index_refresh
AI agents invoke index_refresh to trigger actions in Frontmatter MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool name 'index_refresh' suggests it triggers a re-indexing operation on the document store or DuckDB index. In the context of this server (which indexes Markdown frontmatter and supports semantic search), refreshing an index is an active operation that re-processes or rebuilds data structures — more than a simple read, but likely reversible. With no description available, confidence is reduced.
From the tool's definition Tool name: index_refresh; description is empty and uninformative.
Attacks that exploit this kind of access
index_refresh. It is categorised as a Execute tool in the Frontmatter MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Frontmatter MCP server in PolicyLayer and add a rule for index_refresh: 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 Frontmatter MCP. Nothing to install.
index_refresh is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the index_refresh 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 index_refresh. 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.
index_refresh is provided by the Frontmatter MCP server (kzmshx/frontmatter-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 →