pnpm build # turbo run build — all packages, in dependency order
pnpm test # turbo run testTo work on a single package:
pnpm --filter @guardbee/mcp-ssl-inspector devPackages are versioned independently (Changesets). If you changed something in a PR:
pnpm changesetAfter merging to main, CI automatically opens a version PR; merging that PR publishes the changed packages to npm (see .github/workflows/release.yml).
Packages at 1.0 or later follow semantic versioning: a breaking change to the CLI, the MCP tool names and parameters, the config format or the exported API comes only with a new major version, and is listed in the package's CHANGELOG.md. New rules and detectors arrive in minor versions; they can report findings an earlier version did not. Packages still at 0.x may change between minor versions.
| Package | Stable since |
|---|---|
@guardbee/mcp-security-proxy | 1.0 |
@guardbee/guard-core | 1.0 |
@guardbee/mcp-secret-scanner | 1.0 |
@guardbee/mcp-prompt-injection-scanner | 1.0 |
@guardbee/mcp-prompt-leak-scanner | 1.0 |
@guardbee/mcp-toxic-flow-auditor | 1.0 |
packages/*, real workspace:* dependencies (e.g. security-suite depends on the other packages directly from the workspace, not a registry version)build/test/type-check pipeline, dependency-graph-aware ordering and cachingtsconfig.base.json and vitest.shared.ts at the root; each package layers its own settings on topThe monorepo's earlier write-ups are in CHANGELOG.md; each package's release notes are in its own CHANGELOG.md and on GitHub Releases.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/guardbee-mcp to learn what the "Guardbee Mcp" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npx -y @guardbee/mcp-security-proxy@^1 init --client claude-desktop # or cursor, claude-code
npx -y @guardbee/mcp-owasp-scan scan . --fail-on=high| Name | What it does |
|---|---|
owasp_scan_path | Run a unified OWASP MCP Top 10 scan over a filesystem path — orchestrates secret, server, oauth, audit-gap, context-oversharing, toxic-flow, and tool-poisoning auditors; returns A–F grade. |
owasp_scan_live | Connect to a live MCP server (stdio or HTTP), call tools/list, then grade toxic-flow + tool-poisoning (MCP03/MCP10). |
owasp_scan_catalog | Audit a tools/list JSON dump for toxic flows and tool-description poisoning (MCP03/MCP10). |
list_owasp_coverage | List OWASP MCP Top 10 categories and which GuardBee scanners cover them in this meta-scan |
Read live from the server on October 22, 2026.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/guardbee-mcp)Nothing comparable is listed yet.
@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notes@guardbee/[email protected]Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "guardbee-mcp" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.