Semantic search across all nodes using vector embeddings (with automatic fallback to full-text search). Returns nodes most similar to the query by MEANING (not exact text match). If embeddings are disabled or no results found, automatically falls back to keyword search. For files, searches indivi...
AI agents call vector_search_nodes to retrieve information from M I M I R Multi Agent Intelligent Memory & Insight Repository without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval-only operation. It queries a graph database and returns matching results based on semantic similarity. The tool has no side effects—it does not create, modify, delete data, execute code, or commit financial transactions. The capability is purely informational and read-based, warranting the lowest severity classification.
From the tool's definition Tool performs semantic search across nodes using vector embeddings with optional fallback to full-text search. Returns nodes similar to query by meaning.
Documented attack patterns abuse exactly the kind of access vector_search_nodes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and M I M I R Multi Agent Intelligent Memory & Insight Repository, and nothing reaches the server without passing your rules. This is the rule we recommend for vector_search_nodes:
{
"version": "1",
"default": "deny",
"tools": {
"vector_search_nodes": {}
}
}vector_search_nodes 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.
All 13 M I M I R Multi Agent Intelligent Memory & Insight Repository tools →
Semantic search across all nodes using vector embeddings (with automatic fallback to full-text search). Returns nodes most similar to the query by MEANING (not exact text match). If embeddings are disabled or no results found, automatically falls back to keyword search. For files, searches individual chunks and returns parent file context. Use this to find related concepts, similar problems, or relevant context when you don\. It is categorised as a Read tool in the M I M I R Multi Agent Intelligent Memory & Insight Repository MCP Server, which means it retrieves data without modifying state.
Register the M I M I R Multi Agent Intelligent Memory & Insight Repository MCP server in PolicyLayer and add a rule for vector_search_nodes: 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 M I M I R Multi Agent Intelligent Memory & Insight Repository. Nothing to install.
vector_search_nodes 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_nodes 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_nodes. 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_nodes is provided by the M I M I R Multi Agent Intelligent Memory & Insight Repository MCP server (orneryd/mimir). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 M I M I R Multi Agent Intelligent Memory & Insight Repository tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
13 M I M I R Multi Agent Intelligent Memory & Insight Repository tools catalogued and risk-classified — across an index of 42,500+ MCP servers.