TrustAI Pay MCP

An official MCP server for trustai.center that enables AI agents to perform pay-per-use LLM inference using crypto payments (USDC/USDT) via x402 or prepaid keys. It provides tools for listing models, checking prices, managing balances, setting spend caps, and executing chat completions across hundreds of models.

Visit trustai.center

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by trustai.center

You need:Set export TAI_KEY=tai_… (from step 1 below; a $1 starter top-up is enough to try every model), or skip keys entirely with x402.

MCP endpoint (Streamable HTTP)

https://pay.trustai.center/mcp

Vendor documentation

What you can do with it

List available LLM models and trending options
Quote costs for specific model requests
Manage agent spending caps and usage limits
Execute chat completions with crypto payment

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: center.trustai.pay/trustai-pay@1.0.0 Project website

Protocol and capabilities

Server: trustai-pay 1.4.0
MCP protocol: 2025-06-18
Tools: 11 advertised
Resources: Not advertised
Resource templates: Not advertised
Prompts: Not advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

Pay-per-use LLM inference for agents, paid in USDC/USDT. Use create_topup to get a tai_ key and deposit address, verify_topup after paying, then chat_completion.

Tools

11 advertised

list_models

Advertised by the server during the last successful anonymous check.

List servable text chat models with USD prices (pricing.vs_list vs maker list price). Pass include=discovery to also see image/video models (servable:false). Filter by modality, max output price, text search; sort by popularity or price.

list_models input schema

{
  "type": "object",
  "properties": {
    "q": {
      "type": "string"
    },
    "sort": {
      "enum": [
        "popularity",
        "price",
        "price_desc",
        "name"
      ],
      "type": "string"
    },
    "limit": {
      "type": "number",
      "default": 50
    },
    "include": {
      "enum": [
        "discovery"
      ],
      "type": "string",
      "description": "Also list image/video/other models that are not servable here (servable:false)"
    },
    "modality": {
      "enum": [
        "text",
        "image",
        "video",
        "audio",
        "embedding",
        "rerank",
        "other"
      ],
      "type": "string"
    },
    "max_price": {
      "type": "number",
      "description": "Max USD per 1M output tokens (or per unit for media)"
    }
  }
}

list_trending

Advertised by the server during the last successful anonymous check.

Featured trending models with prices (ranked by recent tokens served when available, otherwise a curated ranking; see ranking field).

list_trending input schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "default": 10
    }
  }
}

quote

Advertised by the server during the last successful anonymous check.

Price check before paying: worst-case USD cost and exact x402 amount for a model + max_tokens (+ optional messages or input_tokens), with up to 3 cheaper trending alternatives. No key needed, never charges.

quote input schema

{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string"
    },
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "role",
          "content"
        ],
        "properties": {
          "role": {
            "type": "string"
          },
          "content": {
            "type": "string"
          }
        }
      }
    },
    "max_tokens": {
      "type": "number"
    },
    "input_tokens": {
      "type": "number"
    }
  }
}

get_balance

Advertised by the server during the last successful anonymous check.

Get the credit balance, spend cap and amount spent for a tai_ API key.

get_balance input schema

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "description": "tai_ key (optional if sent as Authorization: Bearer header)"
    }
  }
}

create_topup

Advertised by the server during the last successful anonymous check.

Create a stablecoin top-up order. Returns the deposit address, chain and the exact amount to send. Omit api_key to create a new key (returned once).

create_topup input schema

{
  "type": "object",
  "required": [
    "pack"
  ],
  "properties": {
    "pack": {
      "enum": [
        1,
        3,
        10,
        25
      ],
      "type": "number",
      "description": "Credits in USD (1 = starter pack)"
    },
    "chain": {
      "enum": [
        "base",
        "solana",
        "bsc"
      ],
      "type": "string",
      "default": "base"
    },
    "promo": {
      "type": "string"
    },
    "api_key": {
      "type": "string"
    }
  }
}

verify_topup

Advertised by the server during the last successful anonymous check.

Confirm a top-up after sending funds, by order id and transaction hash/signature. Credits the amount received (tolerance -0.5% or $0.01; other amounts need the sender's signature).

verify_topup input schema

{
  "type": "object",
  "required": [
    "order_id",
    "tx_hash"
  ],
  "properties": {
    "tx_hash": {
      "type": "string"
    },
    "order_id": {
      "type": "string"
    },
    "signature": {
      "type": "string"
    }
  }
}

claim_topup

Advertised by the server during the last successful anonymous check.

Credit a stablecoin transfer to our address that has no matching order (or a non-exact amount). Requires the sending wallet's signature of 'trustai.center claim <chain>:<tx_hash>'. Max 7 days old, each tx once. Omit api_key to get a new key.

claim_topup input schema

{
  "type": "object",
  "required": [
    "chain",
    "tx_hash"
  ],
  "properties": {
    "chain": {
      "enum": [
        "base",
        "solana",
        "bsc"
      ],
      "type": "string"
    },
    "api_key": {
      "type": "string"
    },
    "tx_hash": {
      "type": "string"
    },
    "signature": {
      "type": "string"
    }
  }
}

set_cap

Advertised by the server during the last successful anonymous check.

Set spend controls on a tai_ key: total spend cap, daily limit (UTC day) and per-request max, in USD. Omit a field to keep it, pass null to remove it.

set_cap input schema

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string"
    },
    "spend_cap_usd": {
      "type": [
        "number",
        "null"
      ]
    },
    "daily_limit_usd": {
      "type": [
        "number",
        "null"
      ]
    },
    "per_request_max_usd": {
      "type": [
        "number",
        "null"
      ]
    }
  }
}

get_usage

Advertised by the server during the last successful anonymous check.

Usage and audit log for a tai_ key: recent charges (model, tokens, cost), top-ups, last-24h totals, balance and limits.

get_usage input schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "default": 50
    },
    "api_key": {
      "type": "string"
    }
  }
}

get_stats

Advertised by the server during the last successful anonymous check.

Public platform stats from our database (tokens and requests in the last 24h, keys created, top models). Real numbers only.

get_stats input schema

{
  "type": "object",
  "properties": {}
}

chat_completion

Advertised by the server during the last successful anonymous check.

Run a chat completion billed to a tai_ key's credits.

chat_completion input schema

{
  "type": "object",
  "required": [
    "model",
    "messages"
  ],
  "properties": {
    "model": {
      "type": "string"
    },
    "api_key": {
      "type": "string"
    },
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "role",
          "content"
        ],
        "properties": {
          "role": {
            "type": "string"
          },
          "content": {
            "type": "string"
          }
        }
      }
    },
    "max_tokens": {
      "type": "number"
    }
  }
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 564 ms
95th percentile latency: 564 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 8:37 AM UTC · probe · passed · 564 ms · metadata changed · 11 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http trustai-pay-mcp https://pay.trustai.center/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add trustai-pay-mcp --url https://pay.trustai.center/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable trustai-pay-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "trustai-pay-mcp": {
      "url": "https://pay.trustai.center/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "trustai-pay-mcp": {
      "type": "streamableHttp",
      "url": "https://pay.trustai.center/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start trustai-pay-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "trustai-pay-mcp": {
      "type": "http",
      "url": "https://pay.trustai.center/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http trustai-pay-mcp https://pay.trustai.center/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "trustai-pay-mcp": {
      "url": "https://pay.trustai.center/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "trustai-pay-mcp": {
      "serverUrl": "https://pay.trustai.center/mcp"
    }
  }
}

Let your agent find its tools

Find servers like TrustAI Pay MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

Do you run TrustAI Pay MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing