Grok SearXNG Adapter MCP
by Huakira
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | 对外宿主机绑定端口，默认 8080 | 8080 |
| API_KEY | Yes | LobeHub/Open WebUI 请求本服务时的访问密钥 | |
| GROK_MODEL | Yes | 中转站提供的 Grok 模型名 | |
| MAX_RESULTS | No | 单请求最大结果数，默认 10 | 10 |
| MCP_ENABLED | No | 是否挂载 /mcp，默认 true | true |
| BIND_ADDRESS | No | 对外宿主机绑定地址，默认 127.0.0.1 | 127.0.0.1 |
| GROK_API_KEY | Yes | 本服务请求中转站的密钥 | |
| GROK_API_MODE | No | responses（默认，Grok 服务端 Web Search）或 chat_completions | responses |
| GROK_BASE_URL | Yes | Grok 中转站的 OpenAI 兼容 API 根地址，通常含 /v1 | |
| FETCH_MAX_URLS | No | 单次 web_fetch 最多读取的 URL 数，默认 5 | 5 |
| FETCH_MAX_CHARS | No | 每页返回给 Agent 的正文字符上限，默认 40000 | 40000 |
| REQUEST_TIMEOUT | No | 上游超时秒数，默认 240 | 240 |
| SEARCH_MAX_USES | No | Grok web search 最大工具使用次数，默认、推荐均为 1 | 1 |
| FIRECRAWL_API_KEY | No | 启用 web_fetch 时必填，Firecrawl API 密钥 | |
| FIRECRAWL_TIMEOUT | No | 单次 Firecrawl scrape 超时秒数，默认 60 | 60 |
| FIRECRAWL_BASE_URL | No | Firecrawl API 地址，默认 https://api.firecrawl.dev | https://api.firecrawl.dev |
| MCP_RESEARCH_ENABLED | No | 是否暴露可选的 web_research 工具，默认 false | false |
| GROK_SEARCH_TOOL_TYPE | No | 搜索工具类型，默认 web_search | web_search |
| MAX_RESULTS_PER_DOMAIN | No | 同一域名的最多结果数，默认 3 | 3 |
| UPSTREAM_RETRY_ATTEMPTS | No | 上游 5xx 的最大尝试次数，默认 3 | 3 |
| FIRECRAWL_RETRY_ATTEMPTS | No | Firecrawl 5xx/超时重试次数，默认 2 | 2 |
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/Huakira/search2searxng'
If you have feedback or need assistance with the MCP directory API, please join our Discord server