A Model Context Protocol (MCP) server that provides agentic tools for interacting with the Trieve API. This server enables AI agents to search and interact with Trieve datasets through a standardized interface. - Search across Trieve datasets using semantic search - List and access dataset information - Support for both environment variables and command-line arguments - Built with TypeScript for t
Add this skill
npx mdskills install devflowinc/trieveWell-documented MCP server with clear setup and comprehensive search tool descriptions
A Model Context Protocol (MCP) server that provides agentic tools for interacting with the Trieve API. This server enables AI agents to search and interact with Trieve datasets through a standardized interface.
To install Trieve for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install trieve-mcp-server --client claude
npm install trieve-mcp-server
Copy the .env.dist file to .env and fill in your Trieve credentials:
cp .env.dist .env
Required environment variables:
TRIEVE_API_KEY: Your Trieve API key from dashboard.trieve.aiTRIEVE_ORGANIZATION_ID: Your Trieve organization ID from dashboard.trieve.aiOptional environment variables:
TRIEVE_DATASET_ID: Specific dataset ID to use (if not provided via CLI)Command-line arguments (override environment variables):
trieve-mcp-server --api-key --org-id [--dataset-id ]
trieve-mcp-server
Search through a specified Trieve dataset.
Parameters:
query (string): The search querydatasetId (string): ID of the dataset to search insearchType (string, optional): "semantic" (default), "fulltext", "hybrid", or "bm25"filters (object, optional): Advanced filtering optionshighlightOptions (object, optional): Customize result highlightingpage (number, optional): Page number, default 1pageSize (number, optional): Results per page, default 10Example:
{
"query": "example search query",
"datasetId": "your-dataset-id",
"searchType": "semantic",
"page": 1,
"pageSize": 10
}
The server exposes Trieve datasets as resources with the following URI format:
trieve://datasets/{dataset-id}The Trieve MCP Server supports MCP integration with Claude Desktop. Place the following in your Claude Desktop's claude_desktop_config.json.
{
"mcpServers": {
"trieve-mcp-server": {
"command": "npx",
"args": ["trieve-mcp-server@latest"],
"env": {
"TRIEVE_API_KEY": "$TRIEVE_API_KEY",
"TRIEVE_ORGANIZATION_ID": "$TRIEVE_ORGANIZATION_ID",
"TRIEVE_DATASET_ID": "$TRIEVE_DATASET_ID"
}
}
}
}
Note: Instead of environment variables, --api-key, --org-id, and --dataset-id can be used as command-line arguments.
Once Claude Desktop starts, attachments will be available that correspond to the datasets available to the Trieve organization. These can be used to select a dataset. After that, begin chatting with Claude and ask for information about the dataset. Claude will use search as needed in order to filter and break down queries, and may make multiple queries depending on your task.
npm install
.env.dist to .env and configure your credentialsnpm run build
npm run build: Build the TypeScript projectnpm run watch: Watch for changes and rebuildnpm run test: Run testsnpm run inspector: Run the MCP inspector for debuggingMIT
Install via CLI
npx mdskills install devflowinc/trieveTrieve MCP Server is a free, open-source AI agent skill. A Model Context Protocol (MCP) server that provides agentic tools for interacting with the Trieve API. This server enables AI agents to search and interact with Trieve datasets through a standardized interface. - Search across Trieve datasets using semantic search - List and access dataset information - Support for both environment variables and command-line arguments - Built with TypeScript for t
Install Trieve MCP Server with a single command:
npx mdskills install devflowinc/trieveThis downloads the skill files into your project and your AI agent picks them up automatically.
Trieve MCP Server works with Claude Code, Claude Desktop, Cursor, Vscode Copilot, Windsurf, Continue Dev, Codex, Gemini Cli, Amp, Roo Code, Goose, Opencode, Trae, Qodo, Command Code. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.