fan-manager 1.3.0

Dell PowerEdge Fan Manager + MCP Server + A2A Agent

Fan Manager

CLI | MCP | Agent

Version: 1.3.0

Documentation — Installation, deployment, and usage across the CLI and MCP interfaces, plus the integrated A2A agent server, are maintained in the official documentation.

---

Overview

Fan Manager controls the fan speed of Dell PowerEdge servers based on CPU temperature. It is a local tool: it reads temperatures via lm-sensors (sensors -j) and drives the server's BMC via ipmitool raw commands. It ships as a CLI, a Model Context Protocol (MCP) server, and an integrated A2A agent for the agent-utilities ecosystem.

Because fan control happens against the local host, no service URL or token is required — the connector degrades to a no-op/local config for authentication.

---

Key Features

• Temperature-Driven Curve: Logarithmic CPU-temperature-to-fan-speed scaling with configurable min/max bounds and intensity.
• Consolidated Action-Routed MCP Tools: Two togglable tool modules (temperature, fan-control) minimize token overhead in LLM contexts.
• Fail-Safe Defaults: On a temperature read error during automatic control, the fans default to maximum.
• Integrated Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and Web UI (AG-UI).

---

CLI

The classic continuous service that polls temperature and adjusts the fans:

fan-manager --intensity 5 --cold 50 --warm 80 --slow 5 --fast 100 --poll-rate 24

Flag	Meaning
-i, --intensity	Temperature power intensity (scales logarithmically, 0-10)
-c, --cold	Minimum temperature for fan scaling (°C)
-w, --warm	Maximum temperature for fan scaling (°C)
-s, --slow	Minimum fan speed (0-100)
-f, --fast	Maximum fan speed (0-100)
-p, --poll-rate	Temperature poll rate in seconds

Requires ipmitool and lm-sensors installed on the host, and privileges to issue raw IPMI commands to the BMC.

---

MCP

This server uses dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

Tool Module	Toggle Env Var	Enabled by Default	Description & Nested Methods
Temperature	TEMPERATURETOOL	True	Read CPU/sensor temperature (CONCEPT:FAN-001). Action-routed methods: get, get_core.
Fan Control	FANCONTROLTOOL	True	Control fan speed via IPMI (CONCEPT:FAN-002). Action-routed methods: set, auto.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime, so you can restrict the exposed tools and avoid blowing up the LLM's context window. Configure filtering via:

• CLI Arguments: --tools / --toolsets (and --disabled-tools / --disabled-toolsets).
• Environment Variables: MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS, MCP_ENABLED_TAGS / MCP_DISABLED_TAGS.
• HTTP Headers: x-mcp-enabled-tools / x-mcp-disabled-tags, etc.
• Query Parameters: ?tools=tool1,tool2 or ?tags=fan-control.

---

MCP Configuration Examples

stdio Transport (Recommended for local IDEs e.g., Cursor, Claude Desktop)

{
  "mcpServers": {
    "fan-manager": {
      "command": "uvx",
      "args": ["--from", "fan-manager", "fan-manager-mcp"],
      "env": {
        "TEMPERATURETOOL": "True",
        "FANCONTROLTOOL": "True"
      }
    }
  }
}

Streamable-HTTP Transport (Recommended for production deployments)

{
  "mcpServers": {
    "fan-manager": {
      "command": "uvx",
      "args": ["--from", "fan-manager", "fan-manager-mcp"],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "0.0.0.0",
        "PORT": "8000"
      }
    }
  }
}

Connect to a pre-deployed remote or local Streamable-HTTP instance:

{
  "mcpServers": {
    "fan-manager": {
      "url": "http://localhost:8000/fan-manager/mcp"
    }
  }
}

Deploying the Streamable-HTTP server via Docker:

docker run -d \
  --name fan-manager-mcp \
  --privileged \
  -p 8000:8000 \
  -e TRANSPORT=streamable-http \
  -e PORT=8000 \
  knucklessg1/fan-manager:latest

The container needs access to the host's IPMI device (--privileged or --device /dev/ipmi0) to drive the BMC.

