Scan a directory of test files for @spec: <ID> tags in
AI agents call auto_link_tests 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 scans test files looking for annotation tags, which is a read/query operation with no apparent side effects. The description is truncated, so there is some uncertainty about whether it also writes linkage data back to a spec system. Given the context of 'bidirectional traceability', it may write links, but the described action is scanning. Confidence is moderate due to the incomplete description.
From the tool's definition 'Scan a directory of test files for `@spec: <ID>` tags' — this is a scanning/reading operation
Attacks that exploit this kind of access
Scan a directory of test files for @spec: <ID> tags in. 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 auto_link_tests: 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.
auto_link_tests 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 auto_link_tests 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 auto_link_tests. 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.
auto_link_tests 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 →