# dev.workers.kikoribera03.flat-rate-llm/x402-tools (remote · flat-rate-llm.kikoribera03.workers.dev) 61 x402 pay-per-call tools that chain: each answer names the next call. No API key, no account. - Trust score: 65/100 (medium) - Change this week: +3 - Registry status: active - Liveness: live - Owner verified: no - Last scored: 2026-09-20 ## Components - remote · `flat-rate-llm.kikoribera03.workers.dev`: 65/100 (this document), [markdown](https://verifymcp.io/servers/dev-workers-kikoribera03-flat-rate-llm-x402-tools/flat-rate-llm.md), [page](https://verifymcp.io/servers/dev-workers-kikoribera03-flat-rate-llm-x402-tools/flat-rate-llm) ## Channel facts - Endpoint: `https://flat-rate-llm.kikoribera03.workers.dev/mcp` - Transports: `streamable-http` - Auth: `none` - Version: `1.2.0` ## Trust breakdown How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog) Scored 2026-09-20. - **Endpoint Security**: 46/100 - The endpoint's TLS certificate is valid, in date, and uses a strong key. - Authorisation not fully verified: no authorisation is required to call this server, and 66 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. - HSTS check failed: the Strict-Transport-Security header is absent. - DNSSEC check failed: this domain isn't protected by DNSSEC. - **Transport & Reachability**: 100/100 - Verified streamable-http transport via a live MCP handshake. - **Schema Quality & AI Usability**: 74/100 - AI-judged instruction clarity (excellent). - Context-footprint check failed: tool/resource definitions use about 8338 tokens (~126/item across 66 items; 66 tools + 0 resources), over budget; trim descriptions and params. - Usage-examples check failed: none of the tools include examples. - **Stability & Change Management**: 37/100 - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses. - **Tool Coverage**: 100/100 - 100% of tools have a non-trivial description (not blank, and not just the tool's name). - 100% of tool parameters carry a description. - **Tool Safety**: 100/100 - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured. - We read all 66 captured tool definition(s), and no name or description among them implies an irreversible operation. - An AI judge read all 67 captured unit(s) of tool text and found none that tries to manipulate the model reading it. - **Capabilities**: 100/100 - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28. ## Install ### How do I install the dev.workers.kikoribera03.flat-rate-llm/x402-tools MCP server? dev.workers.kikoribera03.flat-rate-llm/x402-tools is a hosted endpoint at https://flat-rate-llm.kikoribera03.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation. ### Claude ```bash claude mcp add --transport http dev-workers-kikoribera03-flat-rate-llm-x402-tool 'https://flat-rate-llm.kikoribera03.workers.dev/mcp' ``` ### Cursor ```json { "mcpServers": { "dev-workers-kikoribera03-flat-rate-llm-x402-tool": { "url": "https://flat-rate-llm.kikoribera03.workers.dev/mcp" } } } ``` ### VS Code ```json { "servers": { "dev-workers-kikoribera03-flat-rate-llm-x402-tool": { "type": "http", "url": "https://flat-rate-llm.kikoribera03.workers.dev/mcp" } } } ``` ### Codex ```toml [mcp_servers.dev-workers-kikoribera03-flat-rate-llm-x402-tool] url = "https://flat-rate-llm.kikoribera03.workers.dev/mcp" ``` ### opencode ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "dev-workers-kikoribera03-flat-rate-llm-x402-tool": { "type": "remote", "url": "https://flat-rate-llm.kikoribera03.workers.dev/mcp", "enabled": true } } } ``` ### OpenClaw ```bash openclaw mcp add dev-workers-kikoribera03-flat-rate-llm-x402-tool --url 'https://flat-rate-llm.kikoribera03.workers.dev/mcp' --transport streamable-http ``` ### Hermes ```yaml mcp_servers: dev-workers-kikoribera03-flat-rate-llm-x402-tool: url: "https://flat-rate-llm.kikoribera03.workers.dev/mcp" ``` ### Netclaw ```json { "McpServers": { "dev-workers-kikoribera03-flat-rate-llm-x402-tool": { "Transport": "http", "Url": "https://flat-rate-llm.kikoribera03.workers.dev/mcp" } } } ``` ### Vellum ```bash assistant mcp add dev-workers-kikoribera03-flat-rate-llm-x402-tool -t streamable-http -u 'https://flat-rate-llm.kikoribera03.workers.dev/mcp' ``` ### Other ```json { "mcpServers": { "dev-workers-kikoribera03-flat-rate-llm-x402-tool": { "type": "http", "url": "https://flat-rate-llm.kikoribera03.workers.dev/mcp" } } } ``` The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs. ## Changelog Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims. ### 2026-09-20 (score 65, +1) No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-17 (score 64, +1) No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-15 (score 63, +1) No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes. ### 2026-09-14 (score 62, 0) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “catalog” rewrote its description, which is the text the model reads - [security] Tool “red_email_check” rewrote its description, which is the text the model reads - [functional] New tool “ai_image” - [functional] New tool “ai_speech” - [functional] New tool “ai_transcribe” ### 2026-09-13 (score 62, +1) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “catalog” rewrote its description, which is the text the model reads - [functional] New tool “evm_token_price” ### 2026-09-12 (score 61, 0) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “catalog” rewrote its description, which is the text the model reads - [functional] New tool “crypto_sanctions” ### 2026-09-11 (score 61, 0) - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “content_advice” rewrote its description, which is the text the model reads - [security] Tool “content_fact” rewrote its description, which is the text the model reads - [security] Tool “content_horror_story” rewrote its description, which is the text the model reads - [security] Tool “content_joke” rewrote its description, which is the text the model reads - [security] Tool “content_riddle” rewrote its description, which is the text the model reads - [security] Tool “content_roast” rewrote its description, which is the text the model reads - [security] Tool “content_word_of_the_day” rewrote its description, which is the text the model reads - [security] Tool “evm_balance” rewrote its description, which is the text the model reads - [security] Tool “evm_block” rewrote its description, which is the text the model reads - [security] Tool “evm_call” rewrote its description, which is the text the model reads - [security] Tool “evm_chains” rewrote its description, which is the text the model reads - [security] Tool “evm_ens” rewrote its description, which is the text the model reads - [security] Tool “evm_erc20_allowance” rewrote its description, which is the text the model reads - [security] Tool “evm_erc20_balance” rewrote its description, which is the text the model reads - [security] Tool “evm_estimate_gas” rewrote its description, which is the text the model reads - [security] Tool “evm_fees” rewrote its description, which is the text the model reads - [security] Tool “evm_gas” rewrote its description, which is the text the model reads - [security] Tool “evm_is_contract” rewrote its description, which is the text the model reads - [security] Tool “evm_nft_owner” rewrote its description, which is the text the model reads - [security] Tool “evm_nonce” rewrote its description, which is the text the model reads - [security] Tool “evm_portfolio” rewrote its description, which is the text the model reads - [security] Tool “evm_receipt” rewrote its description, which is the text the model reads - [security] Tool “evm_storage” rewrote its description, which is the text the model reads - [security] Tool “evm_token_info” rewrote its description, which is the text the model reads - [security] Tool “evm_token_safety” rewrote its description, which is the text the model reads - [security] Tool “evm_tx” rewrote its description, which is the text the model reads - [security] Tool “fx_convert” rewrote its description, which is the text the model reads - [security] Tool “llm_completion” rewrote its description, which is the text the model reads - [security] Tool “random_coinflip” rewrote its description, which is the text the model reads - [security] Tool “random_dice” rewrote its description, which is the text the model reads - [security] Tool “random_number” rewrote its description, which is the text the model reads - [security] Tool “random_password” rewrote its description, which is the text the model reads - [security] Tool “random_pick” rewrote its description, which is the text the model reads - [security] Tool “random_shuffle” rewrote its description, which is the text the model reads - [security] Tool “red_asn” rewrote its description, which is the text the model reads - [security] Tool “red_dnsbl” rewrote its description, which is the text the model reads - [security] Tool “red_domain_check” rewrote its description, which is the text the model reads - [security] Tool “red_email_check” rewrote its description, which is the text the model reads - [security] Tool “red_ip” rewrote its description, which is the text the model reads - [security] Tool “red_whois” rewrote its description, which is the text the model reads - [security] Tool “time_convert” rewrote its description, which is the text the model reads - [security] Tool “time_now” rewrote its description, which is the text the model reads - [security] Tool “time_zones” rewrote its description, which is the text the model reads - [security] Tool “util_address” rewrote its description, which is the text the model reads - [security] Tool “util_base64” rewrote its description, which is the text the model reads - [security] Tool “util_hex” rewrote its description, which is the text the model reads - [security] Tool “util_iban” rewrote its description, which is the text the model reads - [security] Tool “util_keccak256” rewrote its description, which is the text the model reads - [security] Tool “util_phone” rewrote its description, which is the text the model reads - [security] Tool “util_selector” rewrote its description, which is the text the model reads - [security] Tool “util_sha256” rewrote its description, which is the text the model reads - [security] Tool “util_units” rewrote its description, which is the text the model reads - [security] Tool “util_uuid” rewrote its description, which is the text the model reads - [security] Tool “util_vat” rewrote its description, which is the text the model reads - [security] Tool “util_verify_signature” rewrote its description, which is the text the model reads - [security] Tool “web_read” rewrote its description, which is the text the model reads - [security] Tool “web_status” rewrote its description, which is the text the model reads - [security] Tool “catalog” rewrote its description, which is the text the model reads - [functional regression] Schema quality: 5678 → 7488 - [functional regression] Schema quality: 5678 → 6998 - [functional] New tool “red_cert” - [functional] New tool “weather_forecast” - [functional] New tool “weather_now” - [functional] New tool “fx_convert” - [functional] New tool “red_asn” - [functional] New tool “red_dnsbl” - [functional] New tool “red_ip” - [functional] New tool “red_whois” - [functional] New tool “util_iban” - [functional] New tool “util_phone” - [functional] New tool “util_vat” - [functional] New tool “web_status” ### 2026-09-10 (score 61, 0) - [security regression] A breaking change shipped without a version bump: still 1.0.0 - [security] The server rewrote its instructions, which are the text every model session reads - [security] Tool “catalog” rewrote its description, which is the text the model reads - [security] Tool “evm_balance” rewrote its description, which is the text the model reads - [security] Tool “evm_block” rewrote its description, which is the text the model reads - [security] Tool “evm_chains” rewrote its description, which is the text the model reads - [security] Tool “evm_erc20_allowance” rewrote its description, which is the text the model reads - [security] Tool “evm_erc20_balance” rewrote its description, which is the text the model reads - [security] Tool “evm_estimate_gas” rewrote its description, which is the text the model reads - [security] Tool “evm_fees” rewrote its description, which is the text the model reads - [security] Tool “evm_gas” rewrote its description, which is the text the model reads - [security] Tool “evm_is_contract” rewrote its description, which is the text the model reads - [security] Tool “evm_nft_owner” rewrote its description, which is the text the model reads - [security] Tool “evm_nonce” rewrote its description, which is the text the model reads - [security] Tool “evm_portfolio” rewrote its description, which is the text the model reads - [security] Tool “evm_receipt” rewrote its description, which is the text the model reads - [security] Tool “evm_storage” rewrote its description, which is the text the model reads - [security] Tool “evm_token_info” rewrote its description, which is the text the model reads - [security] Tool “evm_tx” rewrote its description, which is the text the model reads - [security] Tool “llm_completion” rewrote its description, which is the text the model reads - [functional regression] Schema quality: pass → fail - [functional regression] “random_pick” changed the type of “items”: array → string - [functional regression] “random_shuffle” changed the type of “items”: array → string - [functional improvement] Stability: unverified → 0.03 - [functional] New tool “content_horror_story” - [functional] New tool “content_roast” - [functional] New tool “evm_token_safety” - [functional] New tool “red_domain_check” - [functional] New tool “red_email_check” - [functional] New tool “web_read” - [functional] New tool “content_advice” - [functional] New tool “content_fact” - [functional] New tool “content_joke” - [functional] New tool “content_riddle” - [functional] New tool “content_word_of_the_day” - [functional] New tool “random_coinflip” - [functional] New tool “random_dice” - [functional] New tool “random_number” - [functional] New tool “random_password” - [functional] New tool “random_pick” - [functional] New tool “random_shuffle” - [functional] New tool “time_convert” - [functional] New tool “time_now” - [functional] New tool “time_zones” - [cosmetic] “random_pick” reworded the description of “items” - [cosmetic] “random_shuffle” reworded the description of “items” ## MCP tools (66) ### `catalog` (~56 tokens) Catalogue (free) FREE, no payment needed. Lists all 65 tools with a real example of the input and of the output each one returns, plus what a call costs and how to pay for it. Call this first if a tool answered HTTP 402. ### `llm_completion` (~161 tokens) Flat-rate LLM LLM inference at a flat $1.00 per call, with no account, no API key and no token metering. POST a prompt, get the completion: the same price for 10 tokens or 4000, while metered gateways scale with usage. Automatic failover across several large models; typical response under 1s. Pay per call in USDC over x402 - nothing to sign up for. $1.00 per call, paid over x402 (USDC). Input parameters: - `maxTokens` (number): Output token cap, up to 4000. Does not change the price. - `prompt` (string, required): The request for the model. Up to 24000 characters. - `sistema` (string): Optional system instruction. ### `evm_balance` (~104 tokens) EVM native balance Native coin balance (ETH, MATIC...) for any address, on Base, Ethereum, Polygon, Arbitrum or Optimism. Flat price, no rate limits, no API key. Via eth_getBalance. $0.005 per call, paid over x402 (USDC). Input parameters: - `address` (string, required): 0x-prefixed address to look up. - `chain` (string): base | ethereum | polygon | arbitrum | optimism. Defaults to base. ### `evm_erc20_balance` (~110 tokens) ERC20 token balance ERC20 token balance for any wallet - USDC, USDT, DAI or any token - via balanceOf. Returns the raw amount and the decimals so you can format it. Via eth_call (balanceOf). $0.005 per call, paid over x402 (USDC). Input parameters: - `address` (string, required): Wallet to look up. - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `token` (string, required): ERC20 contract address. ### `evm_token_info` (~87 tokens) ERC20 token info Name, symbol, decimals and total supply of any ERC20 contract in one call. Useful to label a token address before showing it to a user. Via eth_call. $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `token` (string, required): ERC20 contract address. ### `evm_token_price` (~157 tokens) DEX token price, with the pool that produced it Spot price of any ERC20 read straight from the deepest Uniswap V3 pool against USDC, on Base, Ethereum, Polygon, Arbitrum or Optimism. Returns the pool address, fee tier, liquidity, sqrtPriceX96, tick and block, so the number can be audited instead of trusted. No aggregator and no API key: the source is the chain itself. Via eth_call. $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `quote` (string): Token to price it against. Defaults to the chain's native USDC. - `token` (string, required): ERC20 contract address to price. ### `evm_gas` (~80 tokens) EVM gas price Current gas price and base fee for any supported chain, in wei and gwei, plus the cost estimate of a plain transfer. For agents planning a transaction. Via eth_gasPrice. $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. ### `evm_block` (~79 tokens) EVM block height Latest block height and timestamp of any supported chain, plus how old the chain head is in seconds. Tells an agent whether a node is in sync. Via eth_getBlockByNumber. $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. ### `evm_tx` (~87 tokens) EVM transaction Full transaction details by hash, merged with its receipt: from, to, value, gas used, status and block. One call instead of two. Via eth_getTransactionByHash. $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `hash` (string, required): Transaction hash. ### `evm_nonce` (~82 tokens) EVM address nonce Next transaction nonce for any address, and whether the address is a contract. What an agent needs before signing a transaction. Via eth_getTransactionCount. $0.005 per call, paid over x402 (USDC). Input parameters: - `address` (string, required): Address to look up. - `chain` (string): base | ethereum | polygon | arbitrum | optimism. ### `evm_is_contract` (~87 tokens) Contract or wallet Tells whether an address is a smart contract or a plain wallet, and how big its bytecode is. A cheap safety check before sending funds. Via eth_getCode. $0.005 per call, paid over x402 (USDC). Input parameters: - `address` (string, required): Address to inspect. - `chain` (string): base | ethereum | polygon | arbitrum | optimism. ### `evm_chains` (~65 tokens) Chain health check Live health of every supported chain in one call: chain id, block height and how stale the head is. Use it to pick a chain that is actually responding. Via eth_getBlockByNumber. $0.005 per call, paid over x402 (USDC). ### `evm_call` (~150 tokens) Raw contract call Runs any read-only contract call (eth_call) with your own calldata and returns the raw result, on five chains, with no API key and no rate limit. The escape hatch for anything the typed endpoints do not cover. $0.005 per call, paid over x402 (USDC). Input parameters: - `block` (string): Block tag or number. Defaults to