Search for tours and activities by location
AI agents call activities_search to retrieve information from Travel Amadeus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches for activity data based on location parameters. Search operations are read-only and return information without modifying, deleting, or executing external actions. No financial transactions, code execution, or data modifications occur. The blast radius of misuse is minimal—worst case being irrelevant or excessive search queries.
From the tool's definition Tool name 'activities_search' and description 'Search for tours and activities by location' indicate a query/search operation that retrieves data without side effects.
Attacks that exploit this kind of access
Search for tours and activities by location. It is categorised as a Read tool in the Travel Amadeus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Travel Amadeus MCP Server MCP server in PolicyLayer and add a rule for activities_search: 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 Travel Amadeus MCP Server. Nothing to install.
activities_search 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 activities_search 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 activities_search. 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.
activities_search is provided by the Travel Amadeus MCP Server MCP server (prathush21/travel-amadeus-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 →