get_recent
AI agents call get_recent to retrieve information from Obsidian MCP (pgvector + Ollama, self-hosted) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool likely retrieves a list or index of recent notes without modifying state. No side effects or data mutation is implied. While the description is empty, the naming convention and sibling tools strongly indicate a read-only retrieval operation with minimal blast radius if misused—an AI agent invoking this would only access metadata about recent activity, not alter data or execute arbitrary operations.
From the tool's definition Tool name 'get_recent' indicates retrieval of recently accessed or modified notes. The verb 'get' is characteristic of Read operations.
Attacks that exploit this kind of access
get_recent. It is categorised as a Read tool in the Obsidian MCP (pgvector + Ollama, self-hosted) MCP Server, which means it retrieves data without modifying state.
Register the Obsidian MCP (pgvector + Ollama, self-hosted) MCP server in PolicyLayer and add a rule for get_recent: 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 (pgvector + Ollama, self-hosted). Nothing to install.
get_recent 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_recent 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_recent. 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_recent is provided by the Obsidian MCP (pgvector + Ollama, self-hosted) MCP server (maxkuminov/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 →