raw_read

Read a raw source document

Server Agent Wiki xinhuagu/agent-wiki
Category Read
Risk class Low
Parameters 00 required

What raw_read does on Agent Wiki

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

Why raw_read needs a policy

This tool performs a read-only operation on source documents with no side effects. It retrieves data without creating, modifying, deleting, or executing any operations. The term 'raw' suggests unprocessed source access, but the action remains purely informational.

From the tool's definition Tool name 'raw_read' and description 'Read a raw source document' explicitly indicate data retrieval with no modification capability.

Questions about raw_read

What does the raw_read tool do? +

Read a raw source document. It is categorised as a Read tool in the Agent Wiki MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on raw_read? +

Register the Agent Wiki MCP server in PolicyLayer and add a rule for raw_read: 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 Agent Wiki. Nothing to install.

What risk level is raw_read? +

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

Can I rate-limit raw_read? +

Yes. Add a rate_limit block to the raw_read 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 raw_read completely? +

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

raw_read is provided by the Agent Wiki MCP server (xinhuagu/agent-wiki). 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.