List all raw source documents with metadata (path, source URL, download time, hash, size).
AI agents call raw_list 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.
This is a straightforward read operation that returns metadata about documents. The blast radius of misuse is minimal—an agent could learn what documents exist and their properties, but cannot modify, execute, or delete anything. The metadata returned (path, source URL, download time, hash, size) is informational only.
From the tool's definition Tool name 'raw_list' and description 'List all raw source documents with metadata' indicates a retrieval operation with no side effects. It queries metadata about existing documents without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
List all raw source documents with metadata (path, source URL, download time, hash, size). It is categorised as a Read tool in the Agent Wiki MCP Server, which means it retrieves data without modifying state.
Register the Agent Wiki MCP server in PolicyLayer and add a rule for raw_list: 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.
raw_list 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 raw_list 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 raw_list. 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.
raw_list 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.
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 →