# Pyfile Toolkit Pyfile Llm MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.pyfile-toolkit%2Fpyfile-llm
Registry id: `mcp-registry/io.github.pyfile-toolkit/pyfile-llm`
Status: live (checked 2026-10-27T06:15:58.646Z)

## Measurements (30 days)

- Uptime: 98.12%
- Checks: 3743
- Outages (90 days): 58

## Install

```json
{
  "mcpServers": {
    "pyfile-toolkit-pyfile-llm-mcp-server": {
      "type": "http",
      "url": "https://pyfile-agent.taile3ff35.ts.net:8443/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http pyfile-toolkit-pyfile-llm-mcp-server https://pyfile-agent.taile3ff35.ts.net:8443/mcp
```

## Tools (13)

- `base_gas`: Current Base L2 gas price in wei and gwei.
- `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, a
- `chat`: Ask an LLM a question. Returns a text completion.
- `crypto_price`: Current USD prices for one or more coins (CoinGecko ids, comma-separated).
- `dns_lookup`: Resolve a DNS record (A, AAAA, MX, TXT, NS).
- `enrich`: One-call domain/company enrichment: DNS A records + certificate transparency names + GLEIF LEI + OFAC SDN + web snapshot, with an aggregate risk_summary. Requir
- `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 
- `fair_pick`: Provably-fair selection of one winner from a list of candidates. For bounties with a single prize.
- `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.
- `ofac_sanctions_search`: Search the US Treasury OFAC SDN sanctions list by entity name (KYB/AML screening).
- `web_read`: Fetch any public web page and return its main readable content as clean Markdown (nav/ads stripped) for RAG and agent pipelines.
- `wikipedia_summary`: Short summary of a Wikipedia article by title.

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.