Tropicalia MCP Server
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Tropicalia MCP Server search for 'renewable energy' using neural strategy, limit to 5"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Tropicalia MCP Server
MCP server exposing Tropicalia search functionality to AI assistants.
Installation
npm install -g tropicalia-mcpOr use directly with npx:
npx tropicalia-mcpRelated MCP server: search-context
Configuration
Environment Variables
Variable | Description | Default |
| API key for authentication | (required) |
| Project ID for this connection | (required) |
Claude Desktop Configuration
{
"mcpServers": {
"tropicalia": {
"command": "npx",
"args": ["-y", "tropicalia-mcp"],
"env": {
"TROPICALIA_API_KEY": "tr_xxx",
"TROPICALIA_PROJECT": "prj_xxx"
}
}
}
}Available Tools
search
Search documents in a Tropicalia project.
Parameters:
query(required): Search query textstrategy: Retrieval strategy -hybrid(default),neural, orkeywordlimit: Maximum results (1-300, default: 50)generate_answer: Generate AI answer from results (default: true)expand_query: Generate query variations for better recall (default: false)include_sources: Include source documents in response (default: true)
get_config
Display current configuration and available tools.
Development
# Install dependencies
npm install
# Run with MCP inspector
npm run dev
# Run tests
npm test
# Type check
npm run typecheck
# Build
npm run buildAvailable Tools
2 toolsget_configB
Get current Tropicalia MCP configuration
Inputs: no named parameters.
searchA
Search documents in a Tropicalia project.
Available Parameters:
query: Search query text (required)strategy: 'hybrid' | 'neural' | 'keyword' (default: hybrid)expand_query: Generate query variations for better recall (default: false)generate_answer: AI-generated completion from results (default: true)limit: Maximum results 1-300 (default: 50)include_sources: Include source documents in response (default: true)
Natural Language Examples:
"Use neural search for semantic similarity" → strategy: "neural"
"Search without expanding the query" → expand_query: false
"Just return results, no AI summary" → generate_answer: false
"Get more results" → limit: 100
"Only give me the answer" → include_sources: false
Inputs: query (required), limit, strategy, expand_query, +2 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools serve completely different purposes: `search` performs document queries while `get_config` retrieves server configuration. There is no possible confusion between them.
Both names use imperative verbs, but one is a bare verb (`search`) while the other follows a verb_noun pattern (`get_config`). This is a minor deviation from a consistent pattern.
With only 2 tools, the server feels thin for a general-purpose 'Tropicalia MCP Server'. However, the tools cover the core search and configuration needs, so it is borderline rather than severely under-scoped.
The search tool is feature-rich with multiple strategies and options, and `get_config` covers configuration. Missing operations like listing indexes or managing documents are minor gaps that agents can work around.
Maintenance
Related MCP Connectors
Search the Cerebrium docs: deployment, cerebrium.toml, hardware, endpoints. Also sends feedback.
Read-only search over the aidata.stream documentation, blog, changelog, pricing and FAQ.
Search the PolyAI docs, including the Dialog-RSN-1 realtime voice API. No API key needed.
Semantic search over the current Dodo Payments documentation. No authentication required.
Related MCP Servers
AlicenseNot gradedqualityNot gradedmaintenanceEnables semantic search of project documentation using hybrid vector and full-text search with fast and deep query modes for immediate results or complex multi-round synthesis.MIT- AlicenseAqualityFmaintenanceEnables semantic search across documentation stored in Gemini FileSearchStores, returning AI-generated answers with source citations.11MIT
- FlicenseNot gradedqualityDmaintenanceEnables searching a knowledge base and asking grounded questions with hybrid retrieval, reranking, and cited answers.-
- AlicenseAqualityCmaintenanceEnables LLM hosts to perform grounded, cited retrieval and answer generation over your own documents using hybrid BM25 and dense search, with explicit refusal when answers are not supported by the sources.56 npmMIT