LogSeq
About
Integrates with LogSeq API to enable automated note-taking, content searching, and knowledge management tasks.
Details
- Repository
- ergut/mcp-logseq
- License
- MIT
Explore
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
LogSeqCommand (node, npx, python, etc.)uvArguments-
Argument 1
run -
Argument 2
--with -
Argument 3
mcp-logseq -
Argument 4
mcp-logseq
Environment-
LOGSEQ_API_URL
http://localhost:12315 -
LOGSEQ_API_TOKEN
your_token_here
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Claude Desktop
Add to your config file (Settings → Developer → Edit Config):
{
"mcpServers": {
"mcp-logseq": {
"command": "uv",
"args": ["run", "--with", "mcp-logseq", "mcp-logseq"],
"env": {
"LOGSEQ_API_TOKEN": "your_token_here",
"LOGSEQ_API_URL": "http://localhost:12315"
}
}
}
}
list_pages
Browse your graph. Example use: 'Show me all my pages'.
get_page_content
Read page content. Example use: 'Get my project notes'.
create_page
Add new pages with structured blocks. Example use: 'Create a meeting notes page with agenda items'.
update_page
Modify pages (append/replace modes). Example use: 'Update my task list'.
delete_page
Remove pages. Example use: 'Delete the old draft page'.
delete_block
Remove a block by UUID. Example use: 'Delete this specific block'.
update_block
Edit block content by UUID. Example use: 'Update this specific block text'.
search
Find content across graph. Example use: 'Search for 'productivity tips'.
query
Execute Logseq DSL queries. Example use: 'Find all TODO tasks tagged #project'.
find_pages_by_property
Search pages by property. Example use: 'Find all pages with status = active'.
get_pages_from_namespace
List pages in a namespace. Example use: 'Show all pages under Customer/'.
get_pages_tree_from_namespace
Hierarchical namespace view. Example use: 'Show Projects/ as a tree'.
rename_page
Rename with reference updates. Example use: 'Rename 'Old Name' to 'New Name'.
get_page_backlinks
Find pages linking to a page. Example use: 'What links to this page?'.
insert_nested_block
Insert child/sibling blocks. Example use: 'Add a child block under this task'.
set_block_properties
Set DB-mode class properties on a block. Example use: 'Set the status of this block to active' (DB-mode only).
vector_search
Semantic search by meaning. Example use: 'Find notes about shadow work or Jung'.
sync_vector_db
Sync vector DB with graph files. Example use: 'Update the search index'.
vector_db_status
Show vector DB health and staleness. Example use: 'Is my search index up to date?'.
The server provides 16 tools with intelligent markdown parsing, plus 3 optional vector search tools:
| Tool | Purpose | Example Use |
|------|---------|-------------|
| list_pages | Browse your graph | "Show me all my pages" |
| get_page_content | Read page content | "Get my project notes" |
| create_page | Add new pages with structured blocks | "Create a meeting notes page with agenda items" |
| update_page | Modify pages (append/replace modes) | "Update my task list" |
| delete_page | Remove pages | "Delete the old draft page" |
| delete_block | Remove a block by UUID | "Delete this specific block" |
| update_block | Edit block content by UUID | "Update this specific block text" |
| search | Find content across graph | "Search for 'productivity tips'" |
| query | Execute Logseq DSL queries | "Find all TODO tasks tagged #project" |
| find_pages_by_property | Search pages by property | "Find all pages with status = active" |
| get_pages_from_namespace | List pages in a namespace | "Show all pages under Customer/" |
| get_pages_tree_from_namespace | Hierarchical namespace view | "Show Projects/ as a tree" |
| rename_page | Rename with reference updates | "Rename 'Old Name' to 'New Name'" |
| get_page_backlinks | Find pages linking to a page | "What links to this page?" |
| insert_nested_block | Insert child/sibling blocks | "Add a child block under this task" |
| set_block_properties | Set DB-mode class properties on a block | "Set the status of this block to active" (DB-mode only) |
| vector_search ⚗️ | Semantic search by meaning | "Find notes about shadow work or Jung" |
| sync_vector_db ⚗️ | Sync vector DB with graph files | "Update the search index" |
| vector_db_status ⚗️ | Show vector DB health and staleness | "Is my search index up to date?" |
⚗️ Requires vector search setup — see VECTOR_SEARCH.md
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"logseq": {
"env": {
"LOGSEQ_API_URL": "http://localhost:12315",
"LOGSEQ_API_TOKEN": "your_token_here"
},
"args": [
"run",
"--with",
"mcp-logseq",
"mcp-logseq"
],
"command": "uv"
}
}
}Linux
{
"env": {
"LOGSEQ_API_URL": "http://localhost:12315",
"LOGSEQ_API_TOKEN": "your_token_here"
},
"args": [
"run",
"--with",
"mcp-logseq",
"mcp-logseq"
],
"command": "uv"
}Macos
{
"env": {
"LOGSEQ_API_URL": "http://localhost:12315",
"LOGSEQ_API_TOKEN": "your_token_here"
},
"args": [
"run",
"--with",
"mcp-logseq",
"mcp-logseq"
],
"command": "uv"
}Windows
{
"env": {
"LOGSEQ_API_URL": "http://localhost:12315",
"LOGSEQ_API_TOKEN": "your_token_here"
},
"args": [
"run",
"--with",
"mcp-logseq",
"mcp-logseq"
],
"command": "uv"
}Step 1: Enable LogSeq API
1. Settings → Features → Check "Enable HTTP APIs server" 2. Click the API button (🔌) in LogSeq → "Start server" 3. Generate API token: API panel → "Authorization tokens" → Create newSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
