mcpField
V
Valyu MCP Server

Valyu MCP Server

Local
github.com/valyu-networkSearch0Updated 86w ago
Repository

About Valyu MCP Server

A TypeScript MCP server that connects LLMs to Valyu's knowledge retrieval and feedback APIs. It supports searches across proprietary and web sources, as well as feedback submission for transactions.

Key features

  1. 01Search proprietary and web sources
  2. 02Select sources and result limits
  3. 03Set similarity and query rewrite options
  4. 04Submit transaction feedback with sentiment

Use cases

  1. 01Search Valyu sources for a topic
  2. 02Limit or refine knowledge search results
  3. 03Send feedback about a transaction

MCP support

The server exposes Valyu knowledge search and transaction feedback as MCP tools named `knowledge` and `feedback`.

#valyu#mcp#server#api#knowledge-retrieval

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "valyu-mcp-js": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "pull"
      ]
    }
  }
}
Run commanddocker run -i --rm pull

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocipull

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

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 for
      • search_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 over
      • max_num_results (integer): Number of results returned after reranking
      • similarity_threshold (number): Minimum similarity score for included results
      • query_rewrite (boolean): Whether to rewrite the query for better performance

  • feedback - Submit user feedback for a transaction

    • Required arguments:
      • tx_id (string): Transaction ID to provide feedback for
      • feedback (string): User feedback text
      • sentiment (string): Sentiment rating ("very good", "good", "bad", "very bad")

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:

Using Docker 
"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

  1. 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
  }
}
  1. 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

  1. "Can you search for information about artificial intelligence in medicine?"
  2. "I'd like to learn about sustainable energy solutions. Can you search for that?"
  3. "Please help me submit feedback for my transaction with ID TX123456."
  4. "Find me the latest research on climate change adaptation strategies."

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.