Fetches weekly time series data for a cryptocurrency.
AI agents call crypto_weekly to retrieve information from MCP Avantage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical cryptocurrency price/data in time series format. It is a passive read operation that queries financial data without side effects, creating no positions, executing no trades, or modifying any state. While it provides financial market data, it does not move money or commit financial obligations, so it does not meet the Financial category threshold.
From the tool's definition Tool name 'crypto_weekly' and description 'Fetches weekly time series data for a cryptocurrency' indicate data retrieval with no modification or execution of trades/financial transactions.
Attacks that exploit this kind of access
Fetches weekly time series data for a cryptocurrency. It is categorised as a Read tool in the MCP Avantage MCP Server, which means it retrieves data without modifying state.
Register the MCP Avantage MCP server in PolicyLayer and add a rule for crypto_weekly: 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 Avantage. Nothing to install.
crypto_weekly 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 crypto_weekly 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 crypto_weekly. 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.
crypto_weekly is provided by the MCP Avantage MCP server (missionsquad/mcp-avantage). 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 →