Click on "Install 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.
MCP server exposing Tropicalia search functionality to AI assistants.
npm install -g tropicalia-mcpOr use directly with npx:
npx tropicalia-mcpRelated MCP server: search-context
Variable | Description | Default |
| API key for authentication | (required) |
| Project ID for this connection | (required) |
{
"mcpServers": {
"tropicalia": {
"command": "npx",
"args": ["-y", "tropicalia-mcp"],
"env": {
"TROPICALIA_API_KEY": "tr_xxx",
"TROPICALIA_PROJECT": "prj_xxx"
}
}
}
}Search documents in a Tropicalia project.
Parameters:
query (required): Search query text
strategy: Retrieval strategy - hybrid (default), neural, or keyword
limit: 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)
Display current configuration and available tools.
# Install dependencies
npm install
# Run with MCP inspector
npm run dev
# Run tests
npm test
# Type check
npm run typecheck
# Build
npm run buildGet current Tropicalia MCP configuration
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility for behavioral disclosure. 'Get' implies a read-only operation, but the description does not explicitly state safety, permissions, side effects, or any additional behavioral traits, leaving significant gaps for a tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with no wasteful content. It is appropriately sized for the simple nature of the tool and front-loads the core action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (zero parameters, no output schema), the description is nearly complete for an agent to understand the tool's purpose. However, it omits details about the return value structure or any authentication requirements, which would enhance completeness for a no-output-schema tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, and schema coverage is effectively 100%. With no parameters to explain, the description is not required to add parameter details, and the baseline of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Get' and identifies the resource as 'current Tropicalia MCP configuration', clearly stating the tool's purpose. It does not explicitly differentiate from the sibling tool 'search', but the distinction is obvious given the different resource types, so it falls short of the top score for explicit sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool compared to alternatives. It simply states what it does without any context on appropriate scenarios, prerequisites, or exclusions, leaving the agent without usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum results (1-300, default: 50) | |
| query | Yes | Search query text | |
| strategy | No | Retrieval strategy: 'hybrid' (default), 'neural' for semantic, 'keyword' for exact match | |
| expand_query | No | Generate query variations for better recall (default: false) | |
| generate_answer | No | Generate AI answer from results (default: true) | |
| include_sources | No | Include source documents in response (default: true) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits itself. It explains how parameters like strategy, expand_query, and generate_answer affect behavior, but it does not describe the overall response format, error handling, or side effects (e.g., whether any state is modified).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-organized with a clear header, parameter list, and examples. Every section is useful, though the examples could be considered slightly verbose for an API description. It is front-loaded with the purpose statement and remains readable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description should explain what the tool returns. It indirectly hints at response composition via include_sources and generate_answer, but it lacks an explicit statement about the response structure, limiting completeness for an agent anticipating the tool's output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, meaning the input schema already fully documents all parameters. The description repeats this information and adds natural language examples, but it does not introduce deeper semantic meaning beyond what the schema provides, so it only slightly compensates.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with 'Search documents in a Tropicalia project,' a clear verb+resource statement that precisely defines the tool's function. This distinct purpose is well differentiated from the sibling tool get_config, which likely handles configuration settings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on how to use the tool, including parameter defaults and natural language examples that illustrate usage scenarios. However, it does not explicitly contrast this tool with get_config or state when not to use it, so it lacks explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0get_configsearchThe 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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search the Cerebrium docs: deployment, cerebrium.toml, hardware, endpoints. Also sends feedback.
Search your knowledge bases from any AI assistant using hybrid RAG.
Search and read Vector Panda docs: API operations, pricing, storage tiers, measured benchmarks.
Search the SiteGPT documentation: setup, features, API reference, troubleshooting.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/tropicalia-ai/tropicalia-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
