Agent Graph Auditor MCP server
Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs
1 stars567 downloads/wk
Reviews
Write oneNobody has reviewed Agent Graph Auditor yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agent Graph Auditor tools (4)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
list_patternsList every dangerous-capability rule this auditor looks for at the end of a delegation path, grouped by category
scan_directoryRecursively scan a directory of Python files and report excessive-agency paths found in each. Each file's agent/tool graph is analyzed independently — variable references don't resolve across files, so a Crew/GroupChat whose members are defined in a different file than the assembling call won't be connected.
scan_fileScan a single Python file for excessive-agency paths across LangGraph/CrewAI/AutoGen orchestration constructs
scan_textScan a Python snippet defining a multi-agent orchestration (LangGraph, CrewAI, or AutoGen/ag2) for excessive agency reachable through delegation or group membership — an agent with no dangerous tool of its own that can still reach one (shell/code-exec/file-write/network/credentials) through another agent it can hand off to.
Public scan report
scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it
- Code scan23 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identitynamespace and repository owner differ4/10
Install Agent Graph Auditor in Claude Code, Cursor or VS Code
Runs npx -y @guardbee/mcp-agent-graph-auditor on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add agent-graph-auditor -- npx -y @guardbee/mcp-agent-graph-auditor
What the publisher says
From the Agent Graph Auditor repository's README, as published. We do not edit it. Read it on GitHub
guardbee-mcp
🇬🇧 English | 🇹🇷 Türkçe | 🇨🇳 中文
guardbee.ai — AI Security Copilot for websites.
GuardBee's family of MCP (Model Context Protocol) servers — a single monorepo, independent npm packages.
Packages
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Agent Graph Auditor: common questions
- Is Agent Graph Auditor MCP server safe?
- Yes, by our scan: it is graded A (86/100). Read the Agent Graph Auditor safety report
- How do I install Agent Graph Auditor?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Agent Graph Auditor need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Agent Graph Auditor maintained?
- The last commit was 12 days ago (2026-10-01). The latest release is v0.1.2.
- What can I use instead of Agent Graph Auditor?
- Servers from other publishers that do the same job: LLM Sandbox MCP server, Google Surf MCP server and MCP AutoMem MCP server. Compare all Agent Graph Auditor alternatives.
Alternatives to Agent Graph Auditor
Same job from other publishers: the closest match first, then the best rated.
- LLM SandboxSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends.not reviewedWidely usedA
- Google SurfWeb, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.not reviewedEstablishedB
- MCP AutoMemGraph-vector memory for AI assistants using FalkorDB and Qdrantnot reviewedEstablishedC
- SkillsmithShare agent skills across your team, scan them for risk, and track what's actually used.not reviewedEstablishedB
- Total Agent MemoryPersistent local memory for coding agents: temporal knowledge graph, procedural and episodic recallnot reviewedEstablishedA