execution-run-mcp
OfficialClick on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@execution-run-mcp transfer 100 shells to dev@exe_abc123 for compute time"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
execution-run-mcp
Model Context Protocol (MCP) server for the Execute.run bot API. Enables AI agents to manage Shell balances, transfer funds, and execute LLM requests through the Execute.run platform.
Installation
Via npx (Recommended)
npx @execution-run/mcp-serverVia npm
npm install -g @execution-run/mcp-server
execution-run-mcpFrom Source
git clone https://github.com/execution-run/execution-run-mcp.git
cd execution-run-mcp
bun install
bun run buildConfiguration
Set the following environment variables:
EXECUTE_RUN_API_KEY(required): Your Execute.run API key from execution.run/api-keysEXECUTE_RUN_API_URL(optional): API base URL (defaults tohttps://execution.run/v1)
Usage
With Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"execution-run": {
"command": "npx",
"args": ["execution-run-mcp"],
"env": {
"EXECUTE_RUN_API_KEY": "sk_live_your_api_key_here"
}
}
}
}With Kiro
Add to your .kiro/settings/mcp.json:
{
"mcpServers": {
"execution-run": {
"command": "npx",
"args": ["execution-run-mcp"],
"env": {
"EXECUTE_RUN_API_KEY": "sk_live_your_api_key_here"
}
}
}
}Standalone
EXECUTE_RUN_API_KEY=sk_live_xxx execution-run-mcpAvailable Tools
whoami
Get your card and wallet identity information.
Parameters: None
Returns:
{
"cardId": "crd_abc123",
"walletId": "exe_xyz789",
"address": "bot-prod@exe_xyz789",
"balance": 1000,
"status": "active"
}get_balance
Get the current Shell balance and ceiling for your wallet.
Parameters: None
Returns:
{
"balance": 1000,
"ceiling": 1000000
}get_transactions
Get transaction history for your wallet.
Parameters:
limit(optional): Number of transactions to return (default: 50, max: 100)
Returns:
{
"transactions": [
{
"id": "tx_123",
"type": "mint",
"amount": 1000,
"balanceAfter": 1000,
"timestamp": { "_seconds": 1706745600 },
"purpose": "Initial credit"
}
]
}transfer
Transfer Shells to another wallet.
Parameters:
to(required): Recipient wallet ID (exe_xxx) or card address (cardName@exe_xxx)amount(required): Amount of Shells to transfer (positive integer)purpose(required): Purpose/context for the transfer
Returns:
{
"transaction": {
"id": "tx_456",
"type": "transfer",
"amount": 100,
"balanceAfter": 900,
"purpose": "Payment for service"
}
}sign
Sign a challenge with your card's Ed25519 keypair.
Parameters:
challenge(required): Base64-encoded challenge to sign
Returns:
{
"signature": "base64_encoded_signature",
"cardId": "crd_abc123",
"walletId": "exe_xyz789"
}compute
Execute an LLM request by burning Shells.
Parameters:
model(required): Model identifier (e.g., 'gemini-2.0-flash', 'gpt-4o', 'claude-3-5-sonnet-latest')messages(required): Array of conversation messages withroleandcontenttemperature(optional): Sampling temperature (0-2)maxTokens(optional): Maximum tokens to generate
Returns:
{
"content": "Hello! How can I help you?",
"model": "gemini-2.0-flash",
"cost": 4
}Development
# Install dependencies
bun install
# Build
bun run build
# Watch mode
bun run dev
# Run locally
bun run startLicense
MIT
Links
Available Tools
6 toolscomputeA
Execute an LLM request by burning Shells. The cost is calculated based on the model and token usage. Returns the LLM response content and the cost in Shells.
Inputs: model (required), messages (required), temperature, maxTokens.
get_balanceA
Get the current Shell balance and ceiling for your wallet. Returns the available balance and maximum allowed balance.
Inputs: no named parameters.
get_transactionsB
Get transaction history for your wallet. Returns a list of recent transactions including mints, burns, and transfers.
Inputs: limit.
signA
Sign a challenge with your card's Ed25519 keypair. Returns the signature, cardId, and walletId. Useful for proving your identity to other bots.
Inputs: challenge (required).
transferB
Transfer Shells to another wallet. Accepts wallet ID (exe_xxx) or card address (cardName@exe_xxx). Requires the recipient, amount, and a purpose describing why the transfer is being made.
Inputs: to (required), amount (required), purpose (required).
whoamiA
Get your card and wallet identity. Returns cardId, walletId, address (cardName@walletId format), balance, and status.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no overlap: compute handles LLM execution, get_balance and get_transactions provide wallet information, sign handles authentication, transfer manages funds, and whoami returns identity. The descriptions clearly differentiate their functions, eliminating any ambiguity.
All tool names follow a consistent verb_noun pattern with snake_case: compute, get_balance, get_transactions, sign, transfer, and whoami. The naming is predictable and readable throughout the set, with no deviations in style.
With 6 tools, the count is well-scoped for a wallet and execution management server. Each tool earns its place by covering essential operations like balance checking, transactions, transfers, identity, and LLM execution, without being excessive or sparse.
The tool set provides strong coverage for wallet management and LLM execution, including identity, balance, transactions, transfers, and signing. A minor gap exists in lacking a tool for managing or configuring the wallet settings, but core workflows are fully supported without dead ends.
Related MCP Connectors
Verified, pay-per-use API tools for AI agents through one authenticated connection.
ERC-8004 agent identity, on-chain subscriptions, reputation, A2A tasks and chat over 53 tools.
Discover, inspect and run 63,000+ agent tools from one balance. Pay per call, no subscriptions.
Verified EVM, Aptos and finance tools for AI agents; gas for 14 chains. Pay per call (x402).