Olamto MCP Server
MCP server for Web3 AI agents enabling autonomous smart contract engineering on Robinhood EVM and Solana, with Cloudflare One portals for efficient token usage and edge execution.
README
<div align="center">
<img src="https://app.olamto.fun/logo.png" width="110" alt="Olamto Logo" style="border-radius: 18px; box-shadow: 0 0 30px rgba(43, 84, 255,0.3);" />
ā” Olamto Studio
Next-Gen Web3 AI Agentic Platform & Cloudflare One MCP Portals
š Live Studio App ⢠š Developer Docs ⢠š GitHub ⢠š (Twitter) ⢠āļø Telegram
</div>
š Overview
Olamto Studio is the premier Web3 AI development platform designed for autonomous smart contract engineering, stateful AI agent execution, and Model Context Protocol (MCP) server portals running natively on Cloudflare Workers Edge.
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Olamto AI Engine Core ā
ā (16 Frontier AI Models Suite) ā
āāāāāāāāāāāāāāāāāāāāāāāāā¬āāāāāāāāāāāāāāāāāāāāāāāā
ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¼āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā¼ ā¼ ā¼
āāāāāāāāāāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāāāāāāāāāā
ā Robinhood EVM Chain ā ā Solana MCP Autofixer ā ā Cloudflare One MCP ā
ā Solidity Compiler ā ā Anchor & Pinocchio ā ā 5x Token Savings ā
ā Chain ID 4663 ā ā Rust Program Repair ā ā Workers Codemode ā
āāāāāāāāāāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāāāāāāāāāā
⨠Core Features
- š¤ Autonomous Agent SDK (
@olamtostudio/agents): Event-driven agent base class with edge state persistence via Durable Objects and real-time WebSocket fibers. - š¢ Robinhood EVM Chain (Chain ID 4663): Native Solidity compilation, static vulnerability auditing via Blockscout API, and gas estimation.
- š£ Solana MCP Program Autofixer: Anchor & Pinocchio Rust smart contract error parsing, IDL generation, and automated code repair.
- ā” Cloudflare One MCP Server Portals: 5x Token Savings optimization via
minimize_tools()&search_and_execute(), reducing context window usage by up to 80%. - š¤ Cloudflare D1 SQL Vault: Serverless SQL storage for user configurations, API key vaults, and rate limits.
š¦ Installation
Since @olamtostudio/agents is hosted directly on GitHub, install it directly using npm, yarn, or pnpm:
# Install directly from GitHub Repository
npm install github:olamtostudio/agents
# Using yarn
yarn add olamtostudio/agents
# Using pnpm
pnpm add github:olamtostudio/agents
Or clone and build from source:
git clone https://github.com/olamtostudio/agents.git
cd agents
npm install && npm run build
ā” Quick Start
Create an autonomous Web3 AI agent in TypeScript:
import { Agent, type Connection, type WSMessage, type AgentEnv } from "@olamtostudio/agents";
export class Web3AuditorAgent extends Agent {
constructor(env: AgentEnv) {
super(env);
}
// 1. Triggered on connection establishment
async onConnect(connection: Connection): Promise<void> {
console.log("ā” Olamto Agent booted on Robinhood EVM Chain ID 4663");
connection.send(JSON.stringify({
type: "ready",
status: "Connected to Olamto Studio Edge"
}));
}
// 2. Triggered on incoming message or tool command
async onMessage(connection: Connection, message: WSMessage): Promise<void> {
const data = typeof message === "string" ? JSON.parse(message) : message;
if (data.action === "audit") {
await this.setState({ last_contract: data.contract });
const currentState = await this.getState();
connection.send(JSON.stringify({
status: "success",
state: currentState,
content: `Audit initiated for contract on Robinhood EVM Chain ID 4663`
}));
}
}
// 3. Triggered when client disconnects
async onClose(connection: Connection): Promise<void> {
console.log("Client disconnected:", connection.id);
}
}
š SDK Reference (@olamtostudio/agents)
Agent Abstract Base Class
import { Agent, type Connection, type WSMessage, type AgentEnv } from "@olamtostudio/agents";
export class CustomAgent extends Agent {
constructor(env: AgentEnv) {
super(env);
}
// Boots up connection context
async onConnect(connection: Connection): Promise<void> {}
// Handles incoming messages and tool execution commands
async onMessage(connection: Connection, message: WSMessage): Promise<void> {}
// Handles connection teardown
async onClose(connection: Connection): Promise<void> {}
}
Session State Storage
// Set state
await this.setState({ user_wallet: "0x46633e21a4168923058b71b93f21" });
// Get current state
const currentState = await this.getState();
āļø Robinhood EVM Chain Integration (Chain ID 4663)
import { RobinhoodEVM } from "@olamtostudio/agents";
const evm = new RobinhoodEVM({
rpcUrl: "https://rpc.robinhood.olamto.fun",
chainId: 4663,
});
const auditResult = await evm.auditContract(`
pragma solidity ^0.8.20;
contract OlamtoToken {
mapping(address => uint256) public balances;
function transfer(address to, uint256 amount) public {
balances[msg.sender] -= amount;
balances[to] += amount;
}
}
`);
console.log("Audit Status:", auditResult.status);
console.log("Vulnerabilities:", auditResult.issues);
āļø Solana MCP Program Autofixer
import { SolanaMCP } from "@olamtostudio/agents";
const solana = new SolanaMCP();
const fixResult = await solana.autofixProgram({
sourceCode: rustProgramCode,
errorMessage: "Error: AccountDiscriminatorMismatch",
});
console.log("Repaired Rust Code:", fixResult.repairedCode);
š Official Channels & Resources
- š Live Application: https://app.olamto.fun
- š Developer Documentation: https://app.olamto.fun/docs
- š GitHub Repository: https://github.com/olamtostudio/agents
<div align="center"> <sub>MIT License Ā© 2026 Olamto Foundation</sub> </div>
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.