Robot Actions — Remote Device Control

Webpage mock add

webpage_mock_add

Add (or update in place, when id matches an existing route) a mock/abort rule for browser requests on this device. mode "mock" (default) serves the given status/headers/body without the request leaving the device; mode "abort" fails it so the page sees a network error. Routes apply immediately and survive navigation. WEB CONTENT ONLY: this intercepts requests made by browser/WebView pages. Requests made by native app code are NOT intercepted and never will be by this tool. Nothing device-wide is changed and no certificate is installed — the effect is scoped to the page. For requests made by native app code use android_traffic_mock_add / ios_traffic_mock_add instead.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	No	Route id to update in place; omit to auto-generate a new one
`body`	No	Response body for mode "mock" (text, or base64 when bodyEncoding is "base64")
`mode`	No	"mock" serves a canned response (default); "abort" fails the request
`udid`	Yes	Device id (Android serial or iOS UDID)
`method`	No	Optional HTTP method filter (e.g. "GET"/"POST"); matches any method when omitted
`pageId`	No	Pin routing to a specific page id (from the *_list_pages tool). Omit to follow the active page automatically across navigations and new tabs — recommended.
`socket`	No	Abstract unix socket name (default: chrome_devtools_remote)
`status`	No	HTTP status to serve for mode "mock" (default 200)
`delayMs`	No	Latency injected before responding/failing, in ms (clamped to 60s)
`enabled`	No	Whether the route is active (default true) — disabled routes are kept but ignored
`headers`	No	Response headers for mode "mock", as {headerName: value} — e.g. {"content-type": "application/json"}. On iOS a `charset` in content-type is NOT applied to the response: an HTML body with non-ASCII characters must declare it in the document (e.g. <meta charset="utf-8">) or it will be decoded with the default encoding and render as mojibake.
`matchUrl`	Yes	URL pattern to match against the request's full URL
`matchType`	No	How matchUrl is interpreted against the request URL (default "contains")
`bodyEncoding`	No	Encoding of `body` (default "text")

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedAug 18, 2026

changedInput schema / properties / headers / description

Previous value: -"Response headers for mode \"mock\", as {headerName: value} — e.g. {\"content-type\": \"application/json\"}"New value: +"Response headers for mode \"mock\", as {headerName: value} — e.g. {\"content-type\": \"application/json\"}. On iOS a `charset` in content-type is NOT applied to the response: an HTML body with non-ASCII characters must declare it in the document (e.g. <meta charset=\"utf-8\">) or it will be decoded with the default encoding and render as mojibake."

AddedAug 9, 2026

TDQS

A4.7/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true. The description adds substantive traits the annotations cannot convey: routes apply immediately and survive navigation, the effect is page-scoped, no certificate is installed, nothing device-wide changes, and native traffic is never intercepted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and upsert semantics, then scope, then alternatives. It is a long description but nearly every sentence carries distinct information; the 'WEB CONTENT ONLY' emphasis is slightly redundant with the following sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 14-parameter, high-complexity mutation tool with no output schema, it covers scope, side effects, defaults, and sibling routing well. The only gap is that it never hints at what the call returns (e.g., a generated route id), which matters for the upsert flow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning beyond the schema by framing the `id` parameter as an upsert key ('update in place, when `id` matches an existing route') and by stating the default mode. It does not otherwise add syntax or format detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Add ... a mock/abort rule for browser requests on this device') and immediately clarifies the upsert behavior when `id` matches. It explicitly distinguishes itself from android_traffic_mock_add / ios_traffic_mock_add, so an agent can route correctly without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use (browser/WebView requests), when-not-to-use (native app code, 'never will be by this tool'), and names the exact alternative tools for the excluded case. The mode mock vs abort choice is also framed as a decision the caller makes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Robot Actions — Remote Device Control tools Inspect

Try in Browser

Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?