ARYSPHERE x402 chain reads and token verdicts MCP Server

LLM chat completion: send messages and max_tokens, get the reply. OpenAI-style chat completion from DeepSeek-V4-Flash-0731. Returns: an OpenAI-style chat completion from the model the service is named for (DeepSeek-V4-Flash-0731, Qwen3-32B or Llama-3.1-8B-Instruct): POST {messages: [{role, content}], max_tokens <= 1024}; returns the assistant message, the model, and its token usage. Messages up to 16,000 characters in total. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/base_deepseek_chat. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"].

Token Quick Check: Base contract facts -- name, supply, owner, code. Not financial advice. Returns: a token verdict preview on one token contract: the contract facts the full verdict reads -- code size, name, symbol, decimals, total supply, owner(), proxy slots -- read from the chain. No grade, no model, no pool price, no holders, no safety or legitimacy call. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/base_erc20_balance_preview. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"].

Token Quick Check: Base contract facts -- name, supply, owner, code. Not financial advice. Returns: a token verdict preview on one token contract: the contract facts the full verdict reads -- code size, name, symbol, decimals, total supply, owner(), proxy slots -- read from the chain. No grade, no model, no pool price, no holders, no safety or legitimacy call. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/base_erc20_supply_facts_preview. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"].

Token Quick Check: Base contract facts -- name, supply, owner, code. Not financial advice. Returns: a token verdict preview on one token contract: the contract facts the full verdict reads -- code size, name, symbol, decimals, total supply, owner(), proxy slots -- read from the chain. No grade, no model, no pool price, no holders, no safety or legitimacy call. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/base_erc20_token_facts_preview. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"].

LLM chat completion: send messages and max_tokens, get the reply. An OpenAI-style chat completion from Llama-3.1-8B-Instruct. Returns: an OpenAI-style chat completion from the model the service is named for (DeepSeek-V4-Flash-0731, Qwen3-32B or Llama-3.1-8B-Instruct): POST {messages: [{role, content}], max_tokens <= 1024}; returns the assistant message, the model, and its token usage. Messages up to 16,000 characters in total. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/base_llama3_1_8b_chat. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"].

LLM chat completion: send messages and max_tokens, get the reply. OpenAI-style chat completion from Qwen3-32B. Returns: an OpenAI-style chat completion from the model the service is named for (DeepSeek-V4-Flash-0731, Qwen3-32B or Llama-3.1-8B-Instruct): POST {messages: [{role, content}], max_tokens <= 1024}; returns the assistant message, the model, and its token usage. Messages up to 16,000 characters in total. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/base_qwen3_32b_chat. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"].

Token Quick Check: Base contract facts -- name, supply, owner, code. Not financial advice. A token verdict preview of one Base token contract. Returns: a token verdict preview on one token contract: the contract facts the full verdict reads -- code size, name, symbol, decimals, total supply, owner(), proxy slots -- read from the chain. No grade, no model, no pool price, no holders, no safety or legitimacy call. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/base_token_facts_preview. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"].

Token Quick Check: Base contract facts -- name, supply, owner, code. Not financial advice. Returns: a token verdict preview on one token contract: the contract facts the full verdict reads -- code size, name, symbol, decimals, total supply, owner(), proxy slots -- read from the chain. No grade, no model, no pool price, no holders, no safety or legitimacy call. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/base_token_verdict_preview. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"].

Token Risk Report: AI verdict on a Base token contract -- grade, red flags, on-chain facts. Not financial advice. Returns: an AI-written token verdict on one token contract: grade (BASED/MID/COOKED/RADIOACTIVE, a stated rule over the contract's own state), a one-liner and a roast, and the facts read: code size, name, symbol, decimals, supply, owner(), proxy slots; plus the deepest Uniswap V3 pool's USD price and depth. No holders, no safety or legitimacy call. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/base_token_verdict_v3. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"]. Measured output: {"cached": false, "chain": "base", "disclaimer": "Entertainment, not financial advice. Reads the contract and its deepest Uniswap V3 pool (spot price, quote-side depth): not holders, locks or future price.", "grade": "COOKED", "method": "verdict", "ok": true, "result": {"disclaimer": "Entertainment, not financial advice. Reads the contract and its deepest Uniswap V3 pool (spot price, quote-side depth): not holders, locks or future price.", "facts": {"decimals": 6, "erc20_shaped": true, "is_contract": true, "name": "USD Coin", "owner": "0x3abd6f64a422225e61e435bae41db12096106df7", "owner_renounced": false, "proxy_slot": "zeppelinos", "symbol": "USDC", "upgradeable_proxy": true}, "grade": "COOKED", "grade_rule": "RADIOACTIVE: not a contract, or not ERC-20 shaped (no decimals/totalSupply). COOKED: a proxy implementation slot is set (EIP-1967, its beacon, or ZeppelinOS) AND owner() names a live owner. MID: either one. BASED: neither found.", "market": {"deepest_pool": {"fee": 3000, "pool": "0x6c561b446416e1a00e8e93e221854d6ea4171372", "price_usd": 1.00209, "quote": "WETH", "quote_reserve_usd": 87721037.3, "token_reserve": 58770808.350535}, "depth_rule": "pool_depth from the deepest pool's quote-side reserve in USD: <$1k none_or_dust, <$100k thin, <$5M moderate, else deep. A description of on-chain state, not advice.", "dex": "uniswap_v3", "eth_usd": 2432.8015, "eth_usd_source": "chainlink ETH/USD 0x71041dddad3595f9ced3dccfbe3d1f4b0a16bb70", "fee_tiers": [500, 3000, 10000], "pool_depth": "deep", "pools_found": 3, "price_usd": 1.00209, "quote_assets": ["WETH", "USDC"], "quote_reserve_usd": 87721037.3, "rpc_calls": 2}, "one_liner": "USDC is COOKED", "roast": "USDC: COOKED. Proxy (zeppelinos slot set); a live owner holds the keys.", "token": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913", "written_by": "template"}, "service": "x402_bazaar_token_verdict_v2.base_token_verdict_v3"}

LLM chat completion: send messages and max_tokens, get the reply. OpenAI-style chat completion from DeepSeek-V4-Flash-0731. Returns: an OpenAI-style chat completion from the model the service is named for (DeepSeek-V4-Flash-0731, Qwen3-32B or Llama-3.1-8B-Instruct): POST {messages: [{role, content}], max_tokens <= 1024}; returns the assistant message, the model, and its token usage. Messages up to 16,000 characters in total. GET https://api.arysphere.com/v1/ventures/x402_bazaar_token_verdict_v2/deepseek_v4_flash_chat. Same payment terms as that HTTP route. Call once with no payment. The result is the payment terms. Retry the same call with the signed payment at _meta["x402/payment"].