Valyu
Access Valyu's knowledge retrieval and feedback APIs.
Valyu MCP Server
A Model Context Protocol server that provides access to Valyu's knowledge retrieval and feedback APIs. This server enables LLMs to search proprietary and web sources for information and submit feedback on transactions.
Available Tools
-
knowledge- Search proprietary and/or web sources for information- Required arguments:
query(string): The question or topic to search forsearch_type(string): Type of sources to search ("proprietary", "web", or "all")max_price(number): Maximum allowed price per thousand queries (CPM)
- Optional arguments:
data_sources(string[]): List of index names to search overmax_num_results(integer): Number of results returned after rerankingsimilarity_threshold(number): Minimum similarity score for included resultsquery_rewrite(boolean): Whether to rewrite the query for better performance
- Required arguments:
-
feedback- Submit user feedback for a transaction- Required arguments:
tx_id(string): Transaction ID to provide feedback forfeedback(string): User feedback textsentiment(string): Sentiment rating ("very good", "good", "bad", "very bad")
- Required arguments:
Installation
Using Docker
docker pull ghcr.io/tiovikram/valyu-mcp-server
docker run -i --rm -e VALYU_API_KEY=your-api-key ghcr.io/tiovikram/valyu-mcp-server
Configuration
Environment Variables
VALYU_API_KEY(required): Your Valyu API key
Configure for Claude.app
Add to your Claude settings:
"mcpServers": {
"valyu": {
"command": "docker",
"args": ["run", "--pull", "--rm", "-i", "-e", "VALYU_API_KEY", "ghcr.io/tiovikram/valyu-mcp-server"],
"env": {
"VALYU_API_KEY": "<your-valyu-api-key>"
}
}
}
Example Interactions
- Knowledge search:
{
"name": "knowledge",
"arguments": {
"query": "What is quantum computing?",
"search_type": "all",
"max_price": 0.5,
"data_sources": ["valyu/valyu-arxiv", "valyu/valyu-wikipedia"],
"max_num_results": 5
}
}
- Submit feedback:
{
"name": "feedback",
"arguments": {
"tx_id": "12345abcdef",
"feedback": "The information was very helpful and accurate.",
"sentiment": "very good"
}
}
Debugging
You can use the MCP inspector to debug the server:
npx @modelcontextprotocol/inspector node dist/index.js
Examples of Questions for Claude
- "Can you search for information about artificial intelligence in medicine?"
- "I'd like to learn about sustainable energy solutions. Can you search for that?"
- "Please help me submit feedback for my transaction with ID TX123456."
- "Find me the latest research on climate change adaptation strategies."
Related Servers
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
SAP Documentation
Provides offline access to SAP documentation and real-time SAP Community content.
Jolokia MCP Server
A JMX-HTTP bridge for interacting with Java applications using the Jolokia agent.
TestDino MCP
A Model Context Protocol (MCP) server that connects TestDino to AI agents. This server enables you to interact with your TestDino test data directly through natural language commands.
Arduino MCP Server
Control an Arduino board from your computer using AI commands.
LAML MCP Server
Loads and validates LAML (YAML-based markup language) documents via the Model Context Protocol.
Dify Plugin Agent
An agent that supports Function Calling and ReAct for the MCP protocol via HTTP with SSE or Streamable HTTP transport.
AppControl Windows System History
An MCP server that gives AI agents like Claude, Cursor, and Gemini access to historical Windows CPU, GPU, temperature, and privacy data gathered by the AppControl Windows app.
Remote MCP Server (Authless)
An example of a remote MCP server deployable on Cloudflare Workers, without authentication.
MCP Simple Server
A simple MCP server with streamable HTTP transport that supports basic math tools like add and multiply.
JVM MCP Server
A server for monitoring and analyzing Java Virtual Machine (JVM) processes using Arthas, with a Python interface.