@true402.dev/mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SERVER_URL | No | true402 API base. Override to point at a self-hosted instance. | https://true402.dev/api |
| WALLET_PRIVATE_KEY | No | A funded Base wallet private key used to sign x402 payments. Needs USDC (gas is sponsored by the facilitator — no ETH required). Without it, paid tools return the 402 requirements instead of paying. |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_modelsA | List every LLM model available through true402's pay-per-call inference, with live per-token pricing (3% over provider cost, min $0.0001/request). Returns each model's id, provider, and input/output token prices across OpenAI, Anthropic, Google, Groq, Mistral and Together — so an agent can pick a model and know the exact cost before paying via x402 (USDC on Base, no account or API key). |
| chatA | Send a chat completion request to an LLM via true402 (PAID x402 service, USDC on Base). Requires a funded wallet (WALLET_PRIVATE_KEY) on the MCP server. |
| seo_auditA | Audit a web page for SEO + GEO (generative-engine optimization). POST |
| web_extractA | Fetch a web page and return clean readable text + light markdown + title/description/links. POST |
| link_previewA | Fetch a URL and return its Open Graph card (title, description, image, site name, favicon, canonical). POST |
| robots_checkA | Fetch a site's robots.txt + llms.txt and report whether the major AI crawlers are allowed/blocked, plus sitemaps. POST |
| headers_checkA | Fetch a URL and analyse its HTTP security headers (HSTS, CSP, X-Frame-Options, …) into present/missing + a 0–100 score. POST |
| token_safetyA | Rug/honeypot safety check for an ERC-20 token on Base (from on-chain reads — no API key): ERC-20 conformance, ownership renounce, mint-capability, WETH/USDC liquidity depth across Uniswap V3 + Aerodrome, and a buy/sell honeypot simulation (a gas-free eth_call that round-trips a tiny WETH→token→WETH trade to detect tokens you can buy but not sell). Returns a 0–100 score + risk flags. POST |
| new_pairsA | Recently-created Base DEX pairs (Uniswap V3 + Aerodrome) from a background log-watcher — fresh token launches for trading agents/snipers. POST |
| liquidity_pullsA | Liquidity-pull / rug alerts on Base — Burn (liquidity-removal) events on recently-launched DEX pools (the new-pairs watcher's set). POST |
| whale_swapsA | Recent large ($-value) DEX Swap events (Uniswap V3 + Aerodrome) on the Base pools the new-pairs watcher tracks — a whale-following / copy-trading signal. POST |
| token_reportA | The flagship composite for a Base ERC-20 — one call instead of five. Runs the full token-safety check (ERC-20 conformance, ownership, mint-capability, WETH/USDC liquidity depth, buy/sell honeypot simulation), enriches it with the live recent liquidity-removal (rug) + whale-swap activity on the token, and returns a single avoid|caution|ok verdict with reasons plus the underlying reports. POST |
| address_safetyA | Structural safety profile for ANY Base address — an EOA or an arbitrary contract — before an agent sends funds to it, approves it, or calls it. Returns contract-vs-EOA, ETH + USDC balance, tx-count (activity), and for contracts: whether it is a recognised ERC-20, ownership state, a mint() selector, and whether it is an EIP-1967 upgradeable proxy (its logic can be swapped after you trust it). Coarse risk band + flags. On-chain reads only — no API key. POST |
| deployer_checkA | Resolves the deployer of a Base token and profiles that wallet's reputation: age (tx-count), balance, contracts shipped, and whether it is a FRESH throwaway spun up for the launch (a common rug setup) — the discriminating caution. Reputation context a structural/honeypot check can't see; raw contract count is reported as context, NOT a rug verdict (legit protocols ship many). POST |
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 14 tools
Each tool targets a distinct operation: address safety, deployer reputation, web checks, token analysis, on-chain monitoring, and LLM inference. There is no functional overlap between any two tools.
Most tools use a descriptive verb_noun pattern (e.g., address_safety, token_report). The exception is 'chat', which breaks the pattern but is still clear and functional.
14 tools is well-scoped for a server covering blockchain safety, web diagnostics, and LLM services. Each tool addresses a specific need without unnecessary redundancy.
The set covers the full lifecycle of its domain: individual checks (address, token, deployer), aggregated reports (token_report), on-chain monitoring (new_pairs, liquidity_pulls, whale_swaps), web analysis (link_preview, seo_audit, headers_check, robots_check), and LLM capabilities (chat, list_models). No obvious gaps.