latest. - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `data` (string, required): 0x-prefixed calldata: 4-byte selector plus encoded arguments. - `from` (string): Optional caller address, for calls that check msg.sender. - `to` (string, required): Contract address to call. ### `evm_receipt` (~94 tokens) Transaction receipt Receipt of a transaction: whether it succeeded or reverted, gas used, fee actually paid, and how many logs it emitted. The call that answers did my transaction work. Via eth_getTransactionReceipt. $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `hash` (string, required): 32-byte transaction hash. ### `evm_estimate_gas` (~130 tokens) Estimate gas Estimates the gas a transaction would need and prices it at the current gas price, before you sign anything. Also the cheapest way to find out that a call would revert. Via eth_estimateGas. $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `data` (string): Optional 0x calldata. - `from` (string): Sender address. - `to` (string, required): Destination address. - `value` (string): Optional value in wei, as a decimal string. ### `evm_storage` (~119 tokens) Raw contract storage Reads a raw storage slot of any contract, decoded as hex, integer and address. How you inspect proxy implementation slots, owners and paused flags that have no public getter. Via eth_getStorageAt. $0.005 per call, paid over x402 (USDC). Input parameters: - `address` (string, required): Contract to read. - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `slot` (string): Slot number in decimal, or a 0x slot key such as an EIP-1967 hash. ### `evm_erc20_allowance` (~128 tokens) ERC20 allowance How much of a token a spender is still allowed to move on an owner's behalf, and whether that approval is unlimited. The check to run before an approve, and the one that finds forgotten infinite approvals. Via eth_call (allowance). $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `owner` (string, required): Address that owns the tokens. - `spender` (string, required): Address allowed to spend them. - `token` (string, required): ERC20 contract address. ### `evm_nft_owner` (~110 tokens) NFT owner and metadata Who owns a given ERC721 token id, plus its tokenURI and collection name in the same call. Answers is this NFT still theirs without an indexer or an API key. Via eth_call (ownerOf). $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `contract` (string, required): ERC721 contract address. - `tokenId` (string, required): Token id, in decimal. ### `evm_portfolio` (~112 tokens) Wallet token portfolio Native balance plus the balance of every token you list, on one chain, in a single paid call - each with symbol and decimals already applied. One request instead of one per token. Via eth_getBalance + eth_call. $0.005 per call, paid over x402 (USDC). Input parameters: - `address` (string, required): Wallet to inspect. - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `tokens` (array): Up to 20 ERC20 contract addresses. ### `evm_fees` (~91 tokens) EIP-1559 fee suggestion Suggested maxFeePerGas and maxPriorityFeePerGas from the last 20 blocks of real fee history, at slow, normal and fast percentiles. Beats guessing a gas price and getting stuck in the mempool. Via eth_feeHistory. $0.005 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. ### `evm_ens` (~96 tokens) ENS name resolution Resolves an ENS name to its address, or an address back to its primary ENS name, reading Ethereum mainnet directly. Names are what humans paste and addresses are what chains need. $0.005 per call, paid over x402 (USDC). Input parameters: - `address` (string): Address to reverse-resolve. Use instead of name. - `name` (string): ENS name to resolve, such as vitalik.eth. ### `evm_token_safety` (~157 tokens) ERC20 pre-trade safety check Pre-trade risk check for any ERC20 on Base, Ethereum, Polygon, Arbitrum or Optimism, straight from the deployed bytecode and live state. Detects mint, pause, blacklist, upgradeable proxy and mutable buy/sell tax powers, and reports whether ownership is renounced. Unlike LLM-written verdicts this returns the EVIDENCE - the exact selector found and its byte offset - so an agent can apply its own policy. Deterministic: same contract, same answer. $0.01 per call, paid over x402 (USDC). Input parameters: - `chain` (string): base | ethereum | polygon | arbitrum | optimism. - `token` (string, required): ERC20 contract address to check. ### `util_keccak256` (~90 tokens) Keccak-256 hash Keccak-256 of any string or hex payload - the hash Ethereum actually uses, which is NOT the same as SHA3-256. Needed for selectors, event topics, salts and CREATE2 addresses. $0.0025 per call, paid over x402 (USDC). Input parameters: - `input` (string, required): Plain text, or a 0x-prefixed hex payload to hash as bytes. ### `util_sha256` (~83 tokens) SHA-256 hash SHA-256 of any string or hex payload, returned as hex and as base64. The hash everything outside Ethereum uses: file digests, API signatures, content addressing. $0.0025 per call, paid over x402 (USDC). Input parameters: - `input` (string, required): Plain text, or a 0x-prefixed hex payload to hash as bytes. ### `util_address` (~79 tokens) Address checksum and validation Validates an EVM address and returns it in EIP-55 mixed-case checksum form. Catches typos before you send funds: an address that fails the checksum is almost always mistyped. $0.0025 per call, paid over x402 (USDC). Input parameters: - `address` (string, required): The address to validate, in any case. ### `util_units` (~119 tokens) Token unit converter Converts between wei, gwei, ether and any token decimals using exact integer maths - no floating point, no silent rounding. The mistake that costs real money is being off by a thousand on decimals. $0.0025 per call, paid over x402 (USDC). Input parameters: - `amount` (string, required): The quantity, as a string to avoid float loss. - `from` (string, required): wei | gwei | ether, or a number of decimals. - `to` (string, required): wei | gwei | ether, or a number of decimals. ### `util_hex` (~107 tokens) Hex converter Converts between hex, decimal and UTF-8 text in one call, with big integers handled exactly. For reading raw RPC output, which comes back as hex and overflows a JavaScript number. $0.0025 per call, paid over x402 (USDC). Input parameters: - `as` (string): hex | decimal | text. What the value IS. Defaults to autodetect. - `value` (string, required): A 0x-prefixed hex string, a decimal number, or