mcp-logseq
Provides an MCP server that lets an AI assistant interact with your LogSeq knowledge base via LogSeq's local HTTP API. It supports reading, creating, updating, deleting pages/blocks, searching pages/content, executing Logseq DSL queries, and (optionally) semantic vector search and DB-mode property operations.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Uses a LogSeq API token provided via env var. TLS enforcement and secret logging behavior are not described; local HTTP is implied (http://localhost). No evidence of fine-grained scopes, rate-limit headers, or robust structured security error messages in the provided README.
⚡ Reliability
Best When
You run LogSeq locally and want an agent to automate knowledge work directly against your own graph, optionally with local semantic search.
Avoid When
You cannot securely provide/guard an API token for LogSeq's HTTP server, or you need highly reliable transactional/idempotent behavior for repeated writes without duplicates.
Use Cases
- • Read and summarize LogSeq pages or namespaces
- • Create or update LogSeq pages from structured requests (including markdown-to-block conversion)
- • Manage task lists by inserting/updating blocks and properties
- • Search across a LogSeq graph using keyword/DSL and optional vector similarity
- • Maintain a vector index locally (sync and health checks)
- • Use DB-mode graphs to set class properties on blocks/pages (beta/opt-in)
Not For
- • Handling sensitive data in environments where local network access to the LogSeq HTTP API is not acceptable
- • Teams that require strong formal guarantees about error recovery, idempotency, and backward compatibility (release notes not provided here)
- • Scenarios needing cloud-hosted, multi-tenant access control or managed authentication
Interface
Authentication
Authentication is delegated to LogSeq’s local HTTP API via an API token. The README does not describe fine-grained scopes or token permissions.
Pricing
Self-hosted open-source package; costs are local (compute/storage) plus any embeddings runtime (e.g., Ollama) if using vector search.
Agent Metadata
Known Gotchas
- ⚠ Requires LogSeq HTTP APIs server to be started and a token generated; otherwise calls will fail.
- ⚠ Vector search tools require additional setup (VECTOR_SEARCH.md).
- ⚠ DB-mode property tools are opt-in and only applicable to LogSeq DB-mode graphs.
- ⚠ MCP client environment must correctly run the server (e.g., uv availability/path on Claude Desktop).
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-logseq.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.