Agent MCP Server

AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

Local serverstdioPython

What is the Agent MCP server?

Agent MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening.

What you get

Adaptive threat intelligence for AI agent security: semantic memory, multi-turn escalation, output scanning, rate limiting, and prompt hardening — designed to complement deterministic governance stacks (e.g. Microsoft Agent OS), not replace them.

What the assistant can call

Once Agent is connected, these are the calls the assistant has available:

  • Transport — When to use
  • sse — HTTP clients that expect the legacy SSE MCP transport (--port binds 127.0.0.1)
  • Capability — Rule-only (typical)
  • Dataset — Rows
  • Combined — 823
  • Stage — Learned
  • Script — What it shows
  • Project — Focus
  • AgentSeal — Red-team / MCP audit
  • Observability — metrics = MetricsCollector() immune = AdaptiveImmuneSystem(metrics=metrics) immune.assess("some text") print(metrics.snapshot())

Setting it up

agent-immune on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Choosing this one

Among the monitoring and observability options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agent's toolset — Transport, sse, Capability and 7 more — is a fair guide to whether it matches your workflow. It is maintained by denial-web; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agent.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the agent mcp server does with a few real requests.

Available tools

ToolWhat it does
TransportWhen to use
sseHTTP clients that expect the legacy SSE MCP transport (--port binds 127.0.0.1).
CapabilityRule-only (typical)
DatasetRows
Combined823
StageLearned
ScriptWhat it shows
ProjectFocus
AgentSealRed-team / MCP audit
Observabilitymetrics = MetricsCollector() immune = AdaptiveImmuneSystem(metrics=metrics) immune.assess("some text") print(metrics.snapshot())

How to install the Agent MCP server

{
  "mcpServers": {
    "agent-immune": {
      "command": "uvx",
      "args": ["agent-immune"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Agent to Transport.
  • Use Agent to sse.
  • Use Agent to Capability.

Frequently asked questions

It connects Agent to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (Transport, sse, Capability, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agent directly.