Schema | multsearch-mcp

multsearch-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`NO_PROXY`	No	Comma-separated hosts to bypass proxy (e.g., localhost,127.0.0.1,ark.cn-beijing.volces.com)
`HTTP_PROXY`	No	HTTP proxy for accessing Tavily/Firecrawl/Gemini (e.g., http://127.0.0.1:7890)
`MULT_DEBUG`	No	Enable detailed debug logging	false
`MULT_MODEL`	No	LLM model name, can be switched via switch_model tool	glm-5.2
`HTTPS_PROXY`	No	HTTPS proxy for accessing Tavily/Firecrawl/Gemini
`GEMINI_MODEL`	No	Gemini model name	gemini-2.5-flash
`MULT_API_KEY`	Yes	Required API key for the LLM provider
`MULT_API_URL`	No	OpenAI-compatible endpoint (e.g., https://ark.cn-beijing.volces.com/api/plan/v3)
`MULT_LOG_DIR`	No	Directory for log output	~/.config/multsearch/logs
`MULT_PROVIDER`	No	Provider: custom or ark (preset by setup wizard)	custom
`GEMINI_API_KEY`	No	Optional Gemini API key for gemini_search (second search path)
`MULT_LOG_LEVEL`	No	Log level: DEBUG, INFO, WARNING, ERROR	INFO
`TAVILY_API_KEY`	No	Optional Tavily API key for web_search and web_fetch/web_map
`MULT_MAX_TOKENS`	No	Maximum tokens for LLM responses (e.g., 8192 for reasoning models)
`FIRECRAWL_API_KEY`	No	Optional Firecrawl API key for web_search and web_fetch fallback

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/liujp2015/multsearch-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server