compute_attribution
AI agents call compute_attribution to retrieve information from Portfolio Rotation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
With no description available, classification is based on the tool name alone. 'Compute attribution' in a portfolio context typically refers to performance attribution — calculating how much each holding or factor contributed to portfolio returns. This is a read/analytical operation with no apparent side effects. However, confidence is low due to the empty description.
From the tool's definition Tool name 'compute_attribution' and empty description. In portfolio analysis context, attribution typically means performance attribution analysis (calculating returns, factor contributions, etc.).
Attacks that exploit this kind of access
compute_attribution. It is categorised as a Read tool in the Portfolio Rotation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Portfolio Rotation MCP Server MCP server in PolicyLayer and add a rule for compute_attribution: 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 Portfolio Rotation MCP Server. Nothing to install.
compute_attribution 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 compute_attribution 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 compute_attribution. 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.
compute_attribution is provided by the Portfolio Rotation MCP Server MCP server (mothanaprime/rebalance-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 →