evil-mcp-server

Provides a Model Context Protocol (MCP) server (stdio or HTTP mode) with tools intended for security red-team testing. The README describes a tool, record_analytics, that simulates exfiltration/analytics behavior for security demonstrations.

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ Security mcp security-testing red-team tooling exfiltration-simulation nodejs express typescript
⚙ Agent Friendliness
45
/ 100
Can an agent use this?
🔒 Security
25
/ 100
Is it safe for agents?
⚡ Reliability
22
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
50
Documentation
55
Error Messages
0
Auth Simplicity
100
Rate Limits
0

🔒 Security

TLS Enforcement
40
Auth Strength
10
Scope Granularity
0
Dep. Hygiene
55
Secret Handling
30

Security risk profile is intentionally focused on malicious simulation. README warns against production use and real customer data. No auth is documented, increasing risk if reachable by untrusted parties. TLS/transport security is not described. An optional webhook URL environment variable exists, but the handling/validation/logging behavior is not documented.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
30
Error Recovery
20
AF Security Reliability

Best When

Used in isolated test environments with synthetic data and explicit authorization.

Avoid When

Avoid exposing it to untrusted networks/users or using real sensitive data; avoid production use entirely.

Use Cases

  • Red-team exercise tooling for demonstrating data exfiltration patterns
  • Security awareness/training simulations
  • Testing agent/tooling behavior in a controlled environment

Not For

  • Production environments
  • Handling real customer data
  • Any scenario where simulated exfiltration could be misused outside an approved test environment

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication mechanism is described for either stdio MCP mode or the HTTP endpoints (/health, /tools, /tools/call).

Pricing

Free tier: No
Requires CC: No

As an npm package, pricing is not specified; it appears to be self-hosted.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • No authentication described for HTTP endpoints; agents may call tools without access controls if exposed.
  • Only a small set of endpoints/tools are documented; tool argument schemas and error behaviors are not fully specified in the README.
  • HTTP tool execution uses a generic /tools/call pattern; agents must supply correct tool name and argument structure.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for evil-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered