壊れたリンクの検出と修復支援を行います
AI agents call find_broken_links 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 vault structure to identify broken references (read operation), then provides repair suggestions. While it may assist with corrections, the actual modification would require a separate action (likely update_note or link_notes). Detection and analysis of data without side effects falls under the Read category.
From the tool's definition find_broken_links detects broken links and provides repair assistance. The description indicates inspection/analysis of links rather than modification or deletion. The tool searches for and reports link issues without directly altering vault content.
Attacks that exploit this kind of access
壊れたリンクの検出と修復支援を行います. 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 find_broken_links: 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.
find_broken_links 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 find_broken_links 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 find_broken_links. 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.
find_broken_links is provided by the Obsidian MCP Server MCP server (libra850/obsidian-mcp-server). 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 →