Fetch a web page with your Badge identity attached. Your Kya-Token header is injected automatically — merchants see you as an authorized actor, not a bot. Your visit is automatically recorded in your shopping journal. Call kya_getAgentIdentity first. Then use this instead of web_fetch when shoppi...
AI agents invoke kya_web_fetch to trigger actions in Payclaw. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool does more than a passive read: it injects authentication tokens into HTTP requests, presents the agent as an authorized actor to merchant sites, and automatically records activity in a shopping journal. These side effects (identity assertion, session establishment with merchants, audit trail creation) elevate it beyond a simple Read.
From the tool's definition 'Fetch a web page with your Badge identity attached. Your Kya-Token header is injected automatically — merchants see you as an authorized actor, not a bot. Your visit is automatically recorded in your shopping journal.'
Attacks that exploit this kind of access
Fetch a web page with your Badge identity attached. Your Kya-Token header is injected automatically — merchants see you as an authorized actor, not a bot. Your visit is automatically recorded in your shopping journal. Call kya_getAgentIdentity first. Then use this instead of web_fetch when shopping at merchant sites. HTTPS only. Returns status, headers, and body (5MB max, 30s timeout). Redirects are not followed — check the Location header if you receive a 3xx status. It is categorised as a Execute tool in the Payclaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Payclaw MCP server in PolicyLayer and add a rule for kya_web_fetch: 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 Payclaw. Nothing to install.
kya_web_fetch is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the kya_web_fetch 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 kya_web_fetch. 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.
kya_web_fetch is provided by the Payclaw MCP server (kyalabs-io/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 →