List all supported countries for bond data.
AI agents call list_bonds_countries to retrieve information from Marketstack MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about supported countries for bond data. It performs a read-only query that returns reference information without modifying, deleting, or executing any operations. The action is informational and safe for an AI agent to invoke.
From the tool's definition Tool name 'list_bonds_countries' and description 'List all supported countries for bond data' indicate a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List all supported countries for bond data. It is categorised as a Read tool in the Marketstack MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Marketstack MCP Server MCP server in PolicyLayer and add a rule for list_bonds_countries: 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 Marketstack MCP Server. Nothing to install.
list_bonds_countries 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 list_bonds_countries 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 list_bonds_countries. 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.
list_bonds_countries is provided by the Marketstack MCP Server MCP server (matteoantoci/mcp-marketstack). 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 →