mcp-search-kivest
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KIVEST_API_KEY | No | Optional API key for extended features and higher rate limits. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| kivest_searchA | Search the web using Kivest AI Search API. Supports multiple AI models including GPT-5.1 and LLaMA 3.1 8B. Rate limited to 5 requests per minute with automatic queuing and retry. Models:
Best for: Current events, factual queries, general knowledge. |
| kivest_search_streamA | Search the web using Kivest AI Search API with streaming response. Returns response tokens as they are generated for real-time feedback. Supports the same models as kivest_search. |
| kivest_statsA | Get current rate limiter statistics including queue size and token availability |
| kivest_modelsA | List available AI models and their rate limits |
| kivest_web_searchA | Search the web and get search results with titles, URLs, and snippets |
| kivest_image_searchA | Search for images and get results with image URLs, titles, and sources |
| kivest_video_searchA | Search for videos and get results with video URLs, thumbnails, and sources |
| kivest_news_searchA | Search for news articles and get results with titles, sources, and publication dates |
| kivest_scrape_webA | Scrape a website and return clean markdown content |
| kivest_usageA | Get usage statistics for all endpoints |
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 10 tools
Multiple search tools (kivest_search, kivest_search_stream, kivest_web_search) overlap in purpose, with only subtle differences between AI-generated answers, streaming, and raw results. Additionally, kivest_stats and kivest_usage both provide rate/usage information, adding further ambiguity.
All tools share the kivest_ prefix but the naming pattern is inconsistent: some are nouns (models, stats, usage) while others are verb phrases (search, scrape_web, search_stream). Mixed conventions like 'web_search' and 'image_search' vs 'scrape_web' make the set feel less predictable.
Ten tools is a well-scoped size for a search-focused server, covering general search, media-specific searches, scraping, and utility operations without feeling bloated or sparse.
The tool surface covers web, image, video, news, AI search, scraping, and usage monitoring, which is quite complete for a search API. Minor gap: there is no obvious tool for search suggestions or advanced filtering, but the core workflows are well covered.