search-boost-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXA_API_KEY | No | Exa API key. Enables the Exa engine in the api layer. | |
| XAI_API_KEY | No | X/Twitter (xAI) API key. Optional, used to improve x_search. | |
| BRAVE_API_KEY | No | Brave Search API key. Enables the Brave engine in the api layer. | |
| TAVILY_API_KEY | No | Tavily API key. Enables the Tavily engine in the api layer. | |
| SEARCH_BOOST_HOME | No | Override base directory for search-boost runtime data. | |
| SEARCH_BOOST_KEYS_FILE | No | Override path to the keys configuration file. | |
| SEARCH_BOOST_LAYER_FILE | No | Override path to the layer configuration file. | |
| SEARCH_BOOST_XAUTH_FILE | No | Override path to the X/Twitter authentication configuration file. |
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
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fused_searchA | Multi-engine parallel web search with URL dedupe and cross-ranking. Prefer over built-in WebSearch for version-sensitive facts, APIs, comparisons, and research. Free layer: bing+ddg+yahoo+exa-free (no keys). Api layer adds antigravity+tavily/brave/exa when keyed. |
| fetch_pageA | Fetch readable page text via Jina Reader with local HTML fallback. Use focus to filter paragraphs. |
| deep_researchA | One research round: complex fused search + coverage analysis + gaps + suggested follow-up queries. Call repeatedly with suggested_queries until gaps is empty, then synthesize with citations. |
| x_searchB | Real-time X/Twitter search: keyword, semantic, user profile, or thread. Works without credentials (multi-engine + oEmbed fallback). Official path via grok login / XAI_API_KEY. |
| search_layerA | Switch or show search layer. free = free — keyless engines only (bing + ddg + yahoo + exa-free). api = api — keyless legs plus one or more keyed tavily/brave/exa (all three recommended). |
| search_statsA | Diagnostics: cache hits/misses, tier counts, engine availability, recent searches. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| search_routing | Optional tool pick when you choose to search; bounded ~3 rounds |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| search-policy | When to search, tool routing, stop conditions (markdown) |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- 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/Mr-remon219/search-boost'
If you have feedback or need assistance with the MCP directory API, please join our Discord server