MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add logseq -- uvx mcp-logseq~/.codex/config.toml
[mcp_servers.logseq]
command = "uvx"
args = ["mcp-logseq"]
# codex mcp add logseq -- uvx mcp-logseq~/.cursor/mcp.json
{
"mcpServers": {
"logseq": {
"command": "uvx",
"args": [
"mcp-logseq"
]
}
}
}.vscode/mcp.json
{
"servers": {
"logseq": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-logseq"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"logseq": {
"command": "uvx",
"args": [
"mcp-logseq"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"logseq": {
"command": "uvx",
"args": [
"mcp-logseq"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"logseq": {
"command": "uvx",
"args": [
"mcp-logseq"
]
}
}
}