AI agents call get_qa_recommendations to retrieve information from Blop without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to query or retrieve QA recommendations from the release confidence control plane, consistent with Read operations (search, list, get, fetch). However, the empty description and potential for recommendations to influence critical release decisions via a 'go/no-go' system elevates severity to medium.
From the tool's definition Tool name 'get_qa_recommendations' indicates retrieval of QA-related recommendations; no action verbs like 'execute', 'delete', or 'modify' present. Description is empty, limiting certainty.
Attacks that exploit this kind of access
get_qa_recommendations. It is categorised as a Read tool in the Blop MCP Server, which means it retrieves data without modifying state.
Register the Blop MCP server in PolicyLayer and add a rule for get_qa_recommendations: 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 Blop. Nothing to install.
get_qa_recommendations 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 get_qa_recommendations 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 get_qa_recommendations. 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.
get_qa_recommendations is provided by the Blop MCP server (n2400813g/blop-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 →