summarize_by_label
AI agents call summarize_by_label to retrieve information from KeyNeg MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to summarize or retrieve data grouped by labels from the sentiment analysis results. No description provided limits confidence slightly, but the semantic context (sentiment analysis, sibling read-only operations like get_sentiment_labels, get_usage_info) indicates a retrieval operation without side effects.
From the tool's definition Tool name 'summarize_by_label' and context as part of a sentiment analysis server with sibling tools like analyze_sentiment, extract_keywords, and get_sentiment_labels suggest data retrieval and summarization operations.
Attacks that exploit this kind of access
summarize_by_label. It is categorised as a Read tool in the KeyNeg MCP Server MCP Server, which means it retrieves data without modifying state.
Register the KeyNeg MCP Server MCP server in PolicyLayer and add a rule for summarize_by_label: 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 KeyNeg MCP Server. Nothing to install.
summarize_by_label 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 summarize_by_label 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 summarize_by_label. 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.
summarize_by_label is provided by the KeyNeg MCP Server MCP server (osseni94/keyneg-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 →