extract

Perform text extraction and chunking on a document.

Server Vectorize @vectorize-io/vectorize-mcp-server
Category Read
Risk class Low
Parameters 00 required

What extract does on Vectorize

AI agents call extract to retrieve information from Vectorize without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why extract needs a policy

Text extraction and chunking are data retrieval and transformation operations with no state changes. The tool reads document content and segments it, producing processed output but leaving the source document intact. This is a classic Read category operation with minimal security risk; misuse would only affect output generated locally, not remote data integrity.

From the tool's definition The tool 'extract' is described as performing 'text extraction and chunking on a document' — these are read-only operations that retrieve and process text content without modifying, deleting, or executing side effects on the underlying document or system.

Questions about extract

What does the extract tool do? +

Perform text extraction and chunking on a document. It is categorised as a Read tool in the Vectorize MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on extract? +

Register the Vectorize MCP server in PolicyLayer and add a rule for extract: 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 Vectorize. Nothing to install.

What risk level is extract? +

extract is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit extract? +

Yes. Add a rate_limit block to the extract 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.

How do I block extract completely? +

Set action: deny in the PolicyLayer policy for extract. 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.

What MCP server provides extract? +

extract is provided by the Vectorize MCP server (@vectorize-io/vectorize-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.