Logseq ToolsCAUTION
mcp server for logseq graph
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/@joelhooks/logseq-mcp-tools)
A Model Context Protocol (MCP) server that provides AI assistants with structured access to your Logseq knowledge graph.
Overview
This project creates an MCP server that allows AI assistants like Claude to interact with your Logseq knowledge base. It provides tools for:
- Retrieving a list of all pages
- Getting content from specific pages
- Generating journal summaries for flexible date ranges
- Extracting linked pages and exploring connections
Installation
Installing via Smithery
To install Logseq Tools for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @joelhooks/logseq-mcp-tools --client claude
- Clone this repository
- Install dependencies using npm, yarn, or pnpm:
# Using npm npm install # Using yarn yarn install # Using pnpm pnpm install
- Copy the environment template and configure your Logseq token:
cp .env.template .env # Edit .env with your Logseq authentication token
Configuration
This project includes a .env.template file that you can copy and rename to .env.
You can find your Logseq auth token by:
- Opening Logseq
- Enabling the HTTP API in Settings > Features > Enable HTTP API
- Setting your authentication token in Settings > Features > HTTP API Authentication Token
Usage
Running the MCP Server
The server can be started using:
# Using the npm script npm start # Or directly with tsx npx tsx index.ts
Connecting with Claude
Claude Desktop
Follow the Claude MCP Quickstart guide:
- Important: Install Node.js globally via Homebrew (or whatever):
brew install node
- Install the Claude desktop app
- Open the Claude menu and select "Settings..."
4.
f28a2cc3fee2OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add logseq-mcp-tools --env LOGSEQ_TOKEN=${LOGSEQ_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"logseq-mcp-tools": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"LOGSEQ_TOKEN": "${LOGSEQ_TOKEN}"
}
}
}
}Exposed tools (16)
16 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
addJournalBlock | read | |
addJournalContent | read | |
addJournalEntry | read | |
addNoteContent | read | |
analyzeGraph | read | |
analyzeJournalPatterns | read | |
createPage | read | |
findKnowledgeGaps | read | |
getAllPages | read | |
getBacklinks | read | |
getBlock | read | |
getJournalSummary | read | |
getPage | read | |
searchPages | read | |
smartQuery | read | |
suggestConnections | read |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (5)
# Defaults to http://127.0.0.1:12315/api if not set.
# LOGSEQ_API_URL=http://127.0.0.1:12315/api
.env.template
Logseq HTTP server runs at http://127.0.0.1:12315 and provides access to the Logseq plugin SDK API.
@logseq/libs, @modelcontextprotocol/sdk, @types/node, dotenv, zod, tsx, typescript
Gates applied: no_behavioural_pass.
f28a2cc3fee2full audit observations/trust-audit/mcp-server/joelhooks__logseq-tools.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | f28a2cc3fee2 | CAUTION | B | 89 | first audit |
Questions
What is the Logseq Tools MCP server?
mcp server for logseq graph
What tools does Logseq Tools expose?
16 in total: 16 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Logseq Tools safe to connect to an agent?
With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Logseq Tools need?
It reads LOGSEQ_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Logseq Tools run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as logseq-mcp-tools at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (f28a2cc3fee2), read on 2026-10-07. The repository is watched and re-audited when it changes.