AI agents call analyze_graph to retrieve information from Obsidian 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 examines graph metadata and relationships within an Obsidian vault without creating, modifying, deleting, or executing any operations. It has no side effects and no ability to alter vault state or trigger external processes. The blast radius of misuse is minimal—worst case, it could expose vault structure information, which is low-severity information disclosure.
From the tool's definition Tool name 'analyze_graph' and description 'Analyze the knowledge graph structure' indicate a query/analysis operation with no data modification or execution of external code.
Documented attack patterns abuse exactly the kind of access analyze_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Obsidian MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for analyze_graph:
{
"version": "1",
"default": "deny",
"tools": {
"analyze_graph": {}
}
}analyze_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.
Analyze the knowledge graph structure. It is categorised as a Read tool in the Obsidian MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Obsidian MCP Server MCP server in PolicyLayer and add a rule for analyze_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 Obsidian MCP Server. Nothing to install.
analyze_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 analyze_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 analyze_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.
analyze_graph is provided by the Obsidian MCP Server MCP server (bazylhorsey/obsidian-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Obsidian 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.
29 Obsidian MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.