Semantic memory search (keyword overlap) (user_id based)
AI agents call semantic_memory_search to retrieve information from Universal Dev MCP 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 (semantic memory) based on keyword overlap, with no side effects or state changes. The user_id scoping further reduces blast radius. Classified as Read with low severity since misuse would only expose information already associated with that user context.
From the tool's definition Tool name contains 'search' and description states 'Semantic memory search' — inherently a retrieval operation. Scoped by 'user_id based', limiting to user-specific data. No modification, deletion, or execution indicated.
Attacks that exploit this kind of access
Semantic memory search (keyword overlap) (user_id based). It is categorised as a Read tool in the Universal Dev MCP MCP Server, which means it retrieves data without modifying state.
Register the Universal Dev MCP server in PolicyLayer and add a rule for semantic_memory_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 Universal Dev MCP. Nothing to install.
semantic_memory_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 semantic_memory_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 semantic_memory_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.
semantic_memory_search is provided by the Universal Dev MCP server (kallusuvaidyam/universal_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 →