text. ### `util_base64` (~110 tokens) Base64 encode and decode Base64 in both directions, including the URL-safe alphabet, with UTF-8 handled properly. Encoding is what carries payloads through headers and JSON, and x402 itself rides on it. $0.0025 per call, paid over x402 (USDC). Input parameters: - `input` (string, required): The text or base64 to convert. - `mode` (string): encode | decode. Defaults to encode. - `urlSafe` (boolean): Use the URL-safe alphabet (-_ instead of +/). ### `util_uuid` (~87 tokens) UUID v4 generator Cryptographically random UUID v4s, up to 100 per call, straight from the platform CSPRNG. For idempotency keys, request ids and correlation ids - the ones that must not collide. $0.0025 per call, paid over x402 (USDC). Input parameters: - `count` (number): How many to generate, 1-100. Defaults to 1. ### `util_verify_signature` (~113 tokens) Verify wallet signature Recovers the address that signed a personal_sign (EIP-191) message and tells you whether it matches the address you expected. This is how you prove a wallet is controlled by whoever is talking to you. $0.0025 per call, paid over x402 (USDC). Input parameters: - `expected` (string): Optional address to compare the recovered signer against. - `message` (string, required): The exact message that was signed. - `signature` (string, required): 65-byte 0x signature from personal_sign. ### `util_selector` (~86 tokens) Function selector and event topic Turns a Solidity signature like transfer(address,uint256) into its 4-byte function selector and its 32-byte event topic0. What you need to build calldata by hand or to filter logs. $0.0025 per call, paid over x402 (USDC). Input parameters: - `signature` (string, required): Canonical signature: name(type1,type2), no spaces and no argument names. ### `random_dice` (~121 tokens) Dice roller Roll dice with any number of faces and get every roll plus the total. Uses the platform CSPRNG with rejection sampling, so every face is equally likely - a plain modulo is biased. Standard dice notation: 3d6, 1d20. $0.0025 per call, paid over x402 (USDC). Input parameters: - `count` (number): How many dice to roll, 1-100. Defaults to 1. - `faces` (number): Faces per die, 2-1000000. Defaults to 6. ### `random_coinflip` (~88 tokens) Coin flip Flip one or more fair coins and get heads or tails, with the tally. Cryptographically random, not Math.random. For tie-breaks and A/B splits an agent has to decide on its own. $0.0025 per call, paid over x402 (USDC). Input parameters: - `count` (number): How many coins to flip, 1-100. Defaults to 1. ### `random_pick` (~131 tokens) Random pick Pick one or more items at random from a list you send, with or without repeats. The list is yours, so this is the unbiased chooser an agent needs when it has options and no reason to prefer any. $0.0025 per call, paid over x402 (USDC). Input parameters: - `count` (number): How many to pick, 1-100. Defaults to 1. - `items` (string, required): The options, comma-separated. A JSON array of strings is also accepted in a POST body. - `repeat` (boolean): Allow the same item more than once. Defaults to false. ### `random_shuffle` (~87 tokens) Shuffle a list Shuffle a list into a uniformly random order with Fisher-Yates over the platform CSPRNG. Every permutation is equally likely, which sorting by a random key does not give you. $0.0025 per call, paid over x402 (USDC). Input parameters: - `items` (string, required): The list to shuffle, comma-separated. A JSON array of strings is also accepted in a POST body. ### `random_password` (~129 tokens) Password generator Generate strong random secrets from the platform CSPRNG, with the entropy in bits so you can judge them. Four alphabets, including one with no look-alike characters for anything a human has to read back. $0.0025 per call, paid over x402 (USDC). Input parameters: - `alphabet` (string): alnum | legible | hex | completo. Defaults to legible. - `count` (number): How many to generate, 1-50. Defaults to 1. - `length` (number): Characters per secret, 8-256. Defaults to 20. ### `random_number` (~133 tokens) Random number Uniform random integers in any range you give, with or without repeats. Rejection sampling, so the ends of the range are not slightly less likely - which is what happens with modulo. $0.0025 per call, paid over x402 (USDC). Input parameters: - `count` (number): How many to draw, 1-100. Defaults to 1. - `max` (number): Highest value, inclusive. Defaults to 100. - `min` (number): Lowest value, inclusive. Defaults to 1. - `unique` (boolean): No repeats. Needs a range at least as wide as count. ### `time_convert` (~193 tokens) Time zone converter Convert a time between any two IANA time zones, with daylight saving applied from the runtime's own tz database. Returns both sides with their UTC offset, abbreviation and DST flag, plus the UTC instant and the difference in hours. Warns when the time you asked for does not exist or happens twice because the clocks change that day: the two cases that quietly make a hand-made conversion wrong. $0.0025 per call, paid over x402 (USDC). Input parameters: - `from` (string, required): Source IANA time zone, e.g. "Europe/Madrid". Required. - `time` (string): Wall clock as YYYY-MM-DD HH:MM in the "from" zone, or an ISO string with Z or an offset, or a unix timestamp, or "now". Defaults to now. - `to` (string, required): Target IANA time zone, e.g. "Asia/Tokyo". Required. ### `time_now` (~120 tokens) Current time in a time zone The current time in any IANA time zone, in every form an agent needs at once: ISO with offset, 24-hour, 12-hour, weekday, unix timestamp and UTC. It also says whether daylight saving is active right now and what the zone's standard offset is, so a shifted clock can be told apart from a permanent one. $0.0025 per call, paid over x402 (USDC). Input parameters: - `zone` (string, required): IANA time zone, e.g. "Asia/Tokyo" or "UTC". Required. ### `time_zones` (~154 tokens) Time zone directory Search the full IANA time zone list and get each zone's current UTC offset, abbreviation, local time and DST state. Use it to turn a city or a country into the exact zone name the other endpoints expect, or to find every zone sitting at a given offset right now. $0.0025 per call, paid over x402 (USDC). Input parameters: - `limit` (number): Maximum zones returned, 1-500. Defaults to 50. - `offset` (string): Keep only zones at this current UTC offset, e.g. "+09:00" or "-5". - `search` (string): Substring