Search for a Star Wars character by name
AI agents call search_character to retrieve information from SWAPI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a search query against the SWAPI database to locate characters. It has no side effects—it only returns matching results. No data is created, modified, or destroyed. This is a classic Read operation with minimal blast radius if misused (worst case: information disclosure of public Star Wars character data).
From the tool's definition Tool name is "search_character" and description states it "Search[es] for a Star Wars character by name". This is a read-only query operation that retrieves data without modifying, creating, or deleting anything.
Attacks that exploit this kind of access
Search for a Star Wars character by name. It is categorised as a Read tool in the SWAPI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SWAPI MCP Server MCP server in PolicyLayer and add a rule for search_character: 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 SWAPI MCP Server. Nothing to install.
search_character 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 search_character 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 search_character. 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.
search_character is provided by the SWAPI MCP Server MCP server (olaekdahl/swapi-mcp-server). 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 →