get_backlinks_tool
AI agents call get_backlinks_tool 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 queries existing backlink relationships in an Obsidian vault, returning data about which notes reference a given note. This is a read-only operation with no side effects, no data modification, and no destructive capability. The low severity reflects that reading note metadata poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'get_backlinks_tool' indicates retrieval of backlink information. Sibling tools show this server is for vault querying and management; get_backlinks_tool retrieves metadata about note references without modifying data.
Attacks that exploit this kind of access
get_backlinks_tool. 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 get_backlinks_tool: 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.
get_backlinks_tool 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_tool 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_tool. 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_tool is provided by the Obsidian MCP Server MCP server (suhailnajeeb/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 →