browser_form_input_fill

THE RISK

High Risk

Why browser_form_input_fill needs a policy

Filling form inputs is a browser interaction/action that can trigger side effects depending on the form (e.g., search queries, login attempts, data submission). It goes beyond passive reading and constitutes an Execute-level operation. Combined with sibling tools like browser_click and browser_evaluate, this is clearly part of an automated browser control suite.

From the tool's definition 'Fill out an input field' — the tool performs a browser action that interacts with web page elements, triggering external operations on web forms

Documented attack patterns abuse exactly the kind of access browser_form_input_fill gives an agent:

POLICY

How to control browser_form_input_fill

PolicyLayer is an MCP gateway — it sits between your AI agents and Search, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_form_input_fill:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_form_input_fill": {
      "limits": [
        {
          "counter": "browser_form_input_fill_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

browser_form_input_fill 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.

Create a free account and register Search — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Search tools

Destructive browser_close_tab Close the current tab Execute browser_evaluate Execute JavaScript in the browser console Execute browser_navigate Navigate to a URL Execute browser_new_tab Open a new tab Execute run_command Run a command on this Execute run_script Run a script on this Execute browser_go_back Go back to the previous page Execute browser_go_forward Go forward to the next page

All 36 Search tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

Govern code and CI agents → Branch allowlists, approval on merges, and rate caps on the build and pipeline tools agents trigger.
High-risk tools in Search → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →
PolicyLayer vs alternatives → How deterministic, per-call MCP policy compares with gateways, identity layers, and authorisation platforms.

FAQ

Questions about browser_form_input_fill

What does the browser_form_input_fill tool do? +

Fill out an input field, before using the tool, Either. It is categorised as a Execute tool in the Search MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_form_input_fill? +

Register the Search MCP server in PolicyLayer and add a rule for browser_form_input_fill: 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 Search. Nothing to install.

What risk level is browser_form_input_fill? +

browser_form_input_fill is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit browser_form_input_fill? +

Yes. Add a rate_limit block to the browser_form_input_fill 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.

How do I block browser_form_input_fill completely? +

Set action: deny in the PolicyLayer policy for browser_form_input_fill. 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.

What MCP server provides browser_form_input_fill? +

browser_form_input_fill is provided by the Search MCP server (@agent-infra/mcp-server-search). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Search tool call.

Start from Search, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →