Get a document by OID, or by owner type/ID and document ID.
AI agents call quire.getDocument to retrieve information from Quire MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves document data based on provided identifiers (OID or owner/document IDs). The 'get' verb and retrieval-only semantics confirm this is a Read operation. Severity is low because it only accesses existing data without altering state, executing code, or causing irreversible changes.
From the tool's definition Tool name 'getDocument' and description 'Get a document by OID, or by owner type/ID and document ID' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get a document by OID, or by owner type/ID and document ID. It is categorised as a Read tool in the Quire MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Quire MCP Server MCP server in PolicyLayer and add a rule for quire.getDocument: 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 Quire MCP Server. Nothing to install.
quire.getDocument 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 quire.getDocument 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 quire.getDocument. 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.
quire.getDocument is provided by the Quire MCP Server MCP server (jacob-hartmann/quire-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 →