AI agents call store.doc-get to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data (a stored document) without side effects or state changes. The wallet-scoping ensures the operation is isolated to the user's own resources, and 'fetch' is an archetypal Read operation. No Write, Execute, Destructive, or Financial impact is evident.
From the tool's definition Tool name 'doc-get' and description 'fetch a stored document by id' indicates a retrieval operation. The phrase 'scoped to YOUR wallet' confirms access control limiting results to the caller's own data with no modification or deletion capability.
Attacks that exploit this kind of access
STORE: fetch a stored document by id, scoped to YOUR wallet. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for store.doc-get: 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. Nothing to install.
store.doc-get 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 store.doc-get 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 store.doc-get. 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.
store.doc-get is provided by the MCP server (@2sio/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 →