openai-search-mcp
by lie5860
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEBUG | No | Debug mode | false |
| FETCH_ENGINE | No | Default fetch engine when fetch_engine is not passed | llm |
| OPENAI_MODEL | No | Model identifier | gpt-4o |
| OPENAI_API_KEY | Yes | API key for your endpoint | |
| OPENAI_API_URL | Yes | OpenAI-compatible API endpoint (must support search) | |
| TAVILY_API_KEY | No | Tavily API key (for web_fetch with fetch_engine=tavily) | |
| TAVILY_API_URL | No | Tavily API base URL | https://api.tavily.com |
| OPENAI_LOG_LEVEL | No | Log level | INFO |
| FIRECRAWL_API_KEY | No | Firecrawl API key (when using firecrawl as default or per call) | |
| FIRECRAWL_API_URL | No | Firecrawl API base URL | https://api.firecrawl.dev/v2 |
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
- 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/lie5860/openai-search-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server