query_inspect
AI agents call query_inspect to retrieve information from Frontmatter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite empty description, the tool name and server context indicate this inspects or queries frontmatter metadata without modification. The '_inspect' suffix typically denotes a read-only diagnostic operation. Confidence is moderate (0.65) due to the missing description; if it performs write operations, severity would increase, but the pattern suggests read-only access.
From the tool's definition Tool name 'query_inspect' suggests inspection/querying of frontmatter metadata; no description provided, but the server description lists 'query' as a sibling tool that 'queries' markdown frontmatter, indicating a read operation pattern.
Attacks that exploit this kind of access
query_inspect. It is categorised as a Read tool in the Frontmatter MCP MCP Server, which means it retrieves data without modifying state.
Register the Frontmatter MCP server in PolicyLayer and add a rule for query_inspect: 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.
query_inspect 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 query_inspect 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 query_inspect. 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.
query_inspect 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 →