Index project files for semantic search using vector embeddings
AI agents use index-vectors to create or update resources in Ultra MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ultra MCP environment.
This tool creates/writes vector embeddings from project files into an index store. It modifies state by building and storing a vector index, but does not delete data or execute arbitrary code. It is reversible in that the index can be rebuilt or cleared (a sibling tool 'clear-vectors' suggests deletion is separate).
From the tool's definition Index project files for semantic search using vector embeddings
Documented attack patterns abuse exactly the kind of access index-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 index-vectors:
{
"version": "1",
"default": "deny",
"tools": {
"index-vectors": {
"limits": [
{
"counter": "index-vectors_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} index-vectors stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Index project files for semantic search using vector embeddings. It is categorised as a Write tool in the Ultra MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ultra MCP server in PolicyLayer and add a rule for index-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.
index-vectors is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the index-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 index-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.
index-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.