search_blocks
AI agents call search_blocks 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.
Search and query operations that retrieve data without side effects are classified as Read. The tool has no destructive, financial, or code-execution implications. Even though the description is empty, the tool name and server context provide sufficient evidence that this performs data retrieval. Confidence is moderate due to missing formal description.
From the tool's definition Tool name 'search_blocks' suggests querying/retrieving block data from a knowledge graph. Sibling tools confirm this is a read-oriented server: 'get_all_pages', 'get_block', 'get_page', 'get_page_blocks', 'get_page_linked_references' are all Read operations.
Attacks that exploit this kind of access
search_blocks. 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 search_blocks: 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.
search_blocks 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 search_blocks 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 search_blocks. 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.
search_blocks 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 →