Get a KB collection by ID with direct subcollections and paginated articles
AI agents call get_collection to retrieve information from SparrowDesk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries knowledge base collection data by ID. It has no side effects, does not create, modify, or delete any data. It is a straightforward read operation consistent with data retrieval utilities. The low severity reflects minimal blast radius if misused by an AI agent - it can only expose existing knowledge base information.
From the tool's definition Tool description states 'Get a KB collection by ID' - a retrieval operation that returns subcollections and articles without modifying data.
Attacks that exploit this kind of access
Get a KB collection by ID with direct subcollections and paginated articles. It is categorised as a Read tool in the SparrowDesk MCP Server, which means it retrieves data without modifying state.
Register the SparrowDesk MCP server in PolicyLayer and add a rule for get_collection: 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 SparrowDesk. Nothing to install.
get_collection 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 get_collection 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 get_collection. 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.
get_collection is provided by the SparrowDesk MCP server (sparrowdesk/sparrowdesk-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 →