Logseq MCP Server

Turn your Logseq graph into memory and workspace for AI agents. A
Model Context Protocol server for
Logseq with safety-scoped writes, an audit trail in your
daily journal, and verified queries exposed as tools. Built on FastMCP (the
high-level API of the official mcp package).

<a href="https://glama.ai/mcp/servers/@dailydaniel/logseq-mcp">

</a>

> Targets the file/Markdown ("OG") version of Logseq — and plain-text files
> are part of why a graph makes good agent memory: git-syncable, greppable,
> durable, no lock-in. The newer DB (SQLite) version changed the underlying
> schema; some methods may behave differently there.

Why

Agents need durable memory, and you already maintain one — your graph. The
missing piece is access you can trust: an agent should read broadly and write
usefully, but never touch what it shouldn't — and never do anything you can't
see. Three design choices make that possible:

- Namespace-scoped writes. Agents write only under their own prefix
(byAgent/ by default), plus one deliberately narrow cross-namespace channel
that can change nothing but a task's TODO/DOING/DONE marker. Blacklisted
pages are hidden and redacted from every read.
- An audit trail in your daily journal. Every successful write appends a
line like 22:30 [[byAgent]] wrote [[byAgent/readingList/...]] to today's
journal — reviewing your agents' work becomes part of a morning routine you
already have.
- Verified queries as tools. Ship known-good Datalog from config as named
tools (query_week_plan, …), so agents don't compose datascript by hand and
cheaper models stay reliable.

How I use it

I run a small fleet of Claude Code agents with this server on an always-on Mac
mini, against my live personal graph:

- Nightly research. A link dropped into the reading list from the phone; at
night an agent claims it (status:: researching), reads the article — or
shallow-clones and reads the repo — writes a structured summary onto the page
and flips it to read.
- Morning brief. At 08:30 a small model assembles a one-page dashboard —
what was read overnight, week-plan progress, current NOW/DOING tasks — and
sends a single push notification.
- One journal for everyone. The human's tasks and the agents' audit lines
interleave in the same daily note:

The pages the researcher writes — properties, summary, relevance — link straight
into the rest of the graph:

flowchart LR
    A[AI agents] -- MCP tools --> S[logseq-mcp]
    S -- HTTP API --> L[Logseq graph]
    S -. audit line per write .-> J[daily journal]
    Y((you)) --> L
    Y -- morning review --> J

Requirements

- A running Logseq with the local HTTP API server enabled
(Settings → Features → HTTP APIs server, then start it from the 🔌 menu).
- An authorization token created in the HTTP API server settings.

Usage

Claude Code

Local (stdio), token from the environment:

claude mcp add logseq --scope user --env LOGSEQ_API_TOKEN=<YOUR_TOKEN> -- uvx mcp-server-logseq

Or point it at a remote instance over Streamable HTTP (how phone and remote
sessions reach a headless host — see Transports):

claude mcp add logseq --scope user --transport http http://<host>:8000/mcp \
  --header "Authorization: Bearer <LOGSEQ_MCP_HTTP_TOKEN>"

Claude Desktop

{
  "mcpServers": {
    "logseq": {
      "command": "uvx",
      "args": ["mcp-server-logseq"],
      "env": {
        "LOGSEQ_API_TOKEN": "<YOUR_TOKEN>",
        "LOGSEQ_API_URL": "http://127.0.0.1:12315"
      }
    }
  }
}

Configuration

| Source | Token | URL |
| --- | --- | --- |
| Environment | LOGSEQ_API_TOKEN | LOGSEQ_API_URL (default http://localhost:12315) |
| CLI flag | --api-key | --url |

The token is read from the environment or --api-key; it is never stored in
code. A .env file is supported (see .env.example).

Config file (optional)

Behaviour beyond the defaults is set in a TOML file — path from
LOGSEQ_MCP_CONFIG (default ~/.config/logseq-mcp/config.toml). Custom queries
live in EDN files next to it. The server runs fine with no config file (safe
read-mostly defaults); see examples/config.toml for a
full annotated example.

| Section | Key options |
| --- | --- |
| [read] | resolve_depth — how deep to expand ((block refs)) |
| [write] | agent_write_prefix (default byAgent), allow_agents_write_any |
| [search] | files_path — graph folder; set it to use the ripgrep backend |
| [blacklist] | pages — pages (and subpages) to hide and redact everywhere |
| [tasks] | allow_status_change — gate for set_task_status |
| [audit_log] | enabled — log writes to today's journal |
| [queries.<name>] | a named query: file/inline query, register_as_tool, … |

Secrets and the API URL stay in the environment, never in this file.

Transports

By default the server runs over stdio (for Claude Desktop and other local
clients). A Streamable HTTP transport is also available for remote/networked
use (e.g. a phone client):

```bash
LOGSEQ_MCP_HTTP_TOKEN=<client-secret> \
mcp-server-logseq --transport streamable-http --host 0.0.0.0 --port 8000