SDW_Search
by DRSFM
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SDW_AUTH_MODE | No | Authenticated download mode: none, persistent, cdp, or experimental extension. | persistent |
| SDW_PROXY_URL | No | Explicit HTTP(S) proxy URL. If empty, the proxy is auto-detected from system settings. | |
| SDW_CACHE_PATH | No | Path to the SQLite cache file. | ~/.sdw-search/cache.sqlite |
| SDW_SEARXNG_URL | No | Comma-separated list of SearXNG instance base URLs. Required if using 'searxng' as a search provider. | |
| SDW_CDP_ENDPOINT | No | Explicit HTTP(S) or WebSocket CDP endpoint required by cdp mode. | |
| SDW_BRAVE_API_KEY | No | API key for Brave Search API. Required if using 'brave' as a search provider. | |
| SDW_MAX_PDF_BYTES | No | Maximum PDF download size in bytes. | 52428800 |
| SDW_REFERENCE_DIR | No | Directory for academic PDF downloads and per-run reports. Defaults to the current working directory's 'reference' folder. | <current directory>/reference |
| SDW_BROWSER_CHANNEL | No | Persistent browser channel: chrome, msedge, or bundled chromium. | chrome |
| SDW_HTTP_TIMEOUT_MS | No | Per-request timeout in milliseconds. | 15000 |
| SDW_MAX_FETCH_BYTES | No | Maximum downloaded page size in bytes. | 5242880 |
| SDW_BROWSER_HEADLESS | No | Whether to run the dedicated browser headless. Use 'true' for headless, but keep false for interactive SSO/MFA. | false |
| SDW_SEARCH_PROVIDERS | No | Comma-separated list of enabled search providers. Defaults to 'auto' which enables configured API providers plus Bing and DuckDuckGo. | auto |
| SDW_BROWSER_PROFILE_DIR | No | Dedicated persistent browser profile directory. Never set this to the daily Chrome/Edge data directory. | %LOCALAPPDATA%/SDW_Search/browser-profile |
| SDW_ALLOW_PRIVATE_NETWORK | No | Whether to allow fetching private network targets. Use 'true' or 'false'. | false |
| SDW_BROWSER_BRING_TO_FRONT | No | Whether to keep automated browser navigation in the background. Use 'true' to bring to foreground. | false |
| SDW_BROWSER_HANDOFF_ENABLED | No | Whether to allow explicit handoff of public URLs to the system default browser. Use 'true' or 'false'. | true |
| SDW_FETCH_CACHE_TTL_SECONDS | No | Fetched page cache lifetime in seconds. | 21600 |
| SDW_SEARCH_CACHE_TTL_SECONDS | No | Search cache lifetime in seconds. | 900 |
| SDW_BROWSER_STARTUP_TIMEOUT_MS | No | Browser launch, connection, and initial navigation timeout in milliseconds. | 30000 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/DRSFM/SDW_Search-MCP-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server