extract_information

Extract structured information from documents using Upstage Universal Information Extraction.

Server MCP-Upstage-Server upstageai/mcp-upstage-server
Category Read
Risk class Low
Parameters 00 required

What extract_information does on MCP-Upstage-Server

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

Why extract_information needs a policy

This tool reads and processes document content to derive structured information, similar to parsing or querying. It has no side effects on the document itself, does not execute arbitrary code, does not modify or delete data, and does not involve financial transactions. The operation is read-only in nature—it analyzes existing documents to pull out information according to specified schemas.

From the tool's definition Tool performs 'extract structured information from documents' using Upstage's information extraction service. The verb 'extract' indicates retrieval and processing of data without modification or deletion of the underlying documents.

Questions about extract_information

What does the extract_information tool do? +

Extract structured information from documents using Upstage Universal Information Extraction. It is categorised as a Read tool in the MCP-Upstage-Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on extract_information? +

Register the MCP-Upstage-Server MCP server in PolicyLayer and add a rule for extract_information: 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 MCP-Upstage-Server. Nothing to install.

What risk level is extract_information? +

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

Can I rate-limit extract_information? +

Yes. Add a rate_limit block to the extract_information 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_information completely? +

Set action: deny in the PolicyLayer policy for extract_information. 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_information? +

extract_information is provided by the MCP-Upstage-Server MCP server (upstageai/mcp-upstage-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.