Secret MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MAX_BROWSERS | No | Maximum number of browsers used for general extraction | 3 |
| BROWSER_TYPES | No | Browsers used for general search and extraction | chromium,firefox |
| DEFAULT_TIMEOUT | No | Timeout for general HTTP and browser requests | 6000 |
| BROWSER_HEADLESS | No | Whether Playwright runs headlessly | true |
| MAX_CONTENT_LENGTH | No | Maximum page-body length extracted from a general webpage | 500000 |
| SECRET_MCP_WEB_HOST | No | Web-server bind address | 127.0.0.1 |
| SECRET_MCP_WEB_PORT | No | Web-server port | 4317 |
| SECRET_MCP_WEB_ORIGIN | No | Web-viewer address included in MCP results | http://127.0.0.1:4317 |
| DEBUG_BROWSER_LIFECYCLE | No | Whether to print browser lifecycle logs | false |
| DESIGN_INDEX_OUTPUT_DIR | No | Directory where generated documents are stored | ./design-index |
| MCP_SAMPLING_TIMEOUT_MS | No | Timeout for each independent per-work LLM request in milliseconds | 1800000 |
| FORCE_MULTI_ENGINE_SEARCH | No | Whether to compare every engine during general search | false |
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| full-web-searchA | Search the web and fetch complete page content from top results. This is the most comprehensive web search tool. It searches the web and then follows the resulting links to extract their full page content, providing the most detailed and complete information available. Use get-web-search-summaries for a lightweight alternative. |
| search-gdweb-designsA | Use this tool only when the user wants a lightweight list of GDWEB references. It applies the dashboard-managed exclusion list before returning results, returns metadata for multiple results, and does not generate implementation documents. For layout analysis, frontend specifications, DESIGN_INDEX files, or implementation planning, use generate-gdweb-design-indexes instead so every result is processed by a separate isolated LLM request. |
| generate-gdweb-design-indexesA | Automatically use this tool when the user asks to find GDWEB references and create layout analysis, frontend specifications, implementation plans, or DESIGN_INDEX files. This tool applies the dashboard-managed exclusion list, performs the GDWEB search internally, and sends one completely separate MCP sampling/createMessage request per non-excluded result. Each isolated request contains only one result and has no previous-result context. It writes one page-by-page, measurement-first DESIGN_INDEX_gdweb-.md file before starting the next request, then returns only file paths and statuses to the calling LLM. Never replace this tool with search-gdweb-designs plus a combined summary. The connected MCP client must support sampling. |
| get-web-search-summariesA | Search the web and return only the search result snippets/descriptions without following links to extract full page content. This is a lightweight alternative to full-web-search for when you only need brief search results. For comprehensive information, use full-web-search instead. |
| get-single-web-page-contentA | Extract and return the full content from a single web page URL. This tool follows a provided URL and extracts the main page content. Useful for getting detailed content from a specific webpage without performing a search. |
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 5 tools
The tools are largely distinct: full-web-search and get-web-search-summaries are explicit alternatives for comprehensive vs lightweight results, and get-single-web-page-content handles a specific URL without searching. The two GDWEB tools could be confused at first glance, but their descriptions strongly differentiate metadata listing from file generation.
Most tools follow a hyphenated verb-noun pattern (search-gdweb-designs, generate-gdweb-design-indexes, get-web-search-summaries, get-single-web-page-content). The exception is full-web-search, which uses an adjective-noun form rather than a verb, creating a minor inconsistency.
Five tools is a well-scoped set for a web search and GDWEB reference server. Each tool has a distinct role—comprehensive search, snippet search, single-page fetch, lightweight GDWEB listing, and GDWEB index generation—so none feel redundant.
The surface covers the core workflows: broad web search with two detail levels, direct page extraction, and the specialized GDWEB design-index generation pipeline. Minor gaps exist around managing the dashboard exclusion list or retrieving previously generated index files, but agents can work around these.