Get a single swipe by ID.
AI agents call get_swipe to retrieve information from SwipeBuilder MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a straightforward data retrieval operation on an existing swipe (ad) by its identifier. It has no side effects, does not modify data, execute code, delete anything, or involve financial transactions. It is a simple Read operation with minimal blast radius if misused—at worst, an unauthorized user could enumerate and view ad content they should not access, but no data would be altered or destroyed.
From the tool's definition Tool name 'get_swipe' with description 'Get a single swipe by ID' clearly retrieves a single saved ad record. The server description confirms this is about 'retrieve saved ads' with no mention of modification or deletion.
Attacks that exploit this kind of access
Get a single swipe by ID. It is categorised as a Read tool in the SwipeBuilder MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SwipeBuilder MCP Server MCP server in PolicyLayer and add a rule for get_swipe: 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 SwipeBuilder MCP Server. Nothing to install.
get_swipe 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_swipe 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_swipe. 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_swipe is provided by the SwipeBuilder MCP Server MCP server (swipebuilder-io/swipebuilder-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 →