Audit OpenAI-compatible / x402 inference sellers; quick check 0.005, bill check 0.003 USDC
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Audit a seller vs Cloudflare Workers AI reference. Free 2/day then 0.05 USDC. Auth header never stored.
Claimed model id. Supported: llama-3.1-8b, llama-3.2-3b, llama-3.3-70b, llama-4-scout, qwen3-30b, qwen2.5-coder-32b, gpt-oss-20b, gpt-oss-120b, gemma-4-26b, glm-4.7-flash
OpenAI-compatible base URL (https://…/v1) or chat completions URL, or "workers-ai" to use the Workers AI binding as the target (self-check)
Unused placeholder for client compatibility; payments use x402 headers / free quota
Optional Authorization value for the target (Bearer …). Used in memory only; never stored or logged.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http fidelity https://fidelity.moneytools.dev/mcp
Audit a seller vs Cloudflare Workers AI reference. Free 2/day then 0.05 USDC. Auth header never stored.
| Argument | Type | Description |
|---|---|---|
| model* | string | Claimed model id. Supported: llama-3.1-8b, llama-3.2-3b, llama-3.3-70b, llama-4-scout, qwen3-30b, qwen2.5-coder-32b, gpt-oss-20b, gpt-oss-120b, gemma-4-26b, glm-4.7-flash |
| apiKey | string | Unused placeholder for client compatibility; payments use x402 headers / free quota |
| endpoint* | string | OpenAI-compatible base URL (https://…/v1) or chat completions URL, or "workers-ai" to use the Workers AI binding as the target (self-check) |
| authHeader | string | Optional Authorization value for the target (Bearer …). Used in memory only; never stored or logged. |
{
"type": "object",
"required": [
"endpoint",
"model"
],
"properties": {
"model": {
"type": "string",
"description": "Claimed model id. Supported: llama-3.1-8b, llama-3.2-3b, llama-3.3-70b, llama-4-scout, qwen3-30b, qwen2.5-coder-32b, gpt-oss-20b, gpt-oss-120b, gemma-4-26b, glm-4.7-flash"
},
"apiKey": {
"type": "string",
"description": "Unused placeholder for client compatibility; payments use x402 headers / free quota"
},
"endpoint": {
"type": "string",
"description": "OpenAI-compatible base URL (https://…/v1) or chat completions URL, or \"workers-ai\" to use the Workers AI binding as the target (self-check)"
},
"authHeader": {
"type": "string",
"description": "Optional Authorization value for the target (Bearer …). Used in memory only; never stored or logged."
}
}
}Recount visible tokens vs seller usage/charge. Free 5/day then 0.01 USDC.
| Argument | Type | Description |
|---|---|---|
| model | string | Claimed model id (informational) |
| request | object | Original request (messages) for input size estimate |
| response* | object | Seller response object with content and optional usage {prompt_tokens,completion_tokens} |
| chargedUsd | number | Amount charged in USDC (optional) |
| priceTable | object | Optional {inputPerMTok, outputPerMTok} USD per million tokens |
| chargedAtomic | number | Amount charged in USDC atomic units (1e6 = 1 USDC) |
{
"type": "object",
"required": [
"response"
],
"properties": {
"model": {
"type": "string",
"description": "Claimed model id (informational)"
},
"request": {
"type": "object",
"description": "Original request (messages) for input size estimate"
},
"response": {
"type": "object",
"description": "Seller response object with content and optional usage {prompt_tokens,completion_tokens}"
},
"chargedUsd": {
"type": "number",
"description": "Amount charged in USDC (optional)"
},
"priceTable": {
"type": "object",
"description": "Optional {inputPerMTok, outputPerMTok} USD per million tokens"
},
"chargedAtomic": {
"type": "number",
"description": "Amount charged in USDC atomic units (1e6 = 1 USDC)"
}
}
}List supported Workers AI reference models (free, read-only).
No arguments.
{
"type": "object",
"properties": {}
}Paid, read-only: probe catalog + supported Workers AI models + pricing snapshot. 0.001 USDC via x402 (strictly paid — no free tier).
No arguments.
{
"type": "object",
"properties": {}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 10, 2026.
Takes a password, API key or token as an argument, so the secret passes through the model's context and chat logs.
Fix: Read credentials from the server's own configuration (environment, OAuth) instead of a tool argument.