
Valyu MCP Server
Typescript implementation of MCP server for Valyu Network API (
What is Valyu MCP Server?
Valyu MCP Server is a Typescript implementation of a Model Context Protocol server that provides access to Valyu's knowledge retrieval and feedback APIs, enabling LLMs to search proprietary and web sources for information and submit feedback on transactions.
How to use Valyu MCP Server?
To use Valyu MCP Server, you can run it using Docker with your Valyu API key. You can perform knowledge searches and submit feedback for transactions through the provided API endpoints.
Key features of Valyu MCP Server?
- Knowledge search tool to access proprietary and web sources.
- Feedback submission tool for user transactions.
- Configurable via environment variables for easy integration.
Use cases of Valyu MCP Server?
- Searching for information on various topics like quantum computing or artificial intelligence.
- Submitting user feedback on transactions to improve service quality.
- Integrating with applications like Claude.app for enhanced knowledge retrieval.
FAQ from Valyu MCP Server?
- How do I install Valyu MCP Server?
You can install it using Docker with the command:
docker pull ghcr.io/tiovikram/valyu-mcp-server
.
- What is required to run the server?
You need to set the
VALYU_API_KEY
environment variable with your Valyu API key.
- Can I use Valyu MCP Server for any type of search?
Yes, you can search across proprietary, web, or all sources based on your needs.
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."