Extract all [[wikilinks]] from a note.
AI agents call get_outlinks to retrieve information from Mcp Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only analysis of existing note content to identify outbound links. It has no side effects, cannot modify data, and poses minimal security risk. The operation is analogous to a search or list function. Confidence is high due to clear evidence from the description and unambiguous read-only nature.
From the tool's definition Tool description states 'Extract all [[wikilinks]] from a note' - this is a retrieval operation with no data modification or deletion. The name 'get_outlinks' and verb 'extract' both indicate querying existing data.
Attacks that exploit this kind of access
Extract all [[wikilinks]] from a note. It is categorised as a Read tool in the Mcp Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Mcp Obsidian MCP server in PolicyLayer and add a rule for get_outlinks: 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 Mcp Obsidian. Nothing to install.
get_outlinks 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_outlinks 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_outlinks. 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_outlinks is provided by the Mcp Obsidian MCP server (jkang8/mcp-obsidian). 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 →