Agent Search MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Log level (info, debug) | |
| BRAVE_API_KEY | No | Brave Search API key (2000 free/month) | |
| TAVILY_API_KEY | No | Tavily API key (1000 free/month) |
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": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| free_searchA | Search the web with automatic fallback between free and paid engines. Phase 1: DuckDuckGo + Sogou (free, no key required). Phase 2: Brave + Tavily (paid, requires BRAVE_API_KEY / TAVILY_API_KEY env vars). All results are deduplicated, scored, and ranked. |
| free_search_advancedA | Advanced search with filters and quality control. Best for: Date ranges, domain filtering, high-confidence only, Chinese content. Not recommended for: Simple queries — use free_search instead. |
| free_extractA | Extract full content from a URL. Returns clean markdown. Best for: Reading a specific page found in search results. Not recommended for: Bulk extraction — use search first. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| capabilities | |
| health |
TDQS
Scored across 3 tools
Each tool has a distinctly different purpose: basic search (free_search), advanced search with filters (free_search_advanced), and content extraction from URLs (free_extract). No overlap.
All tools share the 'free_' prefix. While 'free_search' and 'free_search_advanced' follow a noun-modifier pattern, 'free_extract' uses a verb form, creating a minor inconsistency.
Three tools cover the essential functionality of a search server (search, advanced search, and content extraction) without redundancy or excess.
Core needs are met, but advanced features like pagination, result count control, or batch operations are absent, which could be limiting for complex workflows.