MCPVault

read_block

MCP tool from Logseq MCP by dailydaniel

a block and its children (uuid, depth?).

How to use it

read_block is exposed by the Logseq MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the read_block tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Logseq MCP

$claude mcp add logseq --scope user --env LOGSEQ_API_TOKEN=<YOUR_TOKEN> -- uvx mcp-server-logseq
FULL LOGSEQ MCP LISTING

Other tools in Logseq MCP (13)

create_task

create a task block in the agent namespace (title, agent,

custom_query

run a named query from the config (name, inputs?).

datascript_query

run a raw Datalog query (query, inputs?, rules?).

edit_block

replace one block's content (uuid, oldcontent,

find_tasks

task blocks by markers?, tag?, undertag? (descendant),

get_logseq_guide

returns the authoritative guide for querying/writing this

list_custom_queries

list the configured queries.

list_pages

page names under a namespace prefix? (depth? limits levels).

read_page

a page as a normalized block tree (page, depth?).

search

full-text search over block content (query, regex?, limit?,

set_page_properties

set/remove page properties (subpath, properties;

set_task_status

change only a task's marker (uuid, status); gated by

write_note

create/append/replace a page under agentwriteprefix