logseq-api-mcp marketplace

logseq-api-mcp marketplace is a plugin for Claude Code from gustavo-meilus/logseq-api-mcp. Its token cost is not measured, scanned C, original, MIT.

A connection between Claude and Logseq, a note-taking app that stores linked pages and blocks. It provides tools for reading, writing, searching, and querying that knowledge graph, including Datalog queries, a Logseq query language.

In plain words
What is it for?
Listing pages, querying or editing blocks, creating and renaming pages, working with Markdown or SQLite graphs, hiding tagged private pages, and optionally finding notes by meaning through vector search.
Why use it?
It gives the assistant access to relevant notes instead of starting each session without your stored project knowledge.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add gustavo-meilus/logseq-api-mcp
agentmods
npx agentmods add plugins/gustavo-meilus/logseq-api-mcp/marketplace
Clone the repo
git clone --depth 1 https://github.com/gustavo-meilus/logseq-api-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for logseq-api-mcp marketplace

README.md
[![agentmods](https://agentmods.dev/badge/plugins/gustavo-meilus/logseq-api-mcp/marketplace.svg)](https://agentmods.dev/plugins/gustavo-meilus/logseq-api-mcp/marketplace)
Your own site
<a href="https://agentmods.dev/plugins/gustavo-meilus/logseq-api-mcp/marketplace"><img src="https://agentmods.dev/badge/plugins/gustavo-meilus/logseq-api-mcp/marketplace.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan C 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade C, and why

logseq-api-mcp marketplace scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

"installCommand": "curl -LsSf https://astral.sh/uv/install.sh | sh"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"installCommand": "curl -LsSf https://astral.sh/uv/install.sh | sh"
.claude-plugin/marketplace.json · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "logseq-api-mcp",
  "displayName": "Logseq API MCP Server",
  "slug": "logseq-api-mcp",
  "version": "0.2.0",
  "shortDescription": "Your AI assistant starts every session blind to your Logseq knowledge graph. This plugin gives it 22 tools to read, write, query, and search your notes.",
  "longDescription": "logseq-api-mcp bridges Claude and your Logseq knowledge base through the Model Context Protocol. It ships 22 standard tools covering every read and write operation you need — from listing pages and querying blocks to creating content, renaming pages, and executing raw Datalog queries. Tools auto-register through a dynamic discovery system: drop a .py file into src/tools/ and it appears in Claude without any imports or configuration changes.\n\nDB-mode support covers both the classic markdown-file graph format and Logseq's newer SQLite database format, including structured property upserts and UUID-reference resolution. A privacy layer lets you tag sensitive pages so they vanish from every read operation at query time. An optional vector search module adds semantic block search via LanceDB, built by running logseq-sync against your graph directory.",
  "category": "productivity",
  "subcategory": "knowledge-management",
  "tags": [
    "logseq",
    "knowledge-graph",
    "pkm",
    "notes",
    "zettelkasten",
    "second-brain",
    "mcp",
    "mcp-server",
    "flashcards",
    "vector-search",
    "datalog",
    "markdown"
  ],
  "author": {
    "name": "gustavo-meilus",
    "url": "https://github.com/gustavo-meilus",
    "avatar": "https://github.com/gustavo-meilus.png"
  },
  "repository": "https://github.com/gustavo-meilus/logseq-api-mcp",
  "homepage": "https://github.com/gustavo-meilus/logseq-api-mcp",
  "license": "MIT",
  "icon": "assets/icon.png",
  "screenshots": [
    {
      "url": "assets/architecture-light.svg",
      "alt": "Architecture: AI Client → logseq-api-mcp → Logseq API → Knowledge Graph",
      "caption": "System architectur

Read the full file on GitHub · 192 lines

Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 192 lines scan C b61ce24500b8

Subscribe to this mod's changes

logseq-api-mcp marketplace is a plugin published in the GitHub repository gustavo-meilus/logseq-api-mcp (30 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.