mcpField
S
Shardeum MCP Server

Shardeum MCP Server

Local
github.com/abdulazeem-tk4vrFinance0Updated 16w ago
Repository

About Shardeum MCP Server

Shardeum MCP Server exposes Shardeum network and RPC operations as structured tools for AI agents, IDE assistants, and developer workflows. It supports inspection of nodes, cycles, accounts, blocks, transactions, and receipts, with request validation and RPC error handling.

Key features

  1. 01Inspect nodes, network accounts, and cycles
  2. 02Query blocks, transactions, and receipts
  3. 03Check balances, gas estimates, and chain ID
  4. 04Validate requests and handle RPC failures
  5. 05Dockerized deployment option

Use cases

  1. 01Inspect Shardeum network and node state
  2. 02Debug a block or transaction via RPC
  3. 03Check an account balance and transaction count

MCP support

Exposes structured Shardeum network and RPC tools to MCP clients, including Cursor. Tool calls cover node, cycle, account, block, transaction, receipt, and execution queries.

Configuration

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

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

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
ocibuild

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

Shardeum MCP Server

Model Context Protocol server for distributed-system inspection and developer workflows on Shardeum.

This project exposes Shardeum network and RPC operations as structured MCP tools so AI agents, IDE assistants, and developer workflows can inspect distributed-system state through validated tool calls instead of ad hoc scripts. It is designed for agent-driven debugging, node/network inspection, and repeatable developer operations.

smithery badge MseeP.ai Security Assessment Badge Verified on MseeP

What It Demonstrates

  • MCP server implementation for AI-agent tool use
  • Structured tool-call interfaces over distributed-system RPC methods
  • Node, cycle, account, block, transaction, and receipt inspection
  • IDE integration with Cursor and MCP-compatible clients
  • Dockerized deployment path
  • Error handling around network and RPC failures
  • Security-reviewed MCP server listing through MseeP/Smithery badges

Architecture

MCP client / AI agent / Cursor
        |
        v
Shardeum MCP Server
        |
        +-- tool schema
        +-- request validation
        +-- RPC adapter
        +-- error handling
        |
        v
Shardeum RPC endpoint
        |
        v
Structured response to agent

Supported Tool Areas

Network and Node Inspection
  • shardeum_getNodeList
  • shardeum_getNetworkAccount
  • shardeum_getCycleInfo
Block and Transaction Inspection
  • eth_blockNumber
  • eth_getBlockByHash
  • eth_getBlockByNumber
  • eth_getBlockReceipts
  • eth_getTransactionByHash
  • eth_getTransactionReceipt
  • eth_getTransactionCount
Account and Execution Queries
  • eth_getBalance
  • eth_estimateGas
  • eth_chainId

Cursor Integration

Clone the repo, install dependencies, and register the MCP server:

npm install

Cursor MCP config:

{
  "mcpServers": {
    "shardeum-mcp": {
      "command": "node",
      "args": ["path_to/shardeum-mcp-server/index.js"]
    }
  }
}

Example prompts:

What is the current Shardeum block number?
List available network nodes and summarize their state.
Fetch the receipt for this transaction and explain the result.
Inspect this account balance and transaction count.

Configuration

Set the RPC endpoint in the server configuration or update the rpcUrl constant for your target environment.

Docker

docker build -t shardeum-mcp-server .
docker run --rm shardeum-mcp-server

Why This Is Non-Trivial

MCP servers give agents operational access to external systems. This project converts distributed-system RPC calls into explicit tool schemas, making agent actions easier to validate, debug, and constrain compared with free-form shell or HTTP access.

Roadmap

  • Expand supported network methods
  • Add write-safe transaction workflows with explicit confirmation gates
  • Improve typed responses and validation
  • Add broader distributed-system diagnostics
  • Add more deployment examples for MCP-compatible clients

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.