browse_solve_challenge
If the current page is gated by a CAPTCHA: solve via the configured pluggable solver (Tier-1, BYO provider+key, governed by standing) and inject the token; if none configured or it's a genuine human-gate, returns a HITL-handoff verdict (Tier-2).
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/browse-solve-challenge.md
What browse_solve_challenge does on Gateway
AI agents invoke browse_solve_challenge to trigger actions in Gateway. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
browser_id | string | Yes | from browse_open |
Parameters from the server's own tool schema.
Why browse_solve_challenge is rated High
This tool executes an external CAPTCHA-solving service and injects tokens into a live browser session, constituting an active external operation. It is not merely reading data; it manipulates the browser state and interacts with third-party services. Misuse could enable bypassing security gates on arbitrary websites, hence high severity.
From the tool's definition 'solve via the configured pluggable solver... and inject the token' — actively executes CAPTCHA-solving logic and injects results into a browser session; triggers external operations via BYO provider
Attacks that exploit this kind of access
The rule that runs browse_solve_challenge safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browse_solve_challenge, this is the rule to start with:
browse_solve_challenge stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every browse_solve_challenge call is checked against it from then on.
Questions about browse_solve_challenge
If the current page is gated by a CAPTCHA: solve via the configured pluggable solver (Tier-1, BYO provider+key, governed by standing) and inject the token; if none configured or it's a genuine human-gate, returns a HITL-handoff verdict (Tier-2). It is categorised as a Execute tool in the Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
browse_solve_challenge accepts 1 parameter: browser_id. Required: browser_id. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for browse_solve_challenge: 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 Gateway. Nothing to install.
browse_solve_challenge 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 browse_solve_challenge 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 browse_solve_challenge. 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.
browse_solve_challenge is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
Across the catalogue