matched against the zone name, case-insensitive. Omit to list them all. ### `content_horror_story` (~164 tokens) Two-sentence horror story One two-sentence horror story, in English or Spanish, by theme: domestic, technological, cosmic or folk. Returned SPLIT into setup and payoff as well as joined, so a narrating agent can deliver the first line, pause, and then land the second. Takes parameters, returns an id to avoid repeats, and accepts a seed for a reproducible answer. $0.0025 per call, paid over x402 (USDC). Input parameters: - `exclude` (array): Ids already seen, comma-separated in a GET. - `language` (string): en | es. Defaults to en. - `seed` (string): Same seed always returns the same story. - `theme` (string): domestic | technological | cosmic | folk. Omit for any. ### `content_roast` (~188 tokens) Developer roast, on a target you pick One lighthearted developer roast aimed at a target YOU choose - javascript, python, css, git, regex, kubernetes, agile or legacy code - and at the severity you ask for. Every other roast endpoint returns something generic; this one lets a code-review agent roast the actual stack in front of it. Bilingual, seedable and repeat-free. $0.0025 per call, paid over x402 (USDC). Input parameters: - `exclude` (array): Ids already seen, comma-separated in a GET. - `language` (string): en | es. Defaults to en. - `seed` (string): Same seed always returns the same roast. - `severity` (string): mild | medium | savage. Omit for any. - `target` (string): javascript | python | css | git | regex | kubernetes | agile | legacy. Omit for any. ### `content_joke` (~141 tokens) Random joke One random joke, in English or Spanish, filtered by category: programming, crypto or general. Unlike the usual one-liner endpoints this one takes parameters, returns an id so you can exclude what you have already seen, and accepts a seed for a reproducible answer. $0.0025 per call, paid over x402 (USDC). Input parameters: - `category` (string): programming | crypto | general. Omit for any. - `exclude` (array): Ids already seen, comma-separated in a GET. - `language` (string): en | es. Defaults to en. - `seed` (string): Same seed always returns the same joke. ### `content_fact` (~136 tokens) Random fact One curious but true fact, in English or Spanish, filtered by topic: science, computing, history or nature. Takes parameters, returns an id so you can avoid repeats across a session, and accepts a seed for a reproducible answer. $0.0025 per call, paid over x402 (USDC). Input parameters: - `exclude` (array): Ids already seen, comma-separated in a GET. - `language` (string): en | es. Defaults to en. - `seed` (string): Same seed always returns the same fact. - `topic` (string): science | computing | history | nature. Omit for any. ### `content_riddle` (~144 tokens) Riddle with checkable answer One riddle by difficulty, in English or Spanish, with the answer AND the SHA-256 of the answer in lowercase. The hash is the point: an agent can check whether its guess is right without reading the solution first, which no other riddle endpoint lets you do. $0.0025 per call, paid over x402 (USDC). Input parameters: - `difficulty` (string): easy | medium | hard. Omit for any. - `exclude` (array): Ids already seen, comma-separated in a GET. - `language` (string): en | es. Defaults to en. - `seed` (string): Same seed always returns the same riddle. ### `content_advice` (~133 tokens) One piece of advice One piece of practical advice about work, life or money, in English or Spanish. Short, concrete and usable - not a fortune cookie. Filterable by topic, with an id to avoid repeats and a seed for reproducibility. $0.0025 per call, paid over x402 (USDC). Input parameters: - `exclude` (array): Ids already seen, comma-separated in a GET. - `language` (string): en | es. Defaults to en. - `seed` (string): Same seed always returns the same advice. - `topic` (string): work | life | money. Omit for any. ### `content_word_of_the_day` (~138 tokens) Word of the day The word of the day with its definition, part of speech and an example sentence, in English or Spanish. Genuinely of the day: it is picked deterministically from the UTC date, so everyone gets the same word and you can reproduce any past day by passing it. The usual endpoints just return a random word and call it the word of the day. $0.0025 per call, paid over x402 (USDC). Input parameters: - `date` (string): YYYY-MM-DD in UTC. Defaults to today, and any past date is reproducible. - `language` (string): en | es. Defaults to en. ### `red_email_check` (~142 tokens) Email address check Scores one email address 0-100 with a verdict (ok, risky, disposable, undeliverable, invalid) and the evidence under it: every point lost is itemised with the field that proves it. 12,141 disposable domains from two maintained open lists pinned to a commit, 4,897 free providers, 1,018 role names, typo fix (gmial.com > gmail.com), live MX/SPF/DMARC. No SMTP probe, no API key. $0.005 per call, paid over x402 (USDC). Input parameters: - `email` (string, required): The address to check, e.g. someone@example.com. ### `red_domain_check` (~116 tokens) Domain DNS check Everything DNS says about one domain in a single call: whether it is registered, its A and AAAA addresses, nameservers, MX servers, SPF and DMARC, DNSSEC, and whether it looks parked. Built for going through a list of domains one at a time. Live DNS, no API key, no account. $0.005 per call, paid over x402 (USDC). Input parameters: - `domain` (string, required): The domain to check. A full URL or an email address is accepted and reduced to its host. ### `web_read` (~130 tokens) Read a web page as markdown Fetches one URL and returns the readable page as markdown: title, description, headings, paragraphs and links with their destinations, plus the canonical URL, language and word count. Boilerplate, scripts and navigation are stripped. Built for going through a list of links one at a time. No API key, no account. $0.01 per call, paid over x402 (USDC). Input parameters: - `links` (boolean): Also return the outbound links as a list. Defaults to false. - `url` (string, required): The page to read. http and https only; private and loopback addresses are refused. ### `util_iban` (~106 tokens) IBAN check Validates one IBAN offline: country, expected length, ISO 7064 mod-97 check digits, whether it is inside SEPA, and the account number split out. Deterministic, no network call and no third party that can go