SearchMCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JSON_LOGS | No | Output logs in JSON format | false |
| LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR) | INFO |
| SEARXNG_URL | No | SearxNG server URL | http://localhost:8080 |
| SEARXNG_TIMEOUT | No | Request timeout in seconds | 10 |
| FALLBACK_ENABLED | No | Enable Google scraping fallback | true |
| RATE_LIMIT_PERIOD | No | Rate limit period in seconds | 60 |
| MAX_CONTENT_LENGTH | No | Max characters in fetched content | 10000 |
| RATE_LIMIT_REQUESTS | No | Max requests per period | 30 |
| DEFAULT_SEARCH_LIMIT | No | Default number of search results | 5 |
| SEARCH_MAX_CANDIDATES | No | Maximum candidates before reranking | 30 |
| SEARCH_GENERAL_ENGINES | No | Engines for general queries (empty = SearxNG defaults) | |
| SEARCH_SECURITY_ENGINES | No | Engines used for security/CVE queries | brave,bing,duckduckgo,wikipedia,github,stackoverflow |
| SEARCH_MIN_QUALITY_SCORE | No | Security-query quality threshold for fallback merge | 2.5 |
| SEARCH_ENGINE_PROFILE_MODE | No | Query-aware engine profile mode (auto or off) | auto |
| FETCH_ALLOW_PRIVATE_NETWORK | No | Allow fetching localhost/private network URLs | false |
| SEARCH_CANDIDATE_MULTIPLIER | No | Candidate expansion before reranking | 5 |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchC | Search the web for information. Returns relevant search results with titles, URLs, and descriptions. |
| fetch_contentB | Fetch and extract readable content from a URL. Returns content as markdown. |
| get_suggestionsB | Get search query suggestions. Useful for autocomplete or query refinement. |
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/MachineLearning-Nerd/SearchMCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server