AI agents call get_backlinks to retrieve information from Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a graph traversal query within an Obsidian vault to fetch backlinks (incoming references) to a given note. It retrieves and returns data with no side effects—no creation, modification, deletion, or execution of code. The blast radius of misuse is minimal: an agent could retrieve sensitive note content through link traversal, but this is a standard read operation inherent to knowledge base access.
From the tool's definition Tool name 'get_backlinks' and description 'Return notes that link to the given path, with snippets' indicate a read-only query operation that retrieves existing link data without modifying or deleting any content.
Attacks that exploit this kind of access
Return notes that link to the given path, with snippets. Same data as the. It is categorised as a Read tool in the Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Obsidian MCP server in PolicyLayer and add a rule for get_backlinks: 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. Nothing to install.
get_backlinks 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_backlinks 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_backlinks. 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_backlinks is provided by the Obsidian MCP server (yanxue06/obsidian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →