get_model_perf
Cross-coin ML model performance overview — shows which of our models (v3_tsfresh, v3b, v3c, alpha_funding_mr) perform best on which coins over 180-day shadow-prediction history. $0.10
This record as markdown: /tools/de-carbon-cashmere-api-crypto-intelligence/get-model-perf.md
What get_model_perf does on Crypto Intelligence
AI agents call get_model_perf to retrieve information from Crypto Intelligence without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_model_perf is rated Low
This tool retrieves and displays historical model performance data without side effects. It is purely informational—no data is modified, deleted, created, or used to execute trades or financial operations. The tool serves an analytical/reporting purpose typical of Read category tools.
From the tool's definition Tool provides performance metrics ('shows which of our models...perform best') over historical data ('180-day shadow-prediction history'). Description indicates retrieval and reporting of analytics with no modification, deletion, or execution of trades.
Attacks that exploit this kind of access
The rule that runs get_model_perf safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Crypto Intelligence, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_model_perf, this is the rule to start with:
get_model_perf is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Crypto Intelligence, apply this rule, and every get_model_perf call is checked against it from then on.
Questions about get_model_perf
Cross-coin ML model performance overview — shows which of our models (v3_tsfresh, v3b, v3c, alpha_funding_mr) perform best on which coins over 180-day shadow-prediction history. $0.10. It is categorised as a Read tool in the Crypto Intelligence MCP Server, which means it retrieves data without modifying state.
Register the Crypto Intelligence MCP server in PolicyLayer and add a rule for get_model_perf: 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 Crypto Intelligence. Nothing to install.
get_model_perf 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_model_perf 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_model_perf. 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_model_perf is provided by the Crypto Intelligence MCP server (https://api.carbon-cashmere.de/mcp/sse). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Crypto Intelligence, and thousands of servers like it.
This server
Across the catalogue