solanaprox-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SOLANA_WALLET | Yes | Your Phantom wallet address | |
| SOLANAPROX_URL | No | Override API URL (default: https://solanaprox.com) | https://solanaprox.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_aiA | Send a prompt to an AI model via SolanaProx. Costs are automatically deducted from your Solana wallet balance in USDC. Supports Claude and GPT-4 models. Use this for any AI inference task. |
| check_balanceA | Check your current SolanaProx balance. Returns available USDC and SOL balance that can be used for AI requests. |
| estimate_costB | Estimate the cost of an AI request before making it. Returns estimated USD cost based on prompt length and model. |
| list_modelsA | List all available AI models on SolanaProx with their pricing. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: ask_ai for AI inference, check_balance for wallet status, estimate_cost for pre-request pricing, and list_models for model information. The descriptions reinforce these distinct roles, making tool selection unambiguous.
All tools follow a consistent verb_noun pattern (ask_ai, check_balance, estimate_cost, list_models) with clear, descriptive names. There are no deviations in style or convention, making the set predictable and easy to understand.
Four tools are well-scoped for a server focused on AI inference via SolanaProx, covering core operations like making requests, checking balances, estimating costs, and listing models. It feels slightly thin but reasonable, as it handles the essential workflow without unnecessary complexity.
The toolset covers the key aspects of using SolanaProx for AI tasks: making requests, managing costs, and accessing model info. A minor gap exists in lacking tools for transaction history or detailed billing, but agents can work around this with the provided tools for most use cases.