List all collections in the ChromaDB database.
AI agents call list_collections to retrieve information from ChromaDB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only query to enumerate existing collections. It retrieves metadata about database structure without modifying, executing code, deleting, or creating any resources. The blast radius if misused is minimal—an AI agent could discover collection names but cannot alter them or access sensitive data without additional tools.
From the tool's definition Tool name is 'list_collections' and description states 'List all collections in the ChromaDB database.' The verb 'list' is a pure retrieval operation with no side effects.
Attacks that exploit this kind of access
List all collections in the ChromaDB database. It is categorised as a Read tool in the ChromaDB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ChromaDB MCP Server MCP server in PolicyLayer and add a rule for list_collections: 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.
list_collections 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 list_collections 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 list_collections. 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.
list_collections 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 →