Open-source context intelligence engine for AI coding agents — repository graph, precise code navigation, MCP, impact analysis, memory, and guarded edits.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add codecortex-context-engine -- uvx codecortex-context-engine~/.codex/config.toml
[mcp_servers.codecortex-context-engine]
command = "uvx"
args = ["codecortex-context-engine"]
# codex mcp add codecortex-context-engine -- uvx codecortex-context-engine~/.cursor/mcp.json
{
"mcpServers": {
"codecortex-context-engine": {
"command": "uvx",
"args": [
"codecortex-context-engine"
]
}
}
}.vscode/mcp.json
{
"servers": {
"codecortex-context-engine": {
"type": "stdio",
"command": "uvx",
"args": [
"codecortex-context-engine"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"codecortex-context-engine": {
"command": "uvx",
"args": [
"codecortex-context-engine"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"codecortex-context-engine": {
"command": "uvx",
"args": [
"codecortex-context-engine"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"codecortex-context-engine": {
"command": "uvx",
"args": [
"codecortex-context-engine"
]
}
}
}