Search for existing images from Pexels or Pixabay. When provider is
AI agents call stock_images_search to retrieve information from TSCodex MCP Images without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries external image databases and returns search results. It performs a read-only operation with no ability to modify, delete, or execute actions. The only potential concern is data availability/rate limiting from the APIs, but this poses minimal security risk to the user's systems or data.
From the tool's definition Tool description states 'Search for existing images from Pexels or Pixabay' - a clear retrieval/query operation with no data modification, deletion, or side effects.
Attacks that exploit this kind of access
Search for existing images from Pexels or Pixabay. When provider is. It is categorised as a Read tool in the TSCodex MCP Images MCP Server, which means it retrieves data without modifying state.
Register the TSCodex MCP Images MCP server in PolicyLayer and add a rule for stock_images_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 TSCodex MCP Images. Nothing to install.
stock_images_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 stock_images_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 stock_images_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.
stock_images_search is provided by the TSCodex MCP Images MCP server (unbywyd/tscodex-mcp-images). 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 →