down. Built for cleaning a list of accounts one at a time. $0.005 per call, paid over x402 (USDC). Input parameters: - `iban` (string, required): The IBAN to check. Spaces and lowercase are accepted. ### `util_vat` (~105 tokens) EU VAT number check Validates one EU VAT number offline: country prefix, the format that country uses, and the published check-digit algorithm where one exists. Says explicitly whether the check digits were verified or only the format. Deterministic, no network call. Built for cleaning a list of companies one at a time. $0.005 per call, paid over x402 (USDC). Input parameters: - `vat` (string, required): The VAT number, with or without the country prefix and with any spacing. ### `web_status` (~136 tokens) URL status and redirect chain Checks one URL without downloading the page: HTTP status, the full redirect chain hop by hop with the code of each, the final URL, whether it ends on HTTPS, content type and size, and the security headers the server sends. Built for going through a list of links one at a time. No API key, no account. $0.005 per call, paid over x402 (USDC). Input parameters: - `method` (string): HEAD (default) or GET. Some servers refuse HEAD and only answer GET. - `url` (string, required): The URL to check. http and https only; private and loopback addresses are refused. ### `red_ip` (~139 tokens) IP address intelligence Looks up one IPv4 or IPv6 address against the two authoritative, keyless public sources: RDAP registry data (who holds the block, in which country, since when, abuse contact) via the ARIN-to-RIR referral chain, and the origin ASN from Team Cymru's DNS service. No city-level geolocation and no VPN/proxy detection — those need a licensed commercial database this endpoint deliberately does not use. Built for going through a list of IPs one at a time. $0.005 per call, paid over x402 (USDC). Input parameters: - `ip` (string, required): The IPv4 or IPv6 address to look up. ### `red_asn` (~156 tokens) ASN lookup Everything the authoritative public sources say about one autonomous system number: the RDAP registry record via the ARIN-to-RIR referral chain (holder, status, allocation dates, abuse contact), the AS name, country and RIR from Team Cymru's DNS service, and the prefixes it is announcing right now in the global routing table, from RIPEstat, split into IPv4 and IPv6 with a sample. Keyless and free at the source. The natural second call after /v1/red/ip gives you an origin ASN. $0.005 per call, paid over x402 (USDC). Input parameters: - `asn` (string, required): The AS number, with or without the AS prefix: 15169 or AS15169. ### `red_dnsbl` (~153 tokens) IP blocklist check Checks one IPv4 address against nine public DNS blocklists at once — SpamCop, UCEPROTECT, PSBL, Barracuda, DroneBL and four more — and returns each list's raw return code plus the reason text the list itself publishes, not a score. Every list is re-checked on each call with its RFC 5782 test entry, so a dead list or one that refuses queries comes back as unavailable instead of reading as clean. Includes the delisting URL for each hit. $0.005 per call, paid over x402 (USDC). Input parameters: - `ip` (string, required): The IPv4 address to check. IPv6 is not accepted: these nine lists are IPv4 zones. ### `util_phone` (~189 tokens) Phone number check Checks one phone number offline: normalises it to E.164, works out its country (including the twelve calling codes shared by several countries, such as +1 US/Canada/Caribbean) and validates the national number length against that country's numbering plan. Returns the tel: URI and the national dialling form. Numbering data from Google's libphonenumber. No network call and no API key, so it cannot fail because a third party is down. $0.005 per call, paid over x402 (USDC). Input parameters: - `country` (string): Optional ISO 3166-1 alpha-2 country, e.g. ES. Only used when the number carries no country code. - `phone` (string, required): The phone number, in any usual notation: +34 612 34 56 78, 0034612345678, (612) 345-678. ### `fx_convert` (~186 tokens) Currency conversion at the official ECB rate Converts an amount between any two of the ~30 currencies in the European Central Bank's official reference rates, on today's publication or on a past date within the last 90 days. Returns the rate used, its publication date and whether it was crossed through the euro. This is the auditable rate accounting and customs ask for, not a live market quote: it is published once a day and it is reproducible. $0.005 per call, paid over x402 (USDC). Input parameters: - `amount` (number): Amount to convert. Defaults to 1. - `date` (string): Optional publication date, YYYY-MM-DD, within the last 90 days. Defaults to the latest publication. - `from` (string, required): Source currency, ISO 4217, e.g. USD. - `to` (string, required): Target currency, ISO 4217, e.g. EUR. ### `red_whois` (~141 tokens) Domain registration lookup (RDAP) Registration data for one domain, read from the registry's own RDAP service through the IANA bootstrap — not scraped from port-43 whois text. Returns creation, expiry and last-change dates, age and days to expiry, registrar, EPP status codes, nameservers, DNSSEC and the abuse contact. TLDs with no RDAP server say so instead of reporting the domain as unregistered. No API key, no account. $0.005 per call, paid over x402 (USDC). Input parameters: - `domain` (string, required): The domain to look up. A full URL or an email address is accepted and reduced to its host. ### `weather_now` (~178 tokens) Current weather from the official national forecast Current conditions for any point on Earth, taken from the Norwegian Meteorological Institute's official forecast model rather than a commercial aggregator. Returns temperature, humidity, pressure, wind speed and bearing, cloud cover and the next hour's precipitation, plus the exact model run it came from and the units the institute itself declares, so the figure can be cited and checked instead of merely trusted. $0.01 per call, paid over x402 (USDC). Input parameters: - `hours` (number): How many hourly steps to include after the current one, 0-24. Defaults to 6. - `lat` (number, required): Latitude in decimal degrees, -90 to 90. Rounded to 4 decimals, which is what the institute accepts. - `lon` (number, required): Longitude in decimal degrees, -180 to 180. Rounded to 4 decimals. ### `weather_forecast` (~177 tokens) Multi-day forecast from the official national