MiniApp CDP MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_network_requestsA | List network requests for the currently selected miniapp target/session since MCP started monitoring it. Results are sorted newest-first. By default returns the 20 most recent requests; use page_size/page_idx to paginate. Pass reqid to get a single request's full details. On first call it automatically connects to the endpoint, infers the target, attaches only that target, enables Network on that target session, and starts collecting XHR/Fetch requests. |
| get_response_bodyA | Get the response body for a request returned by list_network_requests. If session_id is omitted, it is inferred from the monitored request cache. |
| get_request_initiatorB | Gets the JavaScript call stack that initiated a network request. This helps trace which code triggered an API call. |
| list_scriptsA | Lists all JavaScript scripts loaded in the current page. Returns script ID, URL, and source map information. Use this to find scripts before setting breakpoints or searching. |
| get_script_sourceB | Gets a snippet of a JavaScript script source by URL (recommended) or script ID. Supports line range (for normal files) or character offset (for minified single-line files). |
| save_script_sourceC | Saves the full source code of a JavaScript script to a local file. |
| search_in_sourcesB | Searches for a string or regex pattern in all loaded JavaScript sources. Returns matching lines with script ID, URL, and line number. |
| evaluate_scriptC | Evaluates a JavaScript expression in the current context. If execution is paused, it automatically evaluates in the paused call frame context. |
| get_websocket_messagesB | Lists WebSocket connections or gets messages for a specific connection. Without wsid, lists all connections. With wsid, gets messages. |
| break_on_xhrA | Sets a breakpoint that triggers when an XHR/Fetch request URL contains the specified string. |
| remove_xhr_breakpointC | Removes an XHR/Fetch breakpoint. |
| pause_or_resumeB | Toggles JavaScript execution. If paused, resumes execution. If running, pauses execution. |
| get_paused_infoA | Gets information about the current paused state including call stack, current location, and scope variables. Use this after a breakpoint is hit to understand the execution context. |
| set_breakpoint_on_textA | Finds a text string in all loaded scripts and sets a breakpoint at that location. CRITICAL AI WORKFLOW WARNING: Do NOT set breakpoints on function names or assignment statements (e.g., 'funcName = function'). In minified code, this will break on the one-time assignment rather than the execution. Instead, ALWAYS use get_script_source to read the function body first, then set the breakpoint on a specific statement INSIDE the function body (e.g., 'var x=', 'return'). |
| remove_breakpointB | Removes a breakpoint by its ID. |
| list_breakpointsB | Lists all active XHR and code breakpoints. |
| stepB | Controls execution when paused. action must be one of: 'over', 'into', 'out'. |
| list_targetsB | Lists all available targets (WebView threads, AppService threads, etc.) in the connected debugger. |
| switch_targetB | Switches the CDP connection to a different target thread (e.g. from WebView to AppService) to debug different parts of the miniapp. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Most tools have distinct purposes with clear boundaries, such as break_on_xhr for XHR breakpoints versus set_breakpoint_on_text for code breakpoints. However, some overlap exists between list_breakpoints and remove_breakpoint/remove_xhr_breakpoint, as they all manage breakpoints but with different granularities, which could cause minor confusion in selection.
Tool names follow a highly consistent verb_noun or verb_noun_noun pattern throughout, such as list_network_requests, get_paused_info, and remove_xhr_breakpoint. There are no deviations in style or convention, making the set predictable and easy to navigate.
With 19 tools, the count is slightly high but reasonable for a comprehensive debugging and monitoring server for miniapps. It covers various aspects like breakpoints, network requests, and script analysis without feeling excessively bloated, though it might be borderline for some use cases.
The toolset provides complete coverage for debugging miniapps, including breakpoint management, network monitoring, script inspection, and execution control. There are no obvious gaps; tools like step, pause_or_resume, and switch_target ensure full lifecycle support for debugging workflows.