Other · Local MCP server

Agent Graph Auditor

Finds transitive excessive agency across LangGraph/CrewAI/AutoGen orchestration graphs.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.4hmetuyar/agent-graph-auditor
Version
0.1.2
Status
Active
Category
other
Transport
stdio (local process)
Package
npm
Published
2026-09-28
Updated
2026-09-28
Publisher
4hmetuyar (GitHub) · 26 servers with pages here
Repository
github.com/GuardBee/guardbee-mcp (folder packages/agent-graph-auditor)
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
npm@guardbee/mcp-agent-graph-auditor0.1.2stdioNone declared

How to connect Agent Graph Auditor

Agent Graph Auditor runs locally from a Node.js package published to the npm registry: @guardbee/mcp-agent-graph-auditor version 0.1.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @guardbee/mcp-agent-graph-auditor@0.1.2.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "agent-graph-auditor": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-agent-graph-auditor@0.1.2"
      ]
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from 4hmetuyar (GitHub)

All 26 →
ServerRunsEndpoint or package
A2a AuditorScans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure.Local · stdionpm: @guardbee/mcp-a2a-auditor
Ai Code ScannerScans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection.Local · stdionpm: @guardbee/mcp-ai-code-scanner
Compliance CheckerKVKK/GDPR/CCPA compliance checks for codebases.Local · stdionpm: @guardbee/mcp-compliance-checker
Db GatewayKVKK/GDPR-compliant LLM-to-database gateway: PII masking, RBAC, rate limiting, audit log.Local · stdionpm: @guardbee/mcp-db-gateway
Dependency AuditorCVE scanning for npm/pip/cargo dependencies via OSV.Local · stdionpm: @guardbee/mcp-dependency-auditor
Dns IntelligenceDNS record enumeration, misconfiguration and dangling-subdomain detection.Local · stdionpm: @guardbee/mcp-dns-intelligence
Elicitation AuditorMCP elicitation anti-patterns: secrets in forms, third-party authorize URLs, credentials in URLs.Local · stdionpm: @guardbee/mcp-elicitation-auditor
Llm RedteamActive jailbreak/extraction/obfuscation red-teaming for live LLM endpoints.Local · stdionpm: @guardbee/mcp-llm-redteam
MCP Config AuditorScans Cursor/Claude/Windsurf/VS Code MCP configs for unpinned versions, secrets, typosquats.Local · stdionpm: @guardbee/mcp-config-auditor
MCP Server AuditorScans MCP server tool definitions for excessive agency, injection sinks, hardcoded secrets.Local · stdionpm: @guardbee/mcp-server-auditor
Memory Poisoning ScannerScans agent code for untrusted input poisoning persistent cross-session memory.Local · stdionpm: @guardbee/mcp-memory-poisoning-scanner
Model ScannerScans ML model files (PyTorch, safetensors, Keras, ONNX) for supply-chain risks.Local · stdionpm: @guardbee/mcp-model-scanner

More other servers

All 6,730 →
ServerRunsEndpoint or package
Agent FactoryDeterministic, receipted digital microservices. Gate A is simulation-only.Remote · HTTPagent-factory-gateway-production.up.railway.app
Agent Firewall MCPInput/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.Local · stdionpm: agent-firewall-mcp
Agent First ListingAgent-first product listing: JSON catalog, agent card, MCP door, hops, measured landings.Remote · HTTPagent-observatory-sensor.nolimit-observatory.workers.dev
Agent GateLocal mandate gate and proof trail for AI agents that take consequential actions.Local · stdionpm: forge-agent-gate
Agent GuardSafety checks an agent runs before it acts: package malware, destructive command, secret leak.Local · stdioPyPI: agent-tripwire
Agent GuardrailDeterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.Local · stdioPyPI: guardrail-mcp
Agent Hive OrchestratorDeterministic nested hive-mind orchestration over the A2A rails: hire N solvers, adversarial cross-r.Remote · HTTPmcp.viridisconservation.com
Agent Hops For Your SiteHops are 302s an agent followed to your site. Count them, attribute them, grow them.Remote · HTTPagent-observatory-sensor.nolimit-observatory.workers.dev