---

Additional Deployment Options

fan-manager can also run as a local container (Docker / Podman / uv) or be consumed from a remote deployment. The Deployment guide has full, copy-paste mcp_config.json for all four transports — stdio, streamable-http, local container / uv, and remote URL:

• Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run, or point at a local streamable-http container by url.
• Remote URL — connect to a server deployed behind Caddy at http://fan-manager-mcp.arpa/mcp using the "url" key.

Agent

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

fan-manager-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

The docker/agent.compose.yml configures the Agent, Web UI, and Terminal Interface alongside the MCP server. See docs/deployment.md for the full Compose stack.

---

Environment Variables

Fan Manager reads the following environment variables (all optional — every one has a safe default). They can be set in the process environment, in a .env file (auto-loaded), or in the MCP client's env block. See .env.example for a ready-to-copy template.

Variable	Default	Scope	Description
HOST	0.0.0.0	MCP server	Bind address for streamable-http/sse transports.
PORT	8000	MCP server	Bind port for streamable-http/sse transports.
TRANSPORT	stdio	MCP server	Transport: stdio, streamable-http, or sse.
AUTH_TYPE	none	MCP server	Auth strategy passed to the agent-utilities MCP factory (none for this local tool).
FASTMCP_LOG_LEVEL	INFO	MCP server	Log verbosity for the underlying FastMCP server.
TEMPERATURETOOL	True	Tool toggle	Register the temperature tool domain (CONCEPT:FAN-001).
FANCONTROLTOOL	True	Tool toggle	Register the fan-control tool domain (CONCEPT:FAN-002).
IPMITOOL_PATH	ipmitool	Local tooling	Path/name of the ipmitool binary used to drive the BMC.
SENSORS_PATH	sensors	Local tooling	Path/name of the lm-sensors binary used to read temperatures.
ENABLE_OTEL	True	Observability	Enable OpenTelemetry/logfire instrumentation for the agent.
ENABLE_DELEGATION	False	Security	Enable OIDC Bearer-token delegation middleware (inert by default — Fan Manager is a local tool).
EUNOMIA_TYPE	none	Security	Eunomia policy mode: none, embedded, or remote.
EUNOMIA_POLICY_FILE	mcp_policies.json	Security	Path to the Eunomia policy file when EUNOMIA_TYPE is set.

Build-time only (not application config): UV_COMPILE_BYTECODE, NO_COLOR, and TERM are consumed by the build/runtime environment (Docker image build, terminal rendering) and are not read by the application code.

---

Security & Governance

Built directly upon the enterprise-ready agent-utilities core, standard security parameters are fully supported:

Access Control & Policy Enforcement

• Eunomia Policies: Fine-grained, policy-driven tool authorization (none, embedded, or remote).
• OIDC Token Delegation: Optional RFC 8693 token exchange (inert by default — Fan Manager is a local tool).

Runtime Security Grid

Feature	Functionality	Enablement
Tool Guard	Sensitivity inspection with human-in-the-loop validation	Enabled by default
Prompt Injection Defense	Input scanning, repetition monitoring, and recursive loop blocks	Enabled by default
Context Safety Guard	Stuck-loop detectors and contextual overflow preemptive alerts	Enabled by default

---

Installation

# Using uv (highly recommended)
uv pip install fan-manager[all]

# Using standard pip
python -m pip install fan-manager[all]

---

Documentation

The complete documentation is published as the official documentation site.

Page	Contents
Installation	pip, source, extras, prebuilt Docker image
Deployment	run the MCP and agent servers, Compose, env config
Usage	the MCP tools, the Api facade, the CLI
Overview	the action-routed tool surface and architecture
Concepts	concept registry (CONCEPT:FAN-*)

---

Contribute

Contributions are welcome! Please ensure code quality by executing local checks before submitting pull requests:

• Format code using ruff format .
• Lint code using ruff check .
• Validate type-safety with mypy .
• Execute test suites using pytest