Sentiment analysis. POST { text }. Returns overall sentiment (positive/negative/neutral/mixed), a polarity score from -1 to 1, a confidence, and a one-line rationale. For reviews, social posts, support messages, and feedback triage.
AI agents call ai.sentiment to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes and classifies provided text to extract sentiment information, returning analysis results without modifying, deleting, or executing external operations. The POST method is used to submit text for analysis, but no data is created, modified, or destroyed—only read and classified. No code execution, financial transaction, or destructive action occurs. This is a pure analytical Read operation.
From the tool's definition POST { text }. Returns overall sentiment (positive/negative/neutral/mixed), a polarity score from -1 to 1, a confidence, and a one-line rationale.
Attacks that exploit this kind of access
Sentiment analysis. POST { text }. Returns overall sentiment (positive/negative/neutral/mixed), a polarity score from -1 to 1, a confidence, and a one-line rationale. For reviews, social posts, support messages, and feedback triage. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for ai.sentiment: 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 Mcp. Nothing to install.
ai.sentiment 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 ai.sentiment 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 ai.sentiment. 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.
ai.sentiment is provided by the MCP server (@2sio/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 →