AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
RAG / Knowledge Base/
mcp-logseq
mcp-logseq logo

mcp-logseq

Active·★ 343·MIT·Updated 2026-09-27

This MCP server seamlessly integrates Claude with your LogSeq knowledge base, enabling AI-powered interaction for reading, creating, and managing pages. It enhances productivity through intelligent organization, automated content creation, and optional semantic vector search across your notes.

mcp-logseq sits in the RAG / Knowledge Base category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Zero Context Switching: Claude works directly with your LogSeq data.. A representative use case is Intelligent Knowledge Management: Analyze project notes, create status summaries, and generate study roadmaps.. The listed license is MIT. GitHub stars are currently 343. Relevant tags include LogSeq, Claude.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool.

#LogSeq#Claude#AI Assistant#Knowledge Base#Vector Search#Semantic Search#API Integration#Markdown Parsing
$ Install
$ claude mcp add mcp-logseq --env LOGSEQ_API_TOKEN=your_token_here --env LOGSEQ_API_URL=http://localhost:12315 -- uv run --with mcp-logseq mcp-logseq
↗ Visit site★ GitHub
01

Features

01Zero Context Switching: Claude works directly with your LogSeq data.
02AI-powered Page Management: Intelligent organization, creation, linking, and search.
03Semantic Vector Search (optional): Find notes by meaning using local Ollama or hosted OpenAI-compatible embeddings.
04Smart Markdown Parsing: Automatically converts markdown into Logseq's native block structure.
05Logseq DB-mode Support: Read and write class properties on Logseq DB-mode graphs.
02

Why choose it

+Zero Context Switching: Claude works directly with your LogSeq data.
+AI-powered Page Management: Intelligent organization, creation, linking, and search.
+Intelligent Knowledge Management: Analyze project notes, create status summaries, and generate study roadmaps.
+Supports 6 platforms or runtime environments.
03

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.
04

Compatibility

LogSeq
Integration
Verified via docs
Claude
Client
Verified via docs
Python
Runtime
Verified via docs
Ollama
Embeddings
Verified via docs
OpenAI
Embeddings
Verified via docs
LanceDB
Vector DB
Verified via docs
05

Quick start

1
$ claude mcp add mcp-logseq --env LOGSEQ_API_TOKEN=your_token_here --env LOGSEQ_API_URL=http://localhost:12315 -- uv run --with mcp-logseq mcp-logseq
06

Use cases

↳Intelligent Knowledge Management: Analyze project notes, create status summaries, and generate study roadmaps.
↳Automated Content Creation: Create new pages for meeting notes or update existing project timelines.
↳Smart Research & Analysis: Compare notes on different topics, summarize themes, and create knowledge maps.
↳Semantic Search: Find notes by meaning across different languages, even without using exact keywords.
↳Meeting & Documentation Workflow: Transform meeting notes into task pages or summarize journal entries into review pages.
07

Alternatives

⚡Top VS:
VSzoteus★61→VSdata360-mcp★41→VSmarkdown-vault-mcp★35→VSmxLore★30→
zoteus logo
zoteus★ 61
⚡ The everything Zotero MCP server: complete Zotero Web API v3 + desktop local API for Claude & any MCP client. Search, safe writes, add-by-DOI, CSL citations, hybrid semantic search, and a scholarly-context graph. TypeScript, local-first.
VSCompare→
data360-mcp logo
data360-mcp★ 41
Model Context Protocol (MCP) server that gives LLM agents and chatbots direct access to the World Bank's Data360 Platform. Search, validate, and retrieve development indicators—from GDP and poverty to gender equality and climate—with structured metadata and time-series data, without hallucinating values.
VSCompare→
markdown-vault-mcp logo
markdown-vault-mcp★ 35
Generic markdown collection MCP server with FTS5 + semantic search, frontmatter-aware indexing, and incremental reindexing
VSCompare→
mxLore logo
mxLore★ 30
Self-hosted MCP server for AI coding assistants. Persistent knowledge base with 45 tools, 12 skills, institutional memory.
VSCompare→
crystalline logo
crystalline★ 17
Local-first crystalline intelligence for AI agents: the knowledge that endures across sessions, taught as Markdown Domains and captured as Engrams. One Rust binary with MCP server, CLI and hybrid search.
VSCompare→
openchronicle-mcp logo
openchronicle-mcp★ 16
Memory database for LLM agents — persistent keyword + optional semantic memory, project namespacing, served over HTTP REST and MCP from a single ASGI process. SQLite-backed, packaged as a Docker container. Runs on your hardware.
VSCompare→
docs-mcp-server logo
docs-mcp-server★ 1.8k
Grounded Docs MCP Server: Open-Source Alternative to Context7, Nia, and Ref.Tools
VSCompare→
stashbase logo
stashbase★ 1.1k
Turn local files into searchable context for AI agents.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Compatibility05Quick start06Use cases07Alternatives
ergut /
mcp-logseq
↗

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.

343MIT
Last commit3w ago
StatusActive
CategoryRAG / Knowledge Base
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.