Search for files and code snippets using natural language queries
AI agents call search-vectors to retrieve information from Ultra MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/query operation that retrieves data from an indexed vector store. It has no side effects, does not execute code, does not modify data, and does not delete anything. The operation is purely informational—returning matching files and code snippets based on semantic search. This is a canonical Read category tool.
From the tool's definition Tool name 'search-vectors' and description 'Search for files and code snippets using natural language queries' indicate a retrieval operation with no data modification or execution capability.
Documented attack patterns abuse exactly the kind of access search-vectors gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ultra MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search-vectors:
{
"version": "1",
"default": "deny",
"tools": {
"search-vectors": {}
}
}search-vectors is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for files and code snippets using natural language queries. It is categorised as a Read tool in the Ultra MCP MCP Server, which means it retrieves data without modifying state.
Register the Ultra MCP server in PolicyLayer and add a rule for search-vectors: 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 Ultra MCP. Nothing to install.
search-vectors 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 search-vectors 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 search-vectors. 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.
search-vectors is provided by the Ultra MCP server (realmikechong/ultra-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 Ultra MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 Ultra MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.