Agoreum
Marketplace where AI agents hire and pay other agents in USDC on Base, through on-chain escrow.
Description from the maker (original English)
MCP Server for Rootstock Blockchain
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"rsk": {
"command": "npx",
"args": [
"-y",
"@rsksmart/rsk-mcp-server"
]
}
}
}Run this in your terminal
claude mcp add rsk -- npx -y @rsksmart/rsk-mcp-serverPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"rsk": {
"command": "npx",
"args": [
"-y",
"@rsksmart/rsk-mcp-server"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"rsk": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@rsksmart/rsk-mcp-server"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 9, 2026
The registry name was verified with the GitHub account rsksmart, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.2.7) reached the registry 4 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Agoreum, Web3 Systemic Agent, Highwire
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Marketplace where AI agents hire and pay other agents in USDC on Base, through on-chain escrow.
Web3 security, DEX honeypot detector, and DAO governance auditor for Base & EVM chains.
Trade, launch and research higher.fun coins on Solana, from any AI agent. Unsigned or policy-signed.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Rootstock MCP Server is a Model Context Protocol (MCP) server that provides advanced tools for interacting with the Rootstock (RSK) blockchain. This project enables AI clients to seamlessly connect and execute blockchain operations.
This server exposes 22 MCP tools. You don't call these directly — once the MCP is connected, your AI client selects the right tool based on your prompt.
| Category | Tool | Description |
|---|---|---|
| Session | start-interaction | Start interacting with the Rootstock CLI functions |
| Session | list-pending-operations | List pending operations awaiting confirmation (deploys, transfers) |
| Session | confirm-operation | Confirm and execute a pending operation by ID |
| Session | cancel-operation | Cancel a pending operation by ID |
| Wallet | start-wallet-interaction | Show available wallet management operations |
| Wallet | create-wallet | Create, import, list, switch, or delete wallets |
| Wallet | use-wallet-from-creation | Reuse wallet data from a previous create-wallet result without re-uploading it |
| Balance | check-balance | Check rBTC or ERC20 token balances |
| Transfers | transfer-tokens | Transfer rBTC or ERC20 tokens between wallets |
| Transactions | check-transaction | Check a transaction's status and details by hash |
| Transactions | check-transaction-history | Query a wallet's transaction history via the Alchemy API |
| Contracts | deploy-contract | Deploy a smart contract using ABI and bytecode |
| Contracts | verify-contract | Verify a deployed contract's source code |
| Contracts | read-contract | Call view/pure functions on a verified contract |
| Attestations | issue-attestation | Issue a new attestation via RAS (Rootstock Attestation Service) |
| Attestations | verify-attestation | Verify an existing attestation by UID |
| Attestations | revoke-attestation | Revoke an existing attestation by UID |
| Attestations | list-attestations | Query attestations by event logs (requires a custom RPC URL) |
| Attestations | create-schema | Register a new attestation schema |
| Attestations | attest-deployment | Attest a contract deployment using the RAS default schema |
| Attestations | attest-verification | Attest a contract verification using the RAS default schema |
| Attestations | attest-transfer | Attest a token transfer using the RAS default schema |
See Detailed Functionality below for parameters and examples.
Note: You will use this Model Context Protocol Server from a LLM Client (e.g Cursor, Claude, Warp, etc) which needs to be compatible with the MCP standard. Take into account there are 2 steps here:
1. Installation and Build
2. AI Client Configuration
IMPORTANT: You need to complete both settings to correctly use MCP within the Client.
git clone https://github.com/rsksmart/rsk-mcp-server
cd rsk-mcp-server
npm install
npm run build
This command:
build/ folderbuild/index.js)node build/index.js
Important Note: For local running this MCP, your client will point to the
index.jsfile created on thebuildfolder after building it.
In Cursor, go to Settings > Cursor Settings > Tools & Integrations
You will see an option to Add Custom MCP
And add to the JSON file:
{
"mcpServers": { "rsk-mcp-server": { "command": "npx", "args": [ "-y", "@rsksmart/rsk-mcp-server" ] } } } // The Args field contains the path to the index.js file created by the build.
> **Note:** For install reference on Cursor, please follow these instructions [Here](https://docs.cursor.com/en/context/mcp)
Once it is installed into Cursor, you should see something like:
Green dot indicates it was installed correctly.
