AllSearch MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ALLSEARCH_XAI_MODEL | No | Primary model name (default grok-4.5) | |
| ALLSEARCH_XAI_API_KEY | Yes | API key for xAI (Grok) primary search | |
| ALLSEARCH_XAI_BASE_URL | Yes | Base URL for xAI compatible endpoint (e.g., https://api.x.ai/v1) | |
| ALLSEARCH_TAVILY_API_KEY | No | API key for Tavily search supplement (optional) | |
| ALLSEARCH_ANYSEARCH_API_KEY | No | API key for AnySearch vertical search (optional) | |
| ALLSEARCH_FIRECRAWL_API_KEY | No | API key for Firecrawl web scraping (optional) | |
| ALLSEARCH_XAI_MAX_TOOL_CALLS | No | Maximum tool calls for Grok (default 4) | |
| ALLSEARCH_XAI_RESPONSES_PATH | No | Path for responses endpoint (default /responses) | |
| ALLSEARCH_XAI_FALLBACK_MODELS | No | Comma-separated fallback model names (default grok-4.3) | |
| ALLSEARCH_XAI_REASONING_EFFORT | No | Reasoning effort level: low, medium, high (default low) | |
| ALLSEARCH_ALLOW_DEGRADED_SEARCH | No | Allow degraded search when Grok is unavailable (default true) |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchB | Orchestrated web search: Grok primary, Tavily/AnySearch/Firecrawl as supplements. |
| fetchB | Fetch full content for a known HTTP(S) URL via Firecrawl (post-discovery assist). |
| healthB | Provider configuration and circuit health. probe=true runs bounded cached probes. |
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 3 tools
Each tool has a distinct purpose: health checks service status, search performs web queries, and fetch retrieves a specific URL. No overlap or ambiguity between them.
All tool names are single lowercase words (health, search, fetch), following a simple and consistent pattern. Though not verb_noun, the style is uniform across the set.
Three tools is an ideal scope for a search service with a health check and content fetching. Each tool serves a clear, non-redundant role.
The tool set covers the full lifecycle of a search workflow: verify service health, execute a search, and fetch full content for follow-up. No obvious missing operations for the stated purpose.