MCP server
by goplausible
Interact with the Algorand blockchain using a robust TypeScript toolkit for accounts, assets, smart contracts, and trans
Connects AI agents to the Algorand blockchain for creating accounts, managing assets, deploying smart contracts, and executing transactions. Features secure wallet management with spending controls and daily limits.
Algorand is a community-built MCP server published by goplausible that provides AI assistants with tools and capabilities via the Model Context Protocol. Interact with the Algorand blockchain using a robust TypeScript toolkit for accounts, assets, smart contracts, and trans It is categorized under finance, developer tools.
You can install Algorand in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Algorand is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Algorand reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
According to our notes, Algorand benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Algorand has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
We wired Algorand into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Algorand reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Algorand has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
According to our notes, Algorand benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
I recommend Algorand for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
Strong directory entry: Algorand surfaces stars and publisher context so we could sanity-check maintenance before adopting.
Algorand reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
showing 1-10 of 48
A comprehensive Model Context Protocol (MCP) server that gives AI agents and LLMs full access to the Algorand blockchain. Built by GoPlausible.
Algorand is a carbon-negative, pure proof-of-stake Layer 1 blockchain with instant finality, low fees, and built-in support for smart contracts (AVM), standard assets (ASAs), and atomic transactions.
Model Context Protocol is an open standard that lets AI applications connect to external tools and data sources. This server exposes Algorand blockchain operations as MCP tools that any compatible AI client can use — Claude Desktop, Claude Code, Cursor, Windsurf, and others.
npm install -g @goplausible/algorand-mcp
git clone https://github.com/GoPlausible/algorand-mcp.git
cd algorand-mcp
npm install
npm run build
The server runs over stdio. There are three ways to invoke it — pick whichever suits your setup:
| Method | Command | When to use |
|---|---|---|
| npx (recommended) | npx @goplausible/algorand-mcp | No install needed, always latest version |
| Global install | algorand-mcp | After npm install -g @goplausible/algorand-mcp |
| Absolute path | node /path/to/dist/index.js | Built from source or local clone |
No environment variables are required for standard use. Network selection, pagination, and node URLs are all handled dynamically per tool call.
No manual configuration needed — install the @goplausible/openclaw-algorand-plugin npm package and the Algorand MCP server is configured automatically:
npm install -g @goplausible/openclaw-algorand-plugin
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Using npx:
{
"mcpServers": {
"algorand-mcp": {
"command": "npx",
"args": ["@goplausible/algorand-mcp"]
}
}
}
Using global install:
{
"mcpServers": {
"algorand-mcp": {
"command": "algorand-mcp"
}
}
}
Using absolute path:
{
"mcpServers": {
"algorand-mcp": {
"command": "node",
"args": ["/absolute/path/to/algorand-mcp/dist/index.js"]
}
}
}
Create .mcp.json in your project root (project scope) or ~/.claude.json (user scope):
{
"mcpServers": {
"algorand-mcp": {
"type": "stdio",
"command": "npx",
"args": ["@goplausible/algorand-mcp"]
}
}
}
Or add interactively:
claude mcp add algorand-mcp -- npx @goplausible/algorand-mcp
Add via Settings > MCP Servers, or edit .cursor/mcp.json in your project root:
{
"mcpServers": {
"algorand-mcp": {
"command": "npx",
"args": ["@goplausible/algorand-mcp"]
}
}
}
Add via Settings > MCP, or edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"algorand-mcp": {
"command": "npx",
"args": ["@goplausible/algorand-mcp"]
}
}
}
Edit .vscode/mcp.json in your workspace root, or open Settings > MCP Servers:
{
"servers": {
"algorand-mcp": {
"type": "stdio",
"command": "npx",
"args": ["@goplausible/algorand-mcp"]
}
}
}
Add via the MCP Servers panel in the Cline sidebar, or edit ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json (macOS):
{
"mcpServers": {
"algorand-mcp": {
"command": "npx",
"args": ["@goplausible/algorand-mcp"],
"disabled": false
}
}
}
Create .codex/mcp.json in your project root or ~/.codex/mcp.json for global scope:
{
"mcpServers": {
"algorand-mcp": {
"command": "npx",
"args": ["@goplausible/algorand-mcp"]
}
}
}
Edit ~/.config/opencode/config.json:
{
"mcp": {
"algorand-mcp": {
"type": "stdio",
"command": "npx",
"args": ["@goplausible/algorand-mcp"]
}
}
}
The server speaks the standard MCP stdio protocol. For any client not listed above, configure it with:
npx (or algorand-mcp if globally installed, or node /path/to/dist/index.js)["@goplausible/algorand-mcp"] (for npx)stdioEvery tool accepts an optional network parameter: "mainnet" (default), "testnet", or "localnet". Algod and Indexer URLs are built-in for mainnet and testnet via AlgoNode.
Example tool call:
{ "name": "api_algod_get_account_info", "arguments": { "address": "ABC...", "network": "testnet" } }
If no network is provided, tools default to mainnet.
API responses are automatically paginated. Every tool accepts an optional itemsPerPage parameter (default: 10). Pass the pageToken from a previous response to fetch the next page.
The wallet system has two layers of storage, each with a distinct security role:
| Layer | What it stores | Where | Encryption |
|---|---|---|---|
| OS Keychain | Mnemonics (secret keys) | macOS Keychain / Linux libsecret / Windows Credential Manager | OS-managed, hardware-backed where available |
| Embedded SQLite | Account metadata (nicknames, allowances, spend tracking) | ~/.algorand-mcp/wallet.db | Plaintext (no secrets) |
Private key material never appears in tool responses, MCP config files, environment variables, or logs. The agent only sees addresses, public keys, and signed transaction blobs.
Agent (LLM) MCP Server Storage
────────── ────────── ───────
│ │ │
│ wallet_add_account │ │
│ { nickname: "main" } │ │
│ ──────────────────────────► │ generate keypair │
│ │ store mnemonic ──────────► │ OS Keychain (encrypted)
│ │ store metadata ──────────► │ SQLite (nickname, limits)
│ ◄─ { address, publicKey } │ │
│ │ │
│ wallet_sign_transaction │ │
│ { transaction: {...} } │ │
│ ──────────────────────────► │ check spending limits │
│ │ retrieve mnemonic ◄────── │ OS Keychain
│ │ sign in memory │
│ ◄─ { txID, blob } │ (key discarded) │
│ │ │
wallet_add_account) — Generates a keypair (or imports a mnemonic), stores the mnemonic in the OS keychain, and stores metadata (nickname, spending limits) in SQLite. Returns only address and public key.wallet_switch_account changes it by nickname or index. All signing and query tools operate on the active account.wallet_sign_transaction) — Checks per-transaction and daily spending limits, retrieves the key from the keychain, signs in memory, discards the key. Returns only the signed blob.wallet_sign_data) — Signs arbitrary hex data using raw Ed25519 via the @noble/curves library (no Algorand SDK prefix). Useful for off-chain authentication.wallet_optin_asset) — Creates, signs, and submits an opt-in transaction for the active account in one step.Each account has two configurable limits (in microAlgos, 0 = unlimited):
allowance — Maximum amount per single transaction. Rejects any transaction exceeding this.dailyAllowance — Maximum total spend per calendar day across all transactions. Automatically resets at midnight. Tracked in SQLite.The keychain backend is provided by @napi-rs/keyring (Rust-based, prebuilt
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.