get_anomaly_history
ML-detected market anomaly log — per anomaly: ts, symbol, score, severity, features dict, natural-language description. 340+ anomalies over 48 days. $0.03
This record as markdown: /tools/de-carbon-cashmere-api-crypto-intelligence/get-anomaly-history.md
What get_anomaly_history does on Crypto Intelligence
AI agents call get_anomaly_history 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
days | integer | — | Look-back days (1-90) |
symbol | string | — | Filter to single coin |
severity | string | — | Min severity: low, medium, high, critical |
Parameters from the server's own tool schema.
Why get_anomaly_history is rated Low
This is a pure data retrieval operation with no side effects. The tool reads from an anomaly log database and returns historical records at a fixed cost ($0.03 per query). There is no capability to modify, delete, execute code, or move funds. The severity is low because misuse would at worst result in repeated queries consuming micropayments, but poses no operational or data integrity risk.
From the tool's definition Tool retrieves historical data on ML-detected market anomalies with timestamps, symbols, scores, severity levels, and descriptions. No modification, deletion, execution, or financial transaction is performed—it only queries and returns existing log records.
Attacks that exploit this kind of access
The rule that runs get_anomaly_history 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_anomaly_history, this is the rule to start with:
get_anomaly_history 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_anomaly_history call is checked against it from then on.
Questions about get_anomaly_history
ML-detected market anomaly log — per anomaly: ts, symbol, score, severity, features dict, natural-language description. 340+ anomalies over 48 days. $0.03. It is categorised as a Read tool in the Crypto Intelligence MCP Server, which means it retrieves data without modifying state.
get_anomaly_history accepts 3 parameters: days, symbol, severity. The full parameter table on this page comes from the server's own tool schema.
Register the Crypto Intelligence MCP server in PolicyLayer and add a rule for get_anomaly_history: 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_anomaly_history 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_anomaly_history 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_anomaly_history. 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_anomaly_history 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