Semantic vector search across all indexed layers (Entity + Chunk + Fact).
AI agents call vector_search to retrieve information from MCP Roo Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing data (vector-indexed entities, chunks, and facts) and returns results without side effects. It does not create, modify, delete, or execute operations. The blast radius of misuse is minimal—worst case, an agent retrieves unintended information, which poses no destructive or financial risk.
From the tool's definition Tool performs 'semantic vector search across all indexed layers' with no modification, deletion, or execution capabilities implied. The verb 'search' and context of a memory/knowledge graph system indicate read-only retrieval.
Attacks that exploit this kind of access
Semantic vector search across all indexed layers (Entity + Chunk + Fact). It is categorised as a Read tool in the MCP Roo Memory MCP Server, which means it retrieves data without modifying state.
Register the MCP Roo Memory 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 Roo Memory. 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 Roo Memory MCP server (mcasdfgf/mcp-roo-memory). 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 →