Build a multi-level connection graph starting from a note, showing how notes are semantically connected.
AI agents call get_connection_graph to retrieve information from Smart Connections MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents relationship data from an Obsidian vault's knowledge graph. It has no side effects—it only reads and visualizes existing semantic connections between notes. No data is created, modified, deleted, or executed. The operation is purely informational retrieval, making it a Read category tool with low security risk.
From the tool's definition Tool builds and returns a connection graph showing semantic relationships between notes. The description indicates it 'shows how notes are semantically connected' with no mention of modifying, deleting, or executing operations.
Documented attack patterns abuse exactly the kind of access get_connection_graph gives an agent:
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_connection_graph:
{
"version": "1",
"default": "deny",
"tools": {
"get_connection_graph": {}
}
}get_connection_graph 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.
Build a multi-level connection graph starting from a note, showing how notes are semantically connected. It is categorised as a Read tool in the Smart Connections MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Smart Connections MCP Server MCP server in PolicyLayer and add a rule for get_connection_graph: 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.
get_connection_graph 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 get_connection_graph 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 get_connection_graph. 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.
get_connection_graph 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.
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.
Free to start. No card required.
6 Smart Connections MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.