io.github.telegraphprotocol/telegraph

io.github.telegraphprotocol/telegraph

Decentralized AI inference (weather, deepfake detection, LLMs) with x402 USDC micropayments.

View repository →

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.

{
  "mcpServers": {
    "telegraph": {
      "command": "npx",
      "args": [
        "-y",
        "telegraph-protocol-mcp@1.0.0"
      ],
      "env": {
        "TELEGRAPH_NODE_URL": "<your TELEGRAPH_NODE_URL>",
        "TELEGRAPH_ENGINE_URL": "<your TELEGRAPH_ENGINE_URL>",
        "TELEGRAPH_DAEMON_URL": "<your TELEGRAPH_DAEMON_URL>",
        "TELEGRAPH_EVM_PRIVATE_KEY": "<your TELEGRAPH_EVM_PRIVATE_KEY>",
        "TELEGRAPH_SOLANA_PRIVATE_KEY": "<your TELEGRAPH_SOLANA_PRIVATE_KEY>"
      }
    }
  }
}
Environment variables
  • TELEGRAPH_NODE_URLrequiredTelegraph node public API URL (e.g. http://13.237.89.59:7044)
  • TELEGRAPH_ENGINE_URLrequiredTelegraph Engine inference server URL (e.g. http://13.237.89.59:8080)
  • TELEGRAPH_DAEMON_URLrequiredTelegraph Daemon signal API URL (e.g. http://13.237.89.59:8081)
  • TELEGRAPH_EVM_PRIVATE_KEYsecretEVM private key (0x-prefixed hex) of a USDC-funded burner wallet used to sign x402 payments. At least one of TELEGRAPH_EVM_PRIVATE_KEY or TELEGRAPH_SOLANA_PRIVATE_KEY is required.
  • TELEGRAPH_SOLANA_PRIVATE_KEYsecretSolana private key (base58) for SVM x402 payments. Optional alternative to TELEGRAPH_EVM_PRIVATE_KEY.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
AI & ML
Version
1.0.0
Registry
active
Published
6/30/2026

More AI & ML servers

Browse all AI & ML →

io.github.telly6/searchpin

telly6

Self-hosted web search for AI agents — zero API keys, embedding rerank, multi engine parallel search

AI & MLAdded 4 days ago

contextkeeper

TheRealDataBoss

Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.

AI & MLAdded 8 months ago

vaultit

TheRealDataBoss

Zero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.

AI & MLAdded 7 months ago

io.github.Timluogit/clawriver

Timluogit

Agent 知识共享市场 — 让 AI Agent 搜索/购买/上传经验记忆。34 个 Tools，支持记忆搜索、购买、上传、评价、团队协作。

AI & MLAdded 7 months ago

io.github.timmx7/styx-mcp-server

timmx7

MCP server for Styx — intelligent AI routing across OpenAI, Anthropic, Google, and Mistral.

AI & MLAdded 8 months ago

io.github.tjacquesson/llmtest-mcp

tjacquesson

Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.

AI & MLAdded 5 months ago

Add the badge to your site

Show visitors that io.github.telegraphprotocol/telegraph is listed here — it’s also the link we check for a free listing.

io.github.telegraphprotocol/telegraph — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/io-github-telegraphprotocol-telegraph?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="io.github.telegraphprotocol/telegraph — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![io.github.telegraphprotocol/telegraph — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/io-github-telegraphprotocol-telegraph?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.