retrieve_batch
AI agents call retrieve_batch 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 tabular data in batches from a vector database. The server's core function is retrieval-focused ('Retriever' in name, 'retrieve' operations), with no mention of write, delete, or execution capabilities. Batch retrieval is a read-only operation with no side effects.
From the tool's definition Tool name 'retrieve_batch' combined with server description emphasizing 'retrieval' and 'semantic search' through 'local ChromaDB instance' indicates batch querying of stored data without modification capabilities.
Attacks that exploit this kind of access
retrieve_batch. 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_batch: 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_batch 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_batch 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_batch. 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_batch 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 →