List all terms currently in the glossary (returns only term names, not full content).
AI agents call list_terms to retrieve information from Obsidian Dictionary 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 and retrieves existing data from the glossary without modifying, executing, or deleting anything. It is a simple enumeration that returns term names only, making it a non-destructive read operation with minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'list_terms' and description 'List all terms currently in the glossary (returns only term names, not full content)' indicate a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
List all terms currently in the glossary (returns only term names, not full content). It is categorised as a Read tool in the Obsidian Dictionary MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Obsidian Dictionary MCP Server MCP server in PolicyLayer and add a rule for list_terms: 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 Dictionary MCP Server. Nothing to install.
list_terms 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 list_terms 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 list_terms. 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.
list_terms is provided by the Obsidian Dictionary MCP Server MCP server (sarahan774/obsidian-dictionary-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 →