Score a tweet draft (0-100) based on X
AI agents call score_tweet to retrieve information from X Algorithm Toolkit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes and retrieves a score for a provided tweet draft without modifying data, executing code, triggering external operations, or causing financial transactions. It is a query/analysis function analogous to search or fetch operations. The 'actual algorithm weights' suggests it performs read-only computation on provided input.
From the tool's definition Tool description states it 'Score[s] a tweet draft (0-100) based on X' - a pure scoring/analysis operation with no modification, deletion, or execution of external commands.
Attacks that exploit this kind of access
Score a tweet draft (0-100) based on X. It is categorised as a Read tool in the X Algorithm Toolkit MCP Server, which means it retrieves data without modifying state.
Register the X Algorithm Toolkit MCP server in PolicyLayer and add a rule for score_tweet: 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 X Algorithm Toolkit. Nothing to install.
score_tweet 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 score_tweet 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 score_tweet. 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.
score_tweet is provided by the X Algorithm Toolkit MCP server (mrchartist/x-algorithm-toolkit). 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 →