Kirha MCP Gateway
A unified interface that provides AI agents with access to premium data sources and crypto market intelligence through a single authentication endpoint. It handles multi-API composition and planning to aggregate real-time blockchain analytics and financial data into conversational workflows.
README
<p align="center"> <a href="https://kirha.ai" target="_blank"> <img src="https://raw.githubusercontent.com/kirha-ai/kirha-mcp-gateway/refs/heads/main/assets/logo.png" width="2500" alt="Kirha Logo"> </a> </p>
<h1 align="center">Kirha MCP Gateway</h1> <h3 align="center">The AI bridge to reality</h3>
The golden light of private data will never shine on your AI queries if you can't find what you need and pay for it instantly. Kirha MCP Gateway is an MCP (Model Context Protocol) server that handles exactly that for you: routing and micropayment.
Beta Scope
Kirha launched on the Crypto vertical with providers like Dune, Defillama, Zerion, Xverse, Coingecko, Cielo... Access live market intelligence & wallets' transactions and relations, whales' movements, sentiment analysis, and much more from the comfort of your favourite AI Client. Kirha is under free Beta. Request an access code here.
Why Kirha MCP Gateway?
Kirha MCP Gateway is designed to simplify access to high-value, aggregated data sources through a single, unified interface.
-
One Auth to rule them all: Access multiple premium data sources through a single MCP endpoint. You don't need to integrate or authenticate separately with multiple APIs.
-
Multi-API Composition: In a single request, the gateway can compose and aggregate data from several APIs simultaneously. This reduces complexity and response time for complex queries.
-
Enhanced Context for Agents and Chatbots: By centralizing and combining data, the gateway provides richer context for AI agents and conversational systems (such as Claude), improving their ability to deliver accurate, relevant responses.
Tools
By default, the gateway operates in auto mode, where both planning and execution are performed automatically in a single request.
Planning is deterministic: semantically identical prompts yield the same composition of tool(s).
If the environment variable TOOL_PLAN_MODE_ENABLED is set to true, the gateway switches to planning mode, which separates the planning and execution steps.
When we ship Kirha's payment, you will be able to accept or reject the plan before it is executed.
Auto mode
execute-tool-planning: Automatically performs both planning and execution in a single request. This tool internally creates the plan and immediately executes it, returning the final result in one step.
Plan mode
create-tool-planning: Prepares a query and generates a plan_id for later execution. This tool enables creating a plan in advance, which can then be reviewed before execution.execute-tool-planning: Executes a previously created plan by providing its plan_id. This step runs the predefined plan and returns the result.
Installation
Kirha MCP Installer (recommended)
You can install and run the Kirha MCP Gateway using the Kirha MCP Installer.
npx @kirha/mcp-installer install --client <client> --key <api-key>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.