This project runs a Model Context Protocol (MCP) server that wraps the CodeQL query server. It enables tools like [Cursor](https://cursor.sh/) or AI agents to interact with CodeQL through structured commands.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add codeql -- uv pip install -r requirements.txt~/.codex/config.toml
[mcp_servers.codeql]
command = "uv"
args = ["pip", "install", "-r", "requirements.txt"]
# codex mcp add codeql -- uv pip install -r requirements.txt~/.cursor/mcp.json
{
"mcpServers": {
"codeql": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}.vscode/mcp.json
{
"servers": {
"codeql": {
"type": "stdio",
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"codeql": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"codeql": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"codeql": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}