
Pyfile LLM & Data API
Pay-per-call LLM chat plus data tools: DNS, crypto, Base gas, Wikipedia.
What it can do
What data it sees
Do you need an account
No: the server works without sign-in
Pay-per-call LLM chat plus data tools: DNS, crypto, Base gas, Wikipedia. x402 USDC or Lightning.
How to connect
How to connect Pyfile LLM & Data API to Claude
The server address to paste into Claude settings:
https://pyfile-agent.taile3ff35.ts.net:8443/mcp
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Pyfile LLM & Data API to ChatGPT
The server address to paste into ChatGPT settings:
https://pyfile-agent.taile3ff35.ts.net:8443/mcp
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Pyfile LLM & Data API to Cursor
The server address to paste into Cursor settings:
https://pyfile-agent.taile3ff35.ts.net:8443/mcp
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (13)
Raw names from tools/list. Only developers need these.
| chat | Ask an LLM a question. Returns a text completion. |
| dns_lookup | Resolve a DNS record (A, AAAA, MX, TXT, NS). |
| crypto_price | Current USD prices for one or more coins (CoinGecko ids, comma-separated). |
| base_gas | Current Base L2 gas price in wei and gwei. |
| wikipedia_summary | Short summary of a Wikipedia article by title. |
| brief | Composite analyst brief: gathers live market facts (crypto prices, DeFi yields, Base block height) and returns an LLM-written brief with headline, key points, and a take. Requires a Bearer key. |
| web_read | Fetch any public web page and return its main readable content as clean Markdown (nav/ads stripped) for RAG and agent pipelines. |
| ofac_sanctions_search | Search the US Treasury OFAC SDN sanctions list by entity name (KYB/AML screening). |
| fda_lookup | US FDA open data: drug adverse events, drug/food/device recalls, drug labels. |
| kyb_screening | Composite counterparty due-diligence: OFAC SDN sanctions screening + GLEIF LEI + SEC EDGAR in one call. Requires a Bearer key. |
| enrich | One-call domain/company enrichment: DNS A records + certificate transparency names + GLEIF LEI + OFAC SDN + web snapshot, with an aggregate risk_summary. Requires a Bearer key. |
| fair_draw | Provably-fair random integer from a committed seed (commit-reveal). Use for verifiable winner selection, raffles and allocations. Reveal the seed afterwards so anyone can reproduce the result. |
| fair_pick | Provably-fair selection of one winner from a list of candidates. For bounties with a single prize. |