@guardbee/mcp-agent-graph-auditor

MCPcommunity
v0.1.2io.github.4hmetuyarMITUpdated 14d agonpmGitHub

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

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
72Downloads/wk
1GitHub stars
1Forks
14d agoLast update
Package
Authorio.github.4hmetuyar
LicenseMIT
Version0.1.2
Sourcenpm+mcp-registry
npm@guardbee/mcp-agent-graph-auditor
GitHubGuardBee/guardbee-mcp
SBOMCycloneDX 1.6 ↓
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/20
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
—npm Trusted Publishing (Sigstore)+0/5
→ Publish from GitHub Actions with --provenance so the attestation binds this package to this repo
—npm maintainer match+0/5
→ Earned once your identity is verified above and that login is an npm maintainer of this package
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface4 tools · none privileged
Security scan✓ Cleanv0.1.2 · 2d agoHow well does this scan work?
EvalsNone
IndexedOct 9, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

4 tools · none privileged
Statically extracted from the published packagev0.1.2 · 2d ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

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…

Scan 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…

No input schema was published for this tool.

scan_fileScan a single Python file for excessive-agency paths across LangGraph/CrewAI/AutoGen orchestration constructs

Scan a single Python file for excessive-agency paths across LangGraph/CrewAI/AutoGen orchestration constructs

No input schema was published for this tool.

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…

Recursively 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…

No input schema was published for this tool.

list_patternsList every dangerous-capability rule this auditor looks for at the end of a delegation path, grouped by category

List every dangerous-capability rule this auditor looks for at the end of a delegation path, grouped by category

No input schema was published for this tool.

4 of 4 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

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

Keywords
mcp
Alternatives
Comparing tool surfaces…

Tools exposed

4 tools · none privileged · observed by static extraction. A tool surface is what one scan read on one day, not a live capability list.

Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.

Dependency tree

What one Forge scan resolved from npm metadata on 2026-10-10 — observed resolution, not a publisher declaration.

60 packages resolved · 3 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

The crawl stopped at the depth-4 limit. Anything below that level was never resolved.

The crawl stopped at the 60-package limit. The rest of the tree was never resolved.

36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)

Declared but not resolved

55 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.

+43 more not listed. The counts by reason above cover all of them.

Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.