get_embedding_neighbors

THE RISK

Low Risk

Why get_embedding_neighbors needs a policy

This tool performs a read-only similarity search operation using embedding vectors to discover related notes in an Obsidian vault. It retrieves information but does not create, modify, delete, or execute any operations that could change state or trigger external side effects. The operation is fundamentally a query against existing embeddings, consistent with the 'Read' category for retrieval and search functions.

From the tool's definition Tool name 'get_embedding_neighbors' and description 'Find nearest neighbors for a given embedding vector. Useful for custom similarity searches.' indicate a query/search operation that retrieves data without modification.

Documented attack patterns abuse exactly the kind of access get_embedding_neighbors gives an agent:

POLICY

How to control get_embedding_neighbors

PolicyLayer is an MCP gateway — it sits between your AI agents and Smart Connections MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_embedding_neighbors:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_embedding_neighbors": {}
  }
}

get_embedding_neighbors is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Smart Connections MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Smart Connections MCP Server tools

Read get_connection_graph Build a multi-level connection graph starting from a note, showing how notes are semantica Read get_note_content Retrieve the full content of a note, optionally with specific blocks/sections extracted. Read get_similar_notes Find notes semantically similar to a given note using embeddings. Returns paths, similarit Read get_stats Get statistics about the Smart Connections knowledge base (total notes, blocks, embedding Read search_notes Search for notes using a text query. Returns notes ranked by relevance with similarity sco

All 6 Smart Connections MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_embedding_neighbors

What does the get_embedding_neighbors tool do? +

Find nearest neighbors for a given embedding vector. Useful for custom similarity searches. It is categorised as a Read tool in the Smart Connections MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_embedding_neighbors? +

Register the Smart Connections MCP Server MCP server in PolicyLayer and add a rule for get_embedding_neighbors: 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 Smart Connections MCP Server. Nothing to install.

What risk level is get_embedding_neighbors? +

get_embedding_neighbors is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_embedding_neighbors? +

Yes. Add a rate_limit block to the get_embedding_neighbors 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.

How do I block get_embedding_neighbors completely? +

Set action: deny in the PolicyLayer policy for get_embedding_neighbors. 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.

What MCP server provides get_embedding_neighbors? +

get_embedding_neighbors is provided by the Smart Connections MCP Server MCP server (msdanyg/smart-connections-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Smart Connections MCP Server tool call.

Start from Smart Connections MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →