Reka Research MCP Server
OfficialClick 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., "@Reka Research MCP ServerVerify the claim: Paris is the capital of France."
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.
Reka Research MCP Server
A Model Context Protocol (MCP) server providing AI-powered fact-checking and similarity search using Reka Research API. This server is hosted remotely and ready to use - no local installation required!

Prerequisites
Get your Reka API key at platform.reka.ai
Your API key should have access to
reka-flash-researchmodel
Related MCP server: Exa MCP Server
🚀 Using the Hosted MCP Server
The Reka Research MCP server is hosted at https://mcp-server-nine-bice.vercel.app/mcp and ready to use. Simply configure your MCP client to connect to this endpoint.
Claude Desktop
Add this configuration to your Claude Desktop claude_desktop_config.json file:
{
"mcpServers": {
"reka-research": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://reka-research-mcp.vercel.app/mcp",
"--header",
"Authorization: Bearer $REKA_API_KEY"
],
"env": {
"REKA_API_KEY": "<your-reka-api-key-here>"
}
}
}
}VS Code with MCP Extension
Configure the MCP extension in VS Code by adding this to your settings:
{
"servers": {
"reka-research": {
"url": "https://mcp-server-nine-bice.vercel.app/mcp",
"type": "http",
"headers": {
"Authorization": "Bearer ${input:reka-api-key}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "reka-api-key",
"description": "Reka API Key",
"password": true
}
]
}🛠️ Available Tools
verify_claim
Fact-check statements and claims using advanced AI analysis.
Input:
claim(string) - The statement to verifyOutput: JSON with verdict (true/false/uncertain), confidence score (0-1), and detailed reasoning
Example usage:
Can you verify this claim: "The Great Wall of China is visible from space with the naked eye"find_similar
Find similar items based on specific attributes using agentic analysis.
Input:
target(string) - The item to find similarities forattribute(string) - The comparison attribute (e.g., "functionality", "style", "purpose")
Output: Analysis with similar items and explanations
Example usage:
Find items similar to "ChatGPT" based on "functionality"🔧 Troubleshooting
Authentication errors: Ensure your Reka API key is valid and has access to the
reka-flash-researchmodelConnection issues: Verify the server URL is correct:
https://mcp-server-nine-bice.vercel.app/mcpTool not found: Make sure your MCP client supports the tools interface
🏠 Local Development
For developers who want to run the server locally or contribute to the project.
Prerequisites
Node.js 18+
pnpm package manager
Reka API key (set as
REKA_API_KEYenvironment variable)
Setup
# Clone the repository
git clone https://github.com/reka-ai/reka-research-mcp.git
# Install dependencies
pnpm install
# Set your API key
export REKA_API_KEY="your-reka-api-key"
# Start development server
pnpm run devAvailable Scripts
pnpm install # Install dependencies
pnpm run build # Type check the code
pnpm run test # Test with remote server
pnpm run test:http # Test HTTP endpoints locally
pnpm run deploy # Deploy to VercelLocal Testing
Test the local server:
# Start local development server (usually on port 3000)
pnpm run dev
# In another terminal, test the MCP endpoints
node scripts/test-client.mjs http://localhost:3000
# Test HTTP endpoints directly
node scripts/test-streamable-http-client.mjsDeployment
The server is automatically deployed to Vercel. For manual deployment:
pnpm run deployThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/reka-ai/reka-research-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server