query_collection
AI agents invoke query_collection to trigger actions in ChromaDB MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Based on the tool name and server context (ChromaDB vector database with semantic search capabilities), this tool likely performs a semantic/vector search query against a collection. Querying/searching is typically a Read operation. However, the empty description lowers confidence, and 'query' operations can sometimes execute more complex operations.
From the tool's definition Tool name 'query_collection' on a ChromaDB vector database server; description is empty and uninformative.
Attacks that exploit this kind of access
query_collection. It is categorised as a Execute tool in the ChromaDB MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ChromaDB MCP Server MCP server in PolicyLayer and add a rule for query_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 ChromaDB MCP Server. Nothing to install.
query_collection is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the query_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 query_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.
query_collection is provided by the ChromaDB MCP Server MCP server (rkilchmn/chroma-mcp-server). 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 →