CHANGE AWARENESS ENTRY — call FIRST each session. Shows which MD files were recently added, modified, or deleted, grouped into time batches (±15 min). Returns file paths, line ranges, bold/italic/code terms, and heading context. NOT a debug tool — this is how you discover what changed since you l...
AI agents call md_status to retrieve information from Md Graph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
md_status is a querying/discovery tool that provides awareness of file changes. It retrieves state information (which files changed, when, and metadata about those changes) with no side effects. This is a classic Read operation—it discovers and reports data without creating, modifying, executing, or deleting anything.
From the tool's definition Tool description states it 'Shows which MD files were recently added, modified, or deleted' and 'Returns file paths, line ranges, bold/italic/code terms, and heading context.' It retrieves metadata and discovery information about changes without modifying…
Attacks that exploit this kind of access
CHANGE AWARENESS ENTRY — call FIRST each session. Shows which MD files were recently added, modified, or deleted, grouped into time batches (±15 min). Returns file paths, line ranges, bold/italic/code terms, and heading context. NOT a debug tool — this is how you discover what changed since you last looked. For keyword search, use md_search. To read changed files, use your Read tool. It is categorised as a Read tool in the Md Graph MCP Server, which means it retrieves data without modifying state.
Register the Md Graph MCP server in PolicyLayer and add a rule for md_status: 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 Md Graph. Nothing to install.
md_status 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 md_status 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 md_status. 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.
md_status is provided by the Md Graph MCP server (lzmw/md-graph). 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 →