Edit your Claude Desktop configuration file:
Open your Claude client, and then click on Settings/Developer
Click the “Edit Config” button to open the configuration file and add the following configuration:
Note: This action creates a new configuration file if one doesn’t exist, or opens your existing configuration. The file is located at:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": { "rsk-mcp-server": { "command": "npx", "args": [ "-y", "@rsksmart/rsk-mcp-server" ] } } } // The Args field contains the path to the index.js file created by the build.
> **Note:** For install reference on Claude, please follow these instructions [Here](https://modelcontextprotocol.io/quickstart/user)
Once you have installed this MCP on the Claude client, you will see it once you click on the Search and toolsoption under Web search option (see next image)
In Cursor, go to Settings > Cursor Settings > Tools & Integrations
You will see an option to Add Custom MCP
And add to the JSON file:
{
"mcpServers": { "rsk-mcp": { "command": "node", "args": ["/absolute/path/to/your/project/rsk-mcp-server/build/index.js"] } } } // The Args field contains the path to the index.js file created by the build.
> **Note:** For install reference on Cursor, please follow these instructions [Here](https://docs.cursor.com/en/context/mcp)
Once it is installed into Cursor, you should see something like:
Green dot indicates it was installed correctly.
Edit your Claude Desktop configuration file:
Open your Claude client, and then click on Settings/Developer
Click the “Edit Config” button to open the configuration file and add the following configuration:
Note: This action creates a new configuration file if one doesn’t exist, or opens your existing configuration. The file is located at:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": { "rsk-mcp": { "command": "node", "args": ["/absolute/path/to/your/project/rsk-mcp-server/build/index.js"], "env": {} } } } // The Args field contains the path to the index.js file created by the build.
> **Note:** For install reference on Claude, please follow these instructions [Here](https://modelcontextprotocol.io/quickstart/user)
Once you have installed this MCP on the Claude client, you will see it once you click on the Search and toolsoption under Web search option (see next image)
Any MCP-compatible client can connect using:
node /path/to/project/rsk-mcp-server/build/index.js
Note: This functionality will be available when the server is deployed to a public endpoint.
{
"mcpServers": { "rsk-mcp": { "url": "https://your-server.com/mcp-endpoint", "headers": { "Authorization": "Bearer your-api-key" } } } }
## 🔧 Detailed Functionality
Once this MCP is installed on the client, you will be able to interact with it by prompt, using chat box, for example, a good prompt to start interacting with this MCP is to write a prompt like: I would like to start interacting with Rootstock
Then it will require you to give permission to use the MCP tool, you click on accept, and then it should answer something like:
Perfect! The Rootstock CLI is now active and ready to help you interact with the Rootstock blockchain. Here are the available options:
Available Rootstock Operations: 💼 wallet - Manage your wallet (create new, use existing, or import) 💰 balance - Check wallet balances 💸 transfer - Transfer RBTC or ERC20 tokens 🔍 tx - Check transaction status 🚀 deploy - Deploy a smart contract ✅ verify - Verify a contract 📄 contract - Interact with a contract 📊 history - Check transaction history ❓ help - Display help What would you like to do? If you don't have a wallet yet, I'd recommend starting with option 1 (wallet management) to create or import a wallet first. Then you can proceed with other operations like checking balances, transferring tokens, or deploying contracts. Which option interests you?
You can continue the flow according to what you need to do.
start-interaction: Entry point tool — start here when a user first asks about Rootstock. Lists all available operations.list-pending-operations: List operations awaiting confirmation (contract deployments, token transfers)confirm-operation: Confirm and execute a pending operation using its operation IDcancel-operation: Cancel and discard a pending operation using its operation IDWhy confirmation is needed: Critical operations like deploy-contract and transfer-tokens require a confirmAction boolean on every call — omitting it fails schema validation. Passing confirmAction: false creates a pending operation (expires after 5 minutes) instead of executing, and nothing happens on-chain until it's confirmed via confirm-operation. Passing confirmAction: true on the first call skips that pending step entirely — the tool descriptions themselves instruct AI agents not to do this until a real person has explicitly approved the action, so treat it as an escape hatch for already-approved automation, not the default flow.
List Pending Operations
{} // no parameOnly the beginning is shown; read the rest in the repo