Mmcp.market

MCP Safety Warden MCP server

by gautamvarmadatla·io.github.gautamvarmadatla/mcpsafetywarden·v1.4.18
No reviews yet

MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.

B80/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B80/100

full report

Adoption
Growing

8 stars107 downloads/wk

Reviews

Write one

Nobody has reviewed MCP Safety Warden yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

MCP Safety Warden tools (25, 4 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • analyze_cve_blast_radius

    Report CVEs that affect multiple servers, showing the blast radius across the client's workspace.

  • check_server_drift

    Detect tool schema and tool-list changes since the last inspect_server baseline.

  • discover_servers

    Scan the local machine for MCP servers configured in known MCP client apps.

  • explain_client_risk

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

  • explain_tool_risk

    Walk the risk graph for a specific tool and return blast radius, risk paths, and recommended action.

  • export_graph

    Export the risk graph in the requested format.

  • get_retry_policy

    Get the recommended retry policy for a tool: max retries, backoff strategy, and suggested timeout.

  • get_risk_graph

    Return the inventory graph of MCP servers, tools, security findings, and their relationships.

  • get_run_historywrite action

    Get recent execution history for a tool: timestamps, latency, success/fail, and injection warnings.

  • get_security_scan

    Retrieve the latest stored security scan report for a server.

  • get_tool_profile

    Get the full raw behavior profile for a tool with all observed metrics and confidence scores.

  • inspect_server

    Re-connect to a registered server, enumerate its tools, classify each one, and update stored profiles.

  • list_server_tools

    List all known tools for a server with summarized risk profiles (effect class, retry safety, risk level).

  • list_servers

    List all registered servers with transport type and tool count.

  • onboard_discovered_servers

    Register previously discovered servers into the Safety Warden pipeline (register + inspect).

  • onboard_server

    One-shot server onboarding: register + inspect + security scan in a single call.

  • ping_server

    Check if a registered server is reachable. Returns status and round-trip latency.

  • preflight_tool_call

    Get a risk assessment for a tool WITHOUT executing it.

  • register_server

    Register a server so it can be wrapped, profiled, and called via safe_tool_call. Prefer onboard_server for a single trusted server - it does register + security scan + inspect in one call. Use register_server directly only when you want to control the steps separately.

  • run_replay_testwrite action

    Test idempotency by calling a tool TWICE with identical args and comparing outputs.

  • safe_tool_callwrite action

    Execute a tool through the safety proxy. This is the ONLY correct way to call tools on registered servers. Do NOT call preflight_tool_call before this - preflight runs automatically inside.

  • scan_all_serverswrite action

    Run the MCPSafety 5-stage security pipeline against all registered servers in one call.

  • security_scan_server
  • set_tool_policy

    Set a permanent execution policy for a tool, overriding the normal preflight flow.

  • suggest_safer_alternative

    Find lower-risk alternatives to a tool on the same server, ranked by risk reduction.

Public scan report

scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it

1 medium
  • Code scan45 source files scanned20/25
  • –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 43 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    mcpsafetywarden-1.4.18/mcpsafetywarden/scan/args.py: …rpreter invocations (python -c, eval(), exec(), __import__) embedded in args …
Overall 80/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the MCP Safety Warden repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.gautamvarmadatla/mcpsafetywarden -->

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.

Contents

  • Overview
  • Prerequisites
  • Installation
  • Configuration
  • MCP Integration
  • CLI Reference
  • Auxiliary Integrations
  • Development
  • Testing
  • Further reading

[!IMPORTANT]

MCP security is an active research area. Recent surveys catalog a lot of protocol-specific threat categories spanning tool poisoning, prompt injection, rug-pull attacks, supply chain compromise, credential exfiltration, and composition attacks across the full server lifecycle. See Securing the MCP (OpenReview), Landscape & Threats (arXiv), When MCP Servers Attack (arXiv), and MCP-38 Taxonomy (arXiv).

Overview

Use as a proxy to add safety gating to any MCP server, or point it at a server you don't own and run a full security audit without making a single tool call.

Fig 1. Two operating modes: proxy and audit

Behavioral profiling: Effect class, retry safety, destructiveness. LLM-assisted (Anthropic, OpenAI, Gemini, Ollama) with rule-based fallback. Observed stats (latency p50/p95, failure rate, output size) updated after every proxied call.

Security scanning: mcpsafety+ five-stage pipeline (Recon, Planner, Hacker, Auditor, Supervisor). Cisco AI Defense (AST/YARA). Snyk (metadata analysis). Kali and Burp Suite integrations enrich the pipeline with real network data and HTTP-layer probes. Source code scanning from GitHub with entropy, AST, taint flow, and rug-pull detection.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add mcpsafetywarden -- uvx mcpsafetywarden
Add to Cursor

MCP Safety Warden: common questions

Is MCP Safety Warden MCP server safe?
Mostly: it is graded B (80/100). Read the MCP Safety Warden safety report
How do I install MCP Safety Warden?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does MCP Safety Warden need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is MCP Safety Warden maintained?
The last commit was 43 days ago (2026-08-12). The latest release is v1.4.18.
What can I use instead of MCP Safety Warden?
Servers from other publishers that do the same job: MCPProxy MCP server, Draugr MCP server and Npm Sentinel MCP server. Compare all MCP Safety Warden alternatives.

Alternatives to MCP Safety Warden

Same job from other publishers: the closest match first, then the best rated.

All MCP Safety Warden alternatives →
  • MCPProxy
    Local-first MCP proxy with BM25 tool discovery, security scanning, quarantine & ~99% token savings
    B
  • Draugr
    Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
    A
  • Npm Sentinel
    Advanced NPM analysis: Recursive security scanning, ecosystem awareness, and deep insights.
    A
  • MobiLoop
    Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.
    A
  • Nel Veil
    Free passive security scanning - check any domain's DMARC, TLS, headers, and exposures.
    A
MCP Safety Warden vs MCPProxyMCP Safety Warden vs DraugrMCP Safety Warden vs Npm Sentinel

More from gautamvarmadatla →