agent-safety-mcp

v1.0.0APIsstable

Unified MCP safety server that detects prompt injection (75 patterns), scans LLM outputs for leaked secrets/PII, enforces API cost budgets, and creates signed audit trails. Zero ML dependencies, pure Python.

agent-safetymcpai-integration
Share:
0
Stars
0
Downloads
0
Weekly
0/5

About

Unified MCP safety server that detects prompt injection (75 patterns), scans LLM outputs for leaked secrets/PII, enforces API cost budgets, and creates signed audit trails. Zero ML dependencies, pure Python.

Features

  • Unified MCP safety server that detects prompt injection (75

Use Cases

Unified MCP safety server that detects prompt injection (75 patterns), scans LLM
LuciferForge

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.0
UpdatedN/A
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx agent-safety

Examples

No examples available for this server.

Configuration

Configuration Details

Config File

claude_desktop_config.json

Web UI

Not available

Security

Authentication

RequiredNo

Features

Data Encryption
Audit Logging
RBAC Support

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

More APIs MCP Servers

Explore other servers in the APIs category.

Quick Config Preview

{ "mcpServers": { "agent-safety": { "command": "npx", "args": ["-y", "agent-safety"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use agent-safety-mcp?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides