Claude Marketplaces
SkillsMCP serversMarketplacesPluginsDigestAdvertise
Submit

LLMond Highlights

This week in Claude is LLMond Highlights now. A weekly email, free.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Plugins
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index
  • Plugin index

Site

  • About
  • Submit
  • Advertise
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
by Mert Düzgün
MCP servers/Security & Pentesting
gautamvarmadatla avatar

MCP Safety Warden

gautamvarmadatla/mcpsafetywarden

A proxy layer that sits between Claude and any MCP server to scan tool calls before they execute. It runs behavioral profiling on every tool (effect class, destructiveness, retry safety), checks arguments for 20+ injection patterns including SSRF and path traversal, scans outputs for prompt injection attempts, and gates risky calls with alternatives. The security audit mode pulls source from GitHub and runs entropy scanning, AST taint analysis, and Bandit checks without making live calls. Integrates with Cisco AI Defense, Snyk, Kali Linux MCP for network recon, and Burp Suite MCP for HTTP probing. Tracks drift by hashing server source on first scan and alerts on schema or implementation changes. Useful when wrapping third-party servers or hardening your own tools against composition attacks and credential leakage.

GitHub stars
8
tools
25
transport
STDIO
last updated
Nov 13, 2026
View on GitHubSave

Tools

25 tools

Public tool metadata for what this MCP can expose to an agent.

onboard_serverRegister + inspect + security scan in one call

Register + inspect + security scan in one call

No parameter schema in public metadata yet.

register_serverRegister a server; optionally auto-inspect

Register a server; optionally auto-inspect

No parameter schema in public metadata yet.

inspect_serverRefresh tool list and profiles

Refresh tool list and profiles

No parameter schema in public metadata yet.

check_server_driftDetect schema and tool-list drift against stored baseline

Detect schema and tool-list drift against stored baseline

No parameter schema in public metadata yet.

list_serversList all registered servers

List all registered servers

No parameter schema in public metadata yet.

list_server_toolsList tools on a server with summary profiles

List tools on a server with summary profiles

No parameter schema in public metadata yet.

preflight_tool_callRisk assessment without execution

Risk assessment without execution

No parameter schema in public metadata yet.

safe_tool_callExecute with risk gating and alternatives

Execute with risk gating and alternatives

No parameter schema in public metadata yet.

get_tool_profileFull behavior profile with observed stats

Full behavior profile with observed stats

No parameter schema in public metadata yet.

get_retry_policyRetry and timeout recommendations

Retry and timeout recommendations

No parameter schema in public metadata yet.

suggest_safer_alternativeLLM-ranked safer substitutes

LLM-ranked safer substitutes

No parameter schema in public metadata yet.

run_replay_testIdempotency test (calls tool twice)

Idempotency test (calls tool twice)

No parameter schema in public metadata yet.

security_scan_serverLive security audit (mcpsafety+, Cisco, Snyk)

Live security audit (mcpsafety+, Cisco, Snyk)

No parameter schema in public metadata yet.

scan_all_serversmcpsafety+ pipeline across all registered servers

mcpsafety+ pipeline across all registered servers

No parameter schema in public metadata yet.

get_security_scanLatest stored scan report

Latest stored scan report

No parameter schema in public metadata yet.

set_tool_policyPermanent allow/block policy for a tool

Permanent allow/block policy for a tool

No parameter schema in public metadata yet.

get_run_historyRecent execution history for a tool

Recent execution history for a tool

No parameter schema in public metadata yet.

ping_serverReachability check with latency

Reachability check with latency

No parameter schema in public metadata yet.

discover_serversScan filesystem for MCP client configs and extract server entries

Scan filesystem for MCP client configs and extract server entries

No parameter schema in public metadata yet.

onboard_discovered_serversRegister discovered servers in bulk

Register discovered servers in bulk

No parameter schema in public metadata yet.

get_risk_graphBuild or query the inventory risk graph (servers, tools, findings, agent clients)

Build or query the inventory risk graph (servers, tools, findings, agent clients)

No parameter schema in public metadata yet.

explain_tool_riskWalk risk paths for a tool: blast radius, composition risks, MITRE tags, recommended action

Walk risk paths for a tool: blast radius, composition risks, MITRE tags, recommended action

No parameter schema in public metadata yet.

explain_client_riskAnalyze cross-server risks for all servers under one agent client

Analyze cross-server risks for all servers under one agent client

No parameter schema in public metadata yet.

analyze_cve_blast_radiusReport CVEs affecting multiple servers under the same client

Report CVEs affecting multiple servers under the same client

No parameter schema in public metadata yet.

export_graphExport risk graph as JSON or Mermaid diagram

Export risk graph as JSON or Mermaid diagram

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Readme

MCP Safety Warden

MCP safety warden is a proxy server that wraps any MCP server and adds behavioral profiling, security scanning, risk gating, and safe execution to its tools.


View the full README on GitHub

Details

Repository
github.com/gautamvarmadatla/mcpsafetywarden
Category
Security & Pentesting
Package
mcpsafetywarden
Transport
STDIO
Registry
MCP registry, active

Related Security & Pentesting MCP servers

View all
1bawbel avatarBawbel Scannerbawbel/scannerSecurity scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.7stars
2stackhawk avatarStackhawkstackhawk/stackhawk-mcpAn MCP server that provides interaction with StackHawk's security scanning platform.7stars
3tb0hdan avatarWass Mcptb0hdan/wass-mcpMCP server for web application security scanning7stars
4claytono avatarGo Unifi Mcpclaytono/go-unifi-mcpManage UniFi sites, devices, clients, networks, port forwarding, DNS, and firewall6stars
5goklab avatarGuardvibegoklab/guardvibeDeterministic security layer your AI can't be. 669 rules, 39 tools, CLI + doctor + host audit.6stars
6vouchlyai avatarPincervouchlyai/pincer-mcpSecure grip for your agent's secrets - security-hardened MCP gateway with proxy token architecture6stars