service Day-by-day forecast for any point on Earth, up to nine days out, from the Norwegian Meteorological Institute's official model rather than a commercial aggregator. Each day carries its minimum and maximum temperature, total precipitation, strongest wind and the midday symbol, together with the exact model run and the institute's declared units, so a planning decision can cite where the number came from. $0.01 per call, paid over x402 (USDC). Input parameters: - `days` (number): How many days to return, 1-9. Defaults to 5. The last day is usually partial and says so. - `lat` (number, required): Latitude in decimal degrees, -90 to 90. Rounded to 4 decimals. - `lon` (number, required): Longitude in decimal degrees, -180 to 180. Rounded to 4 decimals. ### `red_cert` (~141 tokens) TLS certificate lookup (Certificate Transparency) Every currently valid TLS certificate publicly issued for one domain, read from the Certificate Transparency logs: issuer, validity window, days to expiry, revocation status and every hostname each certificate covers. It reports what was ISSUED, which is how you find certificates you did not know existed - not what the server is serving today. No API key, no account. $0.005 per call, paid over x402 (USDC). Input parameters: - `domain` (string, required): The domain to look up. A full URL or an email address is accepted and reduced to its host. - `subdomains` (boolean): Also return certificates issued for subdomains. Defaults to false. ### `crypto_sanctions` (~137 tokens) OFAC sanctions check for a crypto address Checks one crypto address against the OFAC SDN list published by the US Treasury, across 16 currencies including Ethereum, Bitcoin, Tron and USDT. A hit returns the actual list entry - sanctioned entity, its type and its sanctions programmes - not a risk score. Exact matching only, never fuzzy. Every answer carries the publication date of the list snapshot. No API key, no account. $0.01 per call, paid over x402 (USDC). Input parameters: - `address` (string, required): The crypto address to check. Any chain: EVM, Bitcoin, Tron, Litecoin, Monero and the rest of the list. ### `ai_image` (~174 tokens) Text-to-image (FLUX.1 schnell) Generates a 1024x1024 JPEG from a text prompt with FLUX.1 [schnell] in about 2 seconds. Returns a hosted image URL valid for 24 hours that you can hand straight to the next tool; add inline=true to also get the base64. Choose 1-8 diffusion steps (default 4). You are only charged if the image is delivered. No API key, no account. $0.01 per call, paid over x402 (USDC). Input parameters: - `inline` (boolean): Also return the JPEG as base64. Default false. - `prompt` (string, required): What to draw, up to 2048 characters. English works best. - `steps` (number): Diffusion steps, 1-8. More is sharper and slower. Default 4. ### `ai_speech` (~156 tokens) Text-to-speech (MeloTTS) Turns text into natural speech with MeloTTS in English, Spanish, French, Chinese, Japanese or Korean, in about a second. Returns a hosted WAV URL valid for 24 hours plus its size; add inline=true to also get the base64. Up to 2000 characters per call. You are only charged if the audio is delivered. No API key, no account. $0.005 per call, paid over x402 (USDC). Input parameters: - `inline` (boolean): Also return the WAV as base64. Default false. - `lang` (string): en, es, fr, zh, ja or ko. Default en. - `text` (string, required): What to say, up to 2000 characters. ### `ai_transcribe` (~188 tokens) Speech-to-text (Whisper large v3 turbo) Transcribes an audio file with Whisper large v3 turbo: pass an https URL (mp3, wav, flac, m4a, ogg, up to 10 MB) or base64 audio in a POST. Returns the text, the detected language with its probability, the duration, and timed segments; add words=true for word-level timestamps. Around 100 languages. You are only charged if the transcript is delivered. No API key, no account. $0.01 per call, paid over x402 (USDC). Input parameters: - `audio` (string): Alternative to url: the audio as base64 (POST only). - `language` (string): Optional ISO code to skip detection, e.g. es. - `url` (string): https URL of the audio file, up to 10 MB. - `words` (boolean): Include word-level timestamps. Default false. ## Diagnostics Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-workers-kikoribera03-flat-rate-llm-x402-tools/flat-rate-llm#diagnostics ## Score history - 2026-09-20: 65 - 2026-09-19: 64 - 2026-09-18: 64 - 2026-09-17: 64 - 2026-09-16: 63 - 2026-09-15: 63 - 2026-09-14: 62 - 2026-09-13: 62 - 2026-09-12: 61 - 2026-09-11: 61 - 2026-09-10: 61 - 2026-09-09: 61 ## Common questions ### What is the dev.workers.kikoribera03.flat-rate-llm/x402-tools MCP server? dev.workers.kikoribera03.flat-rate-llm/x402-tools is an MCP server listed in the public MCP registry as dev.workers.kikoribera03.flat-rate-llm/x402-tools. 61 x402 pay-per-call tools that chain: each answer names the next call. No API key, no account. This page covers its hosted endpoint (https://flat-rate-llm.kikoribera03.workers.dev/mcp). ### Is the dev.workers.kikoribera03.flat-rate-llm/x402-tools MCP server safe to use? dev.workers.kikoribera03.flat-rate-llm/x402-tools scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm. ### What tools does the dev.workers.kikoribera03.flat-rate-llm/x402-tools MCP server expose? dev.workers.kikoribera03.flat-rate-llm/x402-tools exposes 66 tools: catalog, llm_completion, evm_balance, evm_erc20_balance, evm_token_info, and 61 more. Their descriptions and schemas cost roughly 8,266 tokens of context every time the server is loaded. ### Does the dev.workers.kikoribera03.flat-rate-llm/x402-tools MCP server require authentication? No. We connected to dev.workers.kikoribera03.flat-rate-llm/x402-tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address. ### Is the dev.workers.kikoribera03.flat-rate-llm/x402-tools MCP server still maintained? dev.workers.kikoribera03.flat-rate-llm/x402-tools is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced. ## Links - Remote endpoint: https://flat-rate-llm.kikoribera03.workers.dev/mcp - Website: https://flat-rate-llm.kikoribera03.workers.dev/ - Changelog RSS feed: https://verifymcp.io/servers/dev-workers-kikoribera03-flat-rate-llm-x402-tools/flat-rate-llm.xml - Changelog JSON feed: https://verifymcp.io/servers/dev-workers-kikoribera03-flat-rate-llm-x402-tools/flat-rate-llm.json - HTML version of this page: https://verifymcp.io/servers/dev-workers-kikoribera03-flat-rate-llm-x402-tools/flat-rate-llm