Kindly Web Search MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GITHUB_TOKEN | No | GitHub token for improved GitHub Issue/PR extraction (recommended but optional) | |
| SERPER_API_KEY | No | Serper API key (recommended search provider) | |
| TAVILY_API_KEY | No | Tavily API key (alternative search provider) | |
| SEARXNG_BASE_URL | No | Self-hosted SearXNG base URL (alternative search provider) | |
| KINDLY_DIAGNOSTICS | No | Enable diagnostics (set to 1) (optional) | |
| SEARXNG_USER_AGENT | No | Custom User-Agent for SearXNG requests (optional) | |
| KINDLY_CHROME_PROXY | No | Proxy server for headless Chromium traffic (optional) | |
| SEARXNG_HEADERS_JSON | No | JSON-encoded headers for SearXNG authentication (optional) | |
| KINDLY_CHROME_PROXY_BYPASS | No | Comma-separated hosts to bypass proxy (optional) | |
| KINDLY_NODRIVER_PORT_RANGE | No | Port range for devtools (optional) | |
| KINDLY_NODRIVER_REUSE_BROWSER | No | Set to 0 to disable browser reuse (optional) | |
| KINDLY_BROWSER_EXECUTABLE_PATH | No | Path to browser executable if auto-detection fails | |
| KINDLY_NODRIVER_RETRY_ATTEMPTS | No | Number of browser retry attempts (optional) | |
| KINDLY_HTML_TOTAL_TIMEOUT_SECONDS | No | HTML extraction timeout (optional) | |
| KINDLY_NODRIVER_BROWSER_POOL_SIZE | No | Number of pooled browser instances (optional) | |
| KINDLY_TOOL_TOTAL_TIMEOUT_SECONDS | No | Total timeout per tool call (optional, default 120) | |
| KINDLY_WEB_SEARCH_MAX_CONCURRENCY | No | Max parallel content fetches (optional, default 3) | |
| KINDLY_TOOL_TOTAL_TIMEOUT_MAX_SECONDS | No | Maximum allowed timeout cap (optional, default 600) | |
| KINDLY_NODRIVER_ACQUIRE_TIMEOUT_SECONDS | No | Timeout to acquire pooled browser (optional) | |
| KINDLY_NODRIVER_DEVTOOLS_READY_TIMEOUT_SECONDS | No | DevTools ready timeout in seconds (optional) |
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
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/Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server