get_block
AI agents call get_block to retrieve information from Logseq MCP Tools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_block' tool retrieves a block from Logseq without modifying, deleting, or executing anything. It produces no side effects and falls clearly within the Read category alongside similar getter methods. Severity is low because retrieving knowledge graph data poses minimal risk even if accessed by an untrusted agent.
From the tool's definition Tool name 'get_block' indicates data retrieval. The server description mentions 'searching across a knowledge graph' and sibling tools include Read operations like 'get_all_pages', 'get_page', 'get_page_blocks', 'get_page_linked_references' which establish a…
Attacks that exploit this kind of access
get_block. It is categorised as a Read tool in the Logseq MCP Tools MCP Server, which means it retrieves data without modifying state.
Register the Logseq MCP Tools MCP server in PolicyLayer and add a rule for get_block: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Logseq MCP Tools. Nothing to install.
get_block is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_block rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_block. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_block is provided by the Logseq MCP Tools MCP server (mikeysrecipes/logseq-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →