helius-tech-labshelius-tech-labs/core-ai/helius-mcp/CLAUDE.md

core-ai / helius-mcp

CLAUDE.md0 starsChanged 8 months agoMITView on GitHub

MCP (Model Context Protocol) server that exposes Helius/Solana data tools for AI assistants. Each tool file exports tool definitions registered in index.ts. Tools use the helius-sdk createHelius() for SDK methods and restRequest()/rpcRequest()/dasRequest() for non-SDK endpoints.

Reads credentials
Installs packages

In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- helius-cli/CLAUDE.mdCLAUDE.md
- helius-dflowSkill
- helius-okxSkill
- helius-phantomSkill
- heliusSkill
- svmSkill

The file

Create a free account to mount

Files

CLAUDE.md

helius-mcp

MCP (Model Context Protocol) server that exposes Helius/Solana data tools for AI assistants.

Directory Structure

src/
  index.ts             # Entry point — MCP server setup, tool registration
  tools/               # Tool definitions (one file per tool group)
    balance.ts
    assets.ts
    transactions.ts
    webhooks.ts
    network.ts
    wallet.ts
    ...
  utils/
    helius.ts          # SDK client wrapper — getHeliusClient(), rpcRequest(), dasRequest(), restRequest()

Tool Registration Pattern

Each tool file exports tool definitions registered in index.ts. Tools use the helius-sdk createHelius() for SDK methods and restRequest()/rpcRequest()/dasRequest() for non-SDK endpoints.

SDK vs Raw Fetch

SDK (getHeliusClient()): DAS API methods, webhooks, enhanced transactions
RPC (rpcRequest()): Standard Solana RPC (getBalance, getAccountInfo, etc.)
DAS (dasRequest()): DAS API via JSON-RPC
REST (restRequest()): Wallet API (/v1/wallet/...), enhanced transactions (/v0/transactions)

API Key Management

Session key set via setHeliusApiKey tool
Falls back to HELIUS_API_KEY environment variable
Network defaults to mainnet-beta, configurable via setNetwork()

Build / Dev

pnpm install
pnpm build          # tsc → dist/
pnpm dev            # Development mode

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free