ledd-mcp-audit-server

MCPattested
v3.0.1Ledd ConsultingMITUpdated 1mo agonpmGitHub

MCP server interface for AI agent and MCP security auditing — config analysis, trust audits, prompt injection testing, tool probing, and data flow tracing

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.

Attested build
A verified provenance attestation binds this artifact to the listed repository. Nobody has claimed the listing yet — this proves where the code was built, not who stands behind it.
43Downloads/wk
1mo agoLast update
Needs 1 credential before it runs
  • AGENT_SECURITY_API_KEYAPI keyrequired

    API key for the managed hosted audit backend

Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.

Package
AuthorLedd Consulting
LicenseMIT
Version3.0.1
Sourcenpm+mcp-registry
npmledd-mcp-audit-server
GitHubjoepangallo/mcp-audit-server
SBOMCycloneDX 1.6 ↓
Trust Status
A
85/100Trusted
✓Listed in Forge index+10/10
✓Identity verified · attested build+20/20
—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)+5/5
—npm maintainer match+0/5
→ Publisher: add the verified GitHub login to the npm package's maintainers (npm owner add <login>)
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusIdentity verified
PublisherUnverified
SignatureUnsigned
Domain—
Provenance✓ Sigstore-verified · 20babf3
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface10 tools · none privileged
Security scan✓ Cleanv3.0.1 · 1mo agoHow well does this scan work?
PROMPTtool:harden_system_promptReferences the system prompt
EvalsNone
IndexedAug 26, 2026

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

Tools

10 tools · none privileged
Statically extracted from the published packagev3.0.1 · 1mo 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.

audit_mcp_configPerform static analysis on raw MCP config JSON and identify privilege, auth, transport, and launch risks.

Perform static analysis on raw MCP config JSON and identify privilege, auth, transport, and launch risks.

No input schema was published for this tool.

audit_mcp_serverLaunch a target MCP server over stdio, enumerate tools, and run active security probes against its exposed tools. Requires AGENT_SECURITY_ADMIN_MODE=1.

Launch a target MCP server over stdio, enumerate tools, and run active security probes against its exposed tools. Requires AGENT_SECURITY_ADMIN_MODE=1.

No input schema was published for this tool.

audit_agent_trustAudit an MCP or agent deployment for tool-permission inventory, execution provenance coverage, secret exposure controls, policy drift, and an overall trust score.

Audit an MCP or agent deployment for tool-permission inventory, execution provenance coverage, secret exposure controls, policy drift, and an overall trust score.

No input schema was published for this tool.

audit_prompt_injectionPerform a static prompt-hardening review against a 30+ payload prompt-injection catalog.

Perform a static prompt-hardening review against a 30+ payload prompt-injection catalog.

No input schema was published for this tool.

audit_agent_dataflowInfer tagged-data exposure and exfiltration paths from MCP config and observed tool capabilities.

Infer tagged-data exposure and exfiltration paths from MCP config and observed tool capabilities.

No input schema was published for this tool.

scan_mcp_packageScan an npm MCP package for dependency vulnerabilities, dangerous patterns, and permission issues.

Scan an npm MCP package for dependency vulnerabilities, dangerous patterns, and permission issues.

No input schema was published for this tool.

generate_reportCombine multiple stored audit jobs into a composite report with deduplicated findings and an executive summary.

Combine multiple stored audit jobs into a composite report with deduplicated findings and an executive summary.

No input schema was published for this tool.

fix_mcp_configAuto-remediate security issues in an MCP config: remove unsafe flags, strip shell wrappers, upgrade transport to TLS, redact inline secrets, add auth placeholders, and constrain filesystem scope.

Auto-remediate security issues in an MCP config: remove unsafe flags, strip shell wrappers, upgrade transport to TLS, redact inline secrets, add auth placeholders, and constrain filesystem scope.

No input schema was published for this tool.

harden_system_promptAnalyze a system prompt for injection vulnerabilities and return a hardened version with security guardrails appended.

Analyze a system prompt for injection vulnerabilities and return a hardened version with security guardrails appended.

NOTEReferences the system promptAnalyze a system prompt for injection vulnerabilities and return a harden

No input schema was published for this tool.

generate_policyGenerate a JSON security policy from an MCP config that can be enforced by a proxy or middleware.

Generate a JSON security policy from an MCP config that can be enforced by a proxy or middleware.

No input schema was published for this tool.

10 of 10 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

MCP server interface for AI agent and MCP security auditing — config analysis, trust audits, prompt injection testing, tool probing, and data flow tracing

Keywords
mcpsecurityauditai-agentprompt-injectionmcp-serverllm-security
Alternatives
Comparing tool surfaces…

Tools exposed

10 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 2026-08-29 — observed resolution, not a publisher declaration.

60 packages resolved · 1 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

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

+41 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.

Topics

Related in security