What does “zero false positives on benchmarks” mean?
On the benchmarks used in testing, no legitimate inputs were incorrectly flagged as threats, ensuring low friction for normal agent operation.
Agent Immune MCP Server
@denial-web
基本信息
关于 Agent Immune MCP Server
Adaptive security toolkit for AI agents. Assess inputs for prompt injection, scan outputs for credential/PII leaks, teach new attack patterns to semantic memory, harden prompts with role-lock and sandboxing, and monitor metrics — all locally via MCP. Zero false positives on bench
Agent Immune MCP Server 配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"agent-immune": {
"command": "python",
"args": [
"-m",
"agent_immune",
"serve",
"--transport",
"stdio"
]
}
}
}Agent Immune MCP Server 工具
5score text for prompt injection threats
scan output for credentials, PII, and exfiltration
teach new attack patterns to semantic memory
apply role-lock, sandboxing, and output guards
observability snapshot (counts, latency)
概览
What is Agent Immune?
Agent Immune is an adaptive security toolkit for AI agents that runs locally via the Model Context Protocol (MCP). It provides tools to assess inputs and outputs for threats, learn new attack patterns, harden prompts, and expose observability metrics, targeting developers building secure AI agent workflows.
How to use Agent Immune?
Install it with pip install 'agent-immune[mcp]' and serve it via python -m agent_immune serve --transport stdio. Once running, an MCP host can invoke its five tools: assess_input, assess_output, learn_threat, harden_prompt, and get_metrics.
Key features of Agent Immune
- Zero false positives on benchmark evaluations.
- 179 automated tests with 94% code coverage.
- Semantic memory catches rephrased attacks that bypass regex.
- Provides prompt hardening via role-lock, sandboxing, and output guards.
- Observability snapshot through
get_metricstool. - Licensed under Apache-2.0.
Use cases of Agent Immune
- Detect prompt injection threats in user-supplied text before it reaches the AI agent.
- Scan agent outputs for credentials, PII, and data exfiltration.
- Teach the system new attack patterns on the fly to adapt to emerging threats.
- Harden agent prompts with role-lock and sandboxing guards to prevent misuse.
- Monitor security metrics and latency through the observability snapshot.
常见问题
How does Agent Immune differ from simple regex-based filters?
Agent Immune uses semantic memory that can recognize rephrased or novel attack patterns, whereas static regex rules often miss variations and produce false negatives.
Is Agent Immune a cloud service?
No. It runs entirely locally via the MCP protocol; no data is sent to external servers unless the user explicitly configures it.
What transport does Agent Immune use?
The server is started with `--transport stdio`, so it communicates over standard input/output with the MCP host.
What are the runtime dependencies?
The package is installed via pip and requires Python. The `agent-immune[mcp]` extra pulls in MCP dependencies, and the tool operates as a standard Python process.
AI 与智能体 分类下的更多 MCP 服务器
TruVerifAI Panel-review
TruVerifAITruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g
1
L
Legion MCP
faulkjMCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
1
OpenZiti MCP Gateway
openzitiNetFoundry MCP Gateway enables secure, isolated access to Model Context Protocol (MCP) tools across distributed systems without exposing public endpoints. Zero trust gateway for MCP servers. Aggregate, filter, and secure
48
AON — Agent Offer Network
AONAON MCP connects AI agents to real, buyable products and services with live pricing and tracked links—enabling builders to earn developer revenue share from attributed clicks and conversions.
2
Plainpaper
PlainpaperThe AI marketing canvas for Claude and MCP agents. Your agent drafts campaigns as cards on a shared board, briefed by your brand rules, approved by you.
评论