retrieve_single
AI agents call retrieve_single to retrieve information from Tabular Document Retriever MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries tabular data from ChromaDB without side effects. It performs a read-only operation analogous to a SELECT query, with no write, execute, destructive, or financial capabilities. The low severity reflects the minimal risk of data retrieval on a local vector database with no destructive or external operational effects.
From the tool's definition Tool named 'retrieve_single' on a 'Tabular Document Retriever MCP' server that 'enables MCP clients to retrieve relevant tabular data'.
Attacks that exploit this kind of access
retrieve_single. It is categorised as a Read tool in the Tabular Document Retriever MCP MCP Server, which means it retrieves data without modifying state.
Register the Tabular Document Retriever MCP server in PolicyLayer and add a rule for retrieve_single: 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 Tabular Document Retriever MCP. Nothing to install.
retrieve_single 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 retrieve_single 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 retrieve_single. 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.
retrieve_single is provided by the Tabular Document Retriever MCP server (lbaret/chromadb-retriever-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 →