About hyre-mcp
hyre-mcp wraps the HYRE MPP API as paid DeFi data tools for AI agents and MCP clients. It covers Solana token and wallet intelligence, liquidity pools, yields, and natural-language DeFi questions, settling x402 micropayments when a funded wallet key is configured.
Key features
- 01PumpFun token launch and risk data
- 02Wallet PnL and intelligence
- 03Meteora pools and recommendations
- 04Cross-chain TVL and yield data
- 05Natural-language DeFi queries
- 06x402 per-call payments
Use cases
- 01Assessing new PumpFun tokens and snipers
- 02Reviewing wallet holdings and PnL
- 03Comparing pools, TVL, and yield opportunities
- 04Asking an AI-orchestrated DeFi question
MCP support
The MCP server exposes HYRE MPP API endpoints as tools for MCP clients. Tool calls use x402 payments; with a funded Solana wallet key, the server signs and settles payments automatically.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y hyre-mcpSVM_PRIVATE_KEYSecretBase58-encoded Solana private key for a funded wallet (needs USDC for payments + a little SOL for gas). Used to auto-pay x402 micropayments. If omitted, tools return the 402 payment requirements instead of live data.HYRE_API_URLOverride the HYRE MPP API base URL. Defaults to the production endpoint.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
17Saved tool list · updated 2w ago
This tool takes no parameters.
Details
From the project READMEhyre-mcp
HYRE Agent MCP Server — 13 Solana DeFi intelligence tools for AI agents, paid per-call via x402 micropayments (USDC).
Wraps the HYRE MPP API (https://mpp.hyreagent.fun) as Model Context Protocol tools so any MCP client (Claude Desktop, Cursor, OpenHuman, …) can pull live DeFi data and pay automatically.
Tools
| Tool | What it does | Price |
|---|---|---|
hyre-new-tokens | Real-time PumpFun launches + AI snipe signal | $0.008 |
hyre-token-verdict | Full AI verdict on a token (holders, snipers, curve, risk) | $0.015 |
hyre-graduating | Tokens near bonding-curve graduation (>70%) | $0.003 |
hyre-bonding-curve | Bonding curve progress for a PumpFun token | $0.001 |
hyre-token-snipers | Wallets that bought in the first blocks | $0.004 |
hyre-wallet-pnl | Wallet PnL — realized + unrealized, holdings | $0.005 |
hyre-wallet-intel | 30-day wallet intelligence + archetype | $0.012 |
hyre-whales | Top holders with % of supply | $0.003 |
hyre-pools | Meteora DLMM pool list (APR, TVL, volume) | $0.001 |
hyre-pool-recommend | AI pool recommendation for a token pair | $0.008 |
hyre-tvl | TVL across chains with trend narrative | $0.001 |
hyre-yields | Top multi-chain yield pools by APY | $0.002 |
hyre-ask | Natural-language DeFi question, AI-orchestrated | $0.025 |
Install
OpenHuman / Smithery / official MCP registry
Search for HYRE Agent in the MCP browser and install. When prompted, paste your
Solana private key (SVM_PRIVATE_KEY) — it's optional, but required for the tools to
return live data instead of payment requirements.
Any MCP client (manual config)
{
"mcpServers": {
"hyre": {
"command": "npx",
"args": ["-y", "hyre-mcp"],
"env": { "SVM_PRIVATE_KEY": "<your-base58-solana-private-key>" }
}
}
}
CLI
SVM_PRIVATE_KEY=<base58-key> npx -y hyre-mcp
Payment
Each tool call hits a paid HYRE endpoint that returns HTTP 402 with x402 payment
requirements. With SVM_PRIVATE_KEY set to a funded wallet (USDC + a little SOL
for gas), the server signs and settles the micropayment automatically, then returns
the data. Without a key, you get the 402 requirements back — useful for discovery.
| Env | Required | Description |
|---|---|---|
SVM_PRIVATE_KEY | no | Base58 Solana private key of a funded wallet. Secret. |
HYRE_API_URL | no | Override the API base URL (default https://mpp.hyreagent.fun). |
License
MIT
Comments
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.