Skip to main content
Glama
tebinraouf

Hue MCP Server

by tebinraouf
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Hue MCP Server

Control Philips Hue lights through VS Code Copilot or Claude Desktop using the Model Context Protocol (MCP).

Quick Setup

1. Prerequisites

2. Install Dependencies

uv sync

3. Configure Your Bridge IP

Edit .env file:

HUE_BRIDGE_IP=192.168.1.XXX  # Replace with your bridge IP

4. First-Time Authentication

Press the physical button on your Hue Bridge, then run:

uv run python -c "from phue import Bridge; Bridge('YOUR_BRIDGE_IP')"

Related MCP server: Philips Hue MCP Server

Usage

For VS Code Copilot

Add to your VS Code MCP configuration file (mcp.json):

Location: ~/Library/Application Support/Code/User/mcp.json (macOS)

{
  "mcpServers": {
    "custom-hue": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "__PATH__",
        "python",
        "__PATH_TO_main.py__"
      ],
      "env": {
        "HUE_BRIDGE_IP": "192.168.x.x"
      }
    }
  }
}

Note: Replace the paths with your actual project path and update HUE_BRIDGE_IP with your bridge IP.

After adding the configuration, reload VS Code and use Copilot:

  • "Turn on the corner light and set it to blue"

  • "List all my lights"

  • "Turn off all lights"

For Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "hue-lights": {
      "command": "uv",
      "args": ["run", "/FULL/PATH/TO/custom-hue/main.py"],
      "env": {
        "HUE_BRIDGE_IP": "192.168.1.XXX"
      }
    }
  }
}

Available Tools

  • change_hue_light - Control individual lights (brightness, hue, saturation, on/off)

  • list_hue_lights - List all available lights on your Hue Bridge

Available Tools

2 tools
change_hue_lightA

Change the state of a Philips Hue light.

Args: light_id: The ID of the light to control (1-based index) brightness: Brightness level (0-254), where 0 is minimum and 254 is maximum hue: Hue color value (0-65535), where 0 and 65535 are red, 25500 is green, and 46920 is blue saturation: Color saturation (0-254), where 0 is white and 254 is most saturated on: Turn the light on (True) or off (False)

Returns: A message indicating the result of the operation

ParametersJSON Schema
NameRequiredDescriptionDefault
light_idYes
brightnessNo
hueNo
saturationNo
onNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It states the tool changes light state, implying mutation, but doesn't disclose behavioral traits like required permissions, rate limits, error conditions, or whether changes are reversible. The description adds minimal context beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (Args, Returns) and front-loaded purpose statement. Each sentence earns its place by providing essential information. Minor improvement possible by integrating parameter details more seamlessly rather than as a separate list.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters with 0% schema coverage and no annotations, the description does an excellent job explaining parameter semantics. The output schema exists, so return values needn't be detailed. However, it lacks behavioral context for a mutation tool (e.g., error handling, side effects), which slightly reduces completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate fully. It provides detailed semantics for all 5 parameters: light_id (1-based index), brightness (0-254 range with min/max), hue (0-65535 range with color mappings), saturation (0-254 range with white/most saturated), and on (True/False for on/off). This adds substantial value beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Change') and resource ('state of a Philips Hue light'), making the purpose specific and unambiguous. It distinguishes from the sibling tool 'list_hue_lights' by focusing on state modification rather than listing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for controlling a specific light's state, but lacks explicit guidance on when to use this tool versus alternatives or any prerequisites. It doesn't mention the sibling tool 'list_hue_lights' as a way to discover light IDs, which would be helpful context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_hue_lightsA

List all available Philips Hue lights.

Returns: A formatted list of all lights with their IDs, names, and current states

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool lists lights and describes the return format, which is helpful. However, it lacks details on potential side effects, authentication requirements, rate limits, or error conditions that would be important for a tool interacting with hardware.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with two sentences: one stating the purpose and one describing the return format. Every word earns its place with zero redundancy, and the information is front-loaded appropriately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters, an output schema exists, and it's a read-only listing operation, the description provides adequate context. It explains what the tool does and what it returns, though additional behavioral context (like authentication needs) would be beneficial since no annotations are provided.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the schema already fully documents the lack of inputs. The description appropriately doesn't discuss parameters, maintaining focus on the tool's purpose and output. This meets the baseline expectation for parameterless tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('all available Philips Hue lights'), making the purpose specific and understandable. It distinguishes from the sibling 'change_hue_light' by focusing on listing rather than modifying, though it doesn't explicitly mention this distinction in the text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving light information, but provides no explicit guidance on when to use this tool versus alternatives like 'change_hue_light'. There's no mention of prerequisites, timing considerations, or comparative context with the sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 2 tool updatesv1.0.0
    • Changedchange_hue_light1 field changed
      • addedInput schema / title
        Added value: +"change_hue_lightArguments"
    • Changedlist_hue_lights1 field changed
      • addedInput schema / title
        Added value: +"list_hue_lightsArguments"
  2. 2 tool updates
    • First observedchange_hue_light
    • First observedlist_hue_lights
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have completely distinct purposes with no overlap: one lists lights (read-only) while the other controls light states (write operation). An agent would never confuse these tools as they operate on different aspects of the Hue system.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern with 'hue_light(s)' as the common noun component. 'list_hue_lights' and 'change_hue_light' maintain perfect naming consistency throughout the toolset.

Tool Count2/5

With only 2 tools, this server feels severely underpowered for controlling a Philips Hue lighting system. A proper Hue interface would need tools for scenes, groups, schedules, bridge configuration, and more comprehensive light management beyond just listing and changing individual lights.

Completeness2/5

The tool surface is severely incomplete for Hue light control. Missing essential operations include: creating/deleting lights, managing scenes or groups, adjusting transition times, setting color temperatures, configuring bridge settings, and error handling for unavailable lights. Agents will hit dead ends trying to perform basic Hue workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches