Regen Compute

Regen Compute

Enables AI coding assistants to estimate session energy footprint and retire verified ecocredits on Regen Network, providing on-chain proof of regenerative contribution.

Category
访问服务器

README

Regen Compute

Add Regenerative AI to your AI coding assistant in 30 seconds.

npm version CI License: Apache-2.0 MCP

Every AI session consumes energy. This MCP server lets your AI assistant estimate that footprint and retire verified ecocredits on Regen Network — with immutable on-chain proof.

This is regenerative contribution, not carbon offsetting. No neutrality claims. Just verified funding of ecological regeneration.

Install

claude mcp add -s user regen-compute -- npx regen-compute

That's it. Works immediately — no API keys, no wallet, no configuration needed for read-only tools.

Supported Platforms

<details> <summary><b>Cursor</b></summary>

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):

{
  "mcpServers": {
    "regen-compute": {
      "command": "npx",
      "args": ["regen-compute"]
    }
  }
}

Restart Cursor. Tools appear in Cursor's AI chat.

</details>

<details> <summary><b>Windsurf</b></summary>

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "regen-compute": {
      "command": "npx",
      "args": ["regen-compute"]
    }
  }
}

Open Windsurf Settings > Cascade > MCP Servers to verify the connection.

</details>

<details> <summary><b>VS Code (GitHub Copilot)</b></summary>

Add to .vscode/mcp.json in your workspace:

{
  "servers": {
    "regen-compute": {
      "command": "npx",
      "args": ["regen-compute"]
    }
  }
}

Requires VS Code 1.99+ with GitHub Copilot. Tools are available in Agent mode.

</details>

<details> <summary><b>JetBrains (IntelliJ, WebStorm, PyCharm, etc.)</b></summary>

Go to Settings > Tools > AI Assistant > Model Context Protocol (MCP), click +, and paste:

{
  "mcpServers": {
    "regen-compute": {
      "command": "npx",
      "args": ["regen-compute"]
    }
  }
}

Requires a JetBrains AI Assistant subscription.

</details>

<details> <summary><b>Gemini CLI</b></summary>

Add to ~/.gemini/settings.json:

{
  "mcpServers": {
    "regen-compute": {
      "command": "npx",
      "args": ["regen-compute"]
    }
  }
}

</details>

<details> <summary><b>Continue.dev</b></summary>

Create .continue/mcpServers/regen-compute.yaml in your workspace:

name: Regen Compute
version: 0.0.1
schema: v1
mcpServers:
  - name: regen-compute
    type: stdio
    command: npx
    args:
      - "regen-compute"

Note: MCP tools are only available in Continue's agent mode.

</details>

<details> <summary><b>Sourcegraph Cody</b></summary>

Cody uses the OpenCtx bridge, which requires a local file path (not npx). Install first:

npm install -g regen-compute

Then add to your VS Code settings.json:

{
  "openctx.providers": {
    "https://openctx.org/npm/@openctx/provider-modelcontextprotocol": {
      "nodeCommand": "node",
      "mcp.provider.uri": "file:///ABSOLUTE/PATH/TO/node_modules/regen-compute/dist/index.js"
    }
  }
}

Replace the path with the actual location of the installed package.

</details>

<details> <summary><b>Any MCP-compatible client</b></summary>

Most MCP clients accept this standard config:

{
  "mcpServers": {
    "regen-compute": {
      "command": "npx",
      "args": ["regen-compute"]
    }
  }
}

</details>

ChatGPT and OpenAI API: These platforms require a remote HTTP MCP server (streamable HTTP or SSE transport). Regen Compute currently uses stdio transport. HTTP transport support is on the roadmap.

Quick Start

After installing, ask your AI assistant to run these tools:

  1. estimate_session_footprint — See the energy and CO2 cost of your current session
  2. browse_available_credits — Explore live ecological credits (carbon, biodiversity, marine) on Regen Marketplace
  3. retire_credits — Retire credits to fund regeneration (credit card link by default, or on-chain with a wallet)
  4. get_retirement_certificate — Get a verifiable on-chain proof of your contribution

Or just ask: "Estimate my session's footprint and show me credits I can retire" — the AI handles the rest.

What You Get

Tool What it does
estimate_session_footprint Estimate energy, CO2, and retirement cost for your AI session
browse_available_credits Browse live sell orders on Regen Marketplace (carbon, biodiversity, marine, species)
retire_credits Retire credits on-chain (with wallet) or get a credit card purchase link (without)
get_retirement_certificate Verify any retirement with on-chain proof
get_impact_summary Regen Network aggregate stats — projects, retirements, jurisdictions
browse_ecobridge_tokens List 50+ tokens across 10+ chains for cross-chain payment
retire_via_ecobridge Pay with USDC/ETH/etc. on Ethereum, Base, Polygon, Arbitrum, and more

Three payment modes — pick what works for you

  1. Credit card (default, no setup) — get a Regen Marketplace link
  2. Direct on-chain — set REGEN_WALLET_MNEMONIC, retire in a single tx
  3. Any token, any chain — USDC on Base, ETH on Arbitrum, etc. via ecoBridge

How It Works

Your AI Assistant (Claude Code / Cursor / etc.)
    │
    │ MCP Protocol (stdio)
    ▼
Regen Compute MCP Server
    │
    ├─ Footprint estimation (heuristic, clearly labeled as approximate)
    ├─ Credit browsing (live sell order data from Regen Ledger)
    ├─ Retirement execution (MsgBuyDirect with auto-retire)
    └─ Certificate retrieval (on-chain verification)
    │
    ▼
Regen Network Ledger (immutable, verifiable, non-reversible)

If anything fails during on-chain retirement, it falls back to a marketplace link. Users are never stuck.

Configuration

Works with zero config. Set environment variables for advanced features:

cp .env.example .env
Variable Required What it enables
(none) Footprint estimation, credit browsing, impact stats, marketplace links
REGEN_WALLET_MNEMONIC Optional Direct on-chain retirement (MsgBuyDirect)
ECOBRIDGE_EVM_MNEMONIC Optional Cross-chain payment via ecoBridge (send USDC, ETH, etc.)
ECOBRIDGE_ENABLED=false Optional Disable ecoBridge tools

See .env.example for all options with inline documentation.

Developer Resources

MCP Tools

Tool Description Auth required
estimate_session_footprint Estimate AI session energy use and CO2 No
estimate_monthly_footprint Personalized monthly footprint with location/product multipliers No
browse_available_credits Live sell orders from Regen Marketplace No
retire_credits Retire ecocredits on-chain or via marketplace link Wallet
get_retirement_certificate Retrieve on-chain retirement certificate by nodeId or txHash No
get_impact_summary Regen Network aggregate impact statistics No
check_subscription_status Subscriber status, cumulative impact, referral link API key
get_regen_price REGEN/USD price from CoinGecko with cache status No
verify_payment Verify on-chain payment across 19 chains (16 EVM + BTC + SOL + TRX) No
get_community_goals Community retirement goals, progress, subscriber count No
browse_ecobridge_tokens* Cross-chain tokens and prices via ecoBridge No
retire_via_ecobridge* Retire credits by sending tokens on any EVM chain EVM wallet

* Requires ECOBRIDGE_ENABLED=true

MCP Prompts

Pre-built workflows you can invoke:

Prompt Workflow
offset_my_session Estimate footprint → browse credits → retire
show_regen_impact Pull live network stats and summarize
retire_with_any_token* Browse ecoBridge tokens → pick chain/token → retire

* Requires ECOBRIDGE_ENABLED=true

CLI Subcommands

Command Description
npx regen-compute Start MCP server (stdio transport)
npx regen-compute serve Start the web server (port 3141)
npx regen-compute pool-run [--dry-run] Execute monthly pool retirement batch

REST API Endpoints

All endpoints prefixed with /api/v1/. Protected endpoints require Authorization: Bearer <api_key>.

Endpoint Method Auth Description
/openapi.json GET No OpenAPI 3.1 specification
/payment-info GET No Payment addresses and pricing tiers
/confirm-payment POST No Confirm crypto payment for subscription provisioning
/retire POST Yes Retire ecocredits
/credits GET Yes Browse available credits
/footprint GET Yes Estimate session footprint
/certificates/:id GET Yes Get retirement certificate
/impact GET Yes Network impact statistics
/subscription GET Yes Subscription status and cumulative impact
/community/goals GET Yes Community goals, progress, and subscriber stats
/scheduled-retirements GET Yes Scheduled retirements with status breakdown

Credit Types

Type Description
Carbon (C) Verified carbon removal and avoidance
Biodiversity (BT) Terrasos voluntary biodiversity credits
Marine Biodiversity (MBS) Marine ecosystem stewardship
Umbrella Species (USS) Habitat conservation via umbrella species
Kilo-Sheep-Hour (KSH) Grazing-based land stewardship

Data Sources

Source What it provides
Regen Ledger REST Credit classes, projects, batches, sell orders
Regen Indexer GraphQL Retirement certificates, marketplace orders, stats
Regen Marketplace Credit card purchase flow
ecoBridge API Cross-chain tokens, prices, widget links

Development

Local setup

git clone https://github.com/regen-network/regen-compute.git
cd regen-compute
npm install
cp .env.example .env  # fill in your keys (optional — read-only tools work without)
npm run build

Connect to Claude Code (local build)

Point your MCP config at the local build so changes are reflected immediately:

claude mcp add regen-compute -s user -- node /path/to/regen-compute/dist/index.js

To enable ecoBridge tools locally:

claude mcp add regen-compute -s user \
  --env ECOBRIDGE_ENABLED=true \
  -- node /path/to/regen-compute/dist/index.js

Scripts

Command What it does
npm run dev Watch mode with hot reload (tsx)
npm run build Production build (tsc)
npm run typecheck Type checking only
npm test Run test suite (vitest)
npm run test:watch Run tests in watch mode

Running tests

npm test              # single run
npm run test:watch    # re-run on file changes

Tests mock all external APIs (RPC providers, ecoBridge, Regen Ledger) — no network calls, no wallets needed.

Roadmap

Phase Status
1.0 Read-only MCP — footprint, browsing, marketplace links, certificates Complete
1.5 On-chain retirement — wallet signing, order routing, ecoBridge cross-chain Complete
2.0 Subscription pool — Stripe, monthly batch retirements, fractional attribution In progress
3.0 Smart contract — CosmWasm pool, automated retirement, REGEN burn Planned
4.0 Scale — enterprise API, platform partnerships, credit supply development Planned

See ROADMAP.md for the full 3-track rollout plan, dependency graph, and business context.

Contributing

We welcome contributions! See CONTRIBUTING.md for the issue workflow, label guide, and branch conventions.

Good first issues: gh issue list --label "good first issue"

License

Apache-2.0 — see LICENSE.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选