Semantic search using embeddings + Chroma. Optional metadata filter via
AI agents call vector_search to retrieve information from MCP Tooling Lab 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 data from a vector store based on semantic similarity. It has no side effects—it does not create, modify, delete, or execute arbitrary operations. The optional metadata filter is a read-only constraint on the query. This is a classic Read category operation: search/query functionality that returns results without altering the underlying data.
From the tool's definition Tool description states 'Semantic search using embeddings + Chroma' with optional metadata filtering. The verb 'search' and the context of querying a vector database indicate data retrieval without modification.
Attacks that exploit this kind of access
Semantic search using embeddings + Chroma. Optional metadata filter via. It is categorised as a Read tool in the MCP Tooling Lab MCP Server, which means it retrieves data without modifying state.
Register the MCP Tooling Lab MCP server in PolicyLayer and add a rule for vector_search: 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 MCP Tooling Lab. Nothing to install.
vector_search 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 vector_search 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 vector_search. 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.
vector_search is provided by the MCP Tooling Lab MCP server (kaypon/mcp-tooling-lab). 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 →