MCP Server
The Constellation MCP Server connects your AI coding assistants to Constellation's powerful codebase intelligence system. Configure the Constellation MCP server for your project
Installation
It is strongly recommended to use the Constellation CLI command constellation init to automatically configure the MCP server settings in your project for your preferred AI tools, and to commit those MCP server configurations to your project's source control repository (for AI assistants that support project-level MCP configuration).
If using the 🧩 Claude Code Plugin, you do not need to add the Constellation MCP server configuration independently as it comes bundled with the plugin.
Manually configure the Constellation MCP server by following the directions below for your preferred AI tools.
Amazon Q
Add the following property to the mcpServers object of the .amazonq/mcp.json file in your project:
"constellation": {
"command": "npx",
"args": [
"-y",
"@constellationdev/mcp@latest"
]
}
Claude Code
There are multiple alternatives for configuring MCP servers in your project for use with Claude Code.
-
Recommended: Use the official Constellation Plugin for Claude Code. Add the following properties to the root of the
.claude/settings.jsonfile in your project:"extraKnownMarketplaces": {
"constellation-marketplace": {
"source": {
"source": "github",
"repo": "ShiftinBits/constellation-claude"
}
}
},
"enabledPlugins": {
"constellation@constellation-marketplace": true
} -
Add the following property to the root object of the
.mcp.jsonfile in your project:"constellation": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@constellationdev/mcp@latest"
]
}
Codex
Add the following section to the Codex .config.toml file:
[mcp_servers.constellation]
command = "npx"
args = ["-y", "@constellationdev/mcp@latest"]
Cursor
There are multiple alternatives for configuring MCP servers in your project for use with Cursor.
Gemini CLI
Add the following property to the mcpServers object of the .gemini/settings.json file in your project:
"constellation": {
"command": "npx",
"args": [
"-y",
"@constellationdev/mcp@latest"
]
}
GitHub Copilot (VSCode)
Refer to the official documentation for configuring MCP servers for GitHub Copilot in IDEs other than VSCode.
There are multiple alternatives for configuring MCP servers in your project for use with GitHub Copilot.
-
Recommended: Click the following button to automatically install the Constellation MCP server with VSCode:
-
Add the following property to the
serversobject of the.vscode/mcp.jsonfile in your project:"constellation": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@constellationdev/mcp@latest"
]
}
Kilo Code
Add the following property to the mcpServers object of the .kilocode/mcp.json file in your project:
"constellation": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@constellationdev/mcp@latest"
],
"env": {
"CONSTELLATION_ACCESS_KEY": "${env:CONSTELLATION_ACCESS_KEY}"
}
}
The MCP configuration must include the env block as defined in the JSON above in order to properly pass through the CONSTELLATION_ACCESS_KEY value to the MCP instance.
Windsurf
Add the following property to the mcpServers object of the Windsurf ~/.codeium/windsurf/mcp_config.json file:
"constellation": {
"command": "npx",
"args": [
"-y",
"@constellationdev/mcp@latest"
],
"env": {
"CONSTELLATION_ACCESS_KEY": "${env:CONSTELLATION_ACCESS_KEY}"
}
}
The MCP configuration must include the env block as defined in the JSON above in order to properly pass through the CONSTELLATION_ACCESS_KEY value to the MCP instance.
Other / Generic
Typically you will find an mcpServers or servers section in a JSON configuration file for your AI tooling, or perhaps a .mcp.json file in your project root folder. Add an entry for the Constellation MCP server to the proper configuration file in the respective section.
| Property | Value |
|---|---|
| name | constellation |
| type | stdio |
| command | npx |
| args | -y, @constellationdev/mcp@latest |
JSON Example:
"constellation": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@constellationdev/mcp@latest"
]
}
Benefits
Speed
Code Mode is 10-15x faster than traditional sequential tool calls. Complex analyses that would take 30+ seconds now complete in 2-3 seconds.
Composability
Your AI can combine multiple API calls with custom logic, parallel execution via Promise.all(), and sophisticated data transformations all in a single execution.
Team-Wide Intelligence
- All queries operate on your team's shared knowledge graph
- Consistent and accurate results across all team members
- Synchronized with your project's latest indexed changes
Graph-Powered Analysis
- Deep understanding of code relationships and dependencies
- Cross-file analysis that spans your entire codebase
- Pattern recognition and architectural insights
Requirements
- AI Assistant: Compatible AI coding assistant with MCP support (e.g., Claude Code, GitHub Copilot)
- Node.js: Version 18 or higher
- Constellation CLI: Must have a configured and indexed project
- Authentication: Valid Constellation access key (configured via CLI or environment variable)
Quick Start
-
Install the MCP server in your AI assistant (see Installation above)
-
Authenticate:
constellation auth -
Index your codebase:
constellation index -
Ask your AI assistant questions like:
- "Find all uses of the
UserServiceclass" - "What would be affected if I change this function?"
- "Are there any circular dependencies in this module?"
- "Summarize the architecture of this codebase"
- "Find all uses of the
Your AI assistant will automatically utilize Constellation to provide insightful and accurate answers!