Extract structured acceptance criteria from a spec body. Looks for
AI agents call parse_spec to retrieve information from Mk Spec Master without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool takes a spec body as input and extracts/parses structured information from it. This is a read/analysis operation with no writes, mutations, deletions, or external calls implied. The description is somewhat brief, slightly lowering confidence, but 'extract' clearly indicates a non-destructive read operation.
From the tool's definition 'Extract structured acceptance criteria from a spec body' — purely reads and parses input content with no side effects
Attacks that exploit this kind of access
Extract structured acceptance criteria from a spec body. Looks for. It is categorised as a Read tool in the Mk Spec Master MCP Server, which means it retrieves data without modifying state.
Register the Mk Spec Master MCP server in PolicyLayer and add a rule for parse_spec: 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 Mk Spec Master. Nothing to install.
parse_spec 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 parse_spec 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 parse_spec. 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.
parse_spec is provided by the Mk Spec Master MCP server (kao273183/mk-spec-master). 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 →