web-search-plus-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXA_API_KEY | No | API key for Exa (Neural), best for semantic discovery and finding similar content. | |
| YOU_API_KEY | No | API key for You.com, used for real-time RAG and LLM-ready snippets. | |
| QUERIT_API_KEY | No | API key for Querit, used for multi-lingual AI search with real-time info. | |
| SERPER_API_KEY | No | API key for Serper (Google), used for facts, news, shopping, and local businesses. | |
| TAVILY_API_KEY | No | API key for Tavily, optimized for deep research, analysis, and explanations. | |
| SEARXNG_BASE_URL | No | Base URL for a self-hosted SearXNG instance (e.g., https://your-searxng-instance.example.com). | |
| PERPLEXITY_API_KEY | No | API key for Perplexity, used for AI-synthesized answers with citations. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchB | Source-only web search through the Web Search Plus v3 runtime. Routes across configured source-result providers. Returns compact sources by default; detail='full' includes the complete v3 evidence and routing contract. |
| web_extractB | Source-only URL extraction through 9 Web Search Plus v3 providers. Returns bounded page text, truncation warnings and stored-content references. Compact by default; detail='full' includes the complete v3 contract. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: web_search finds sources via providers, while web_extract pulls content from a specific URL. There is no meaningful overlap in intent or expected inputs.
Both names follow a consistent web_<verb> snake_case pattern that directly reflects their actions. The convention is predictable and easy for an agent to infer.
Two tools is thin for a server that also exposes provider routing and detail modes, even if the core surface is intentionally focused. It is borderline rather than clearly over- or under-scoped.
Search and extraction cover the primary web-research workflow without dead ends. Minor gaps exist around batch operations or provider introspection, but agents can work around them.