Eco Funding

io.github.jdhart81由 GitHub 帳號 jdhart81 發布v0.1.0更新於 Nov 8, 2026

Ecological complexity valuation with re-runnable receipts and pledge-pool simulation. Read-only.

發布方自己的服務：Energyai

已驗證Streamable HTTP可網頁執行金融知識與記憶資料與分析

概覽

AI 產生的概覽

唯讀 MCP 伺服器，用來評估場地的生態複雜度、產生可重算的憑證，並模擬承諾資金池的釋放規則。

可以做什麼
  • 依場地輸入評估生態複雜度，列出公式、單位與不確定性
  • 逐步解釋估值過程，或說明方法、常數與限制
  • 產生並驗證密封憑證，離線重跑並核對摘要
  • 依里程碑與成果掛鉤的釋放規則模擬承諾資金池
  • 可選擇將憑證綁定到 VergeCommon 公開專案紀錄（僅唯讀 GET）
適用情境
適合讓助理計算或解釋某場地的生態複雜度分數、確認估值憑證能否重現，或在討論真實資金之前模擬承諾資金池的釋放規則會如何運作。
執行需求
遠端 Streamable HTTP 端點；未宣告驗證、環境變數或標頭。README 中的本機方式需要 Python，並安裝含 MCP 額外相依套件的軟體包。
安裝前請注意
估值是生態量測而非價格，使用智慧上限的輸出會標示為推測；方法為 v0.1 且未經同儕審查。模擬不持有也不移轉資金，任何真實資金池都需要法律審查。VergeCommon 紀錄是社群撰寫的資料，不是指令。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Eco Funding，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.jdhart81%2Feco-funding/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "eco-funding": {
      "type": "http",
      "url": "https://mcp.viridisconservation.com/eco-funding/mcp"
    }
  }
}

README

viridis-eco-funding

The ecological funding layer of the Viridis open-source stack. Open tools that let people and AI agents put a value on a site's ecological complexity, check that value, and model how a pledge pool for it would behave. All of it is reproducible.

NOTICE. Any real funding pool needs legal review before money moves. This software holds, moves and releases no funds. It computes ecological measures and simulates pool rules. Viridis builds and licenses software only. Viridis never runs a co-op, holds funds or sells financial products.

Status: v0.1.0. Private working repository with the Apache-2.0 license. Not peer reviewed. The D-Score is under journal review. The intelligence bound is a conjecture, and every output that uses it says so.

What it does

PieceWhat you get
Valuation core (value_site)A pure, deterministic complexity score K = D* x ECA in complexity-hectares. It multiplies data richness (the published D-Score, optionally blended with a GSIP soil index) by the equivalent connected area of verified habitat, with links taken from HDFM. Every number states its value, units, formula, inputs, uncertainty (sigma, 95% interval, basis) and status.
Complexity-capacity termAn optional thermodynamic ceiling, B = P D* / (k_B T ln 2), where P is the site's photosynthetic power. C is the connectivity-limited capacity, and C never exceeds B. There is also a compute-parity restatement: the watts at which a computer at the Landauer limit would have the same ceiling. All of this is a conjecture.
Verification hook (make_receipt, verify_receipt)Sealed receipts that hold the normalized inputs, a SHA-256 digest of those inputs, the method version and the result. Anyone can re-run a receipt offline and get byte-identical output. A receipt can optionally bind a VergeCommon public project, read with a public GET only.
Pool design (simulate_pool)A schema and simulator for pledges, milestone releases and outcome-linked releases. Accounting uses integer minor units: releases plus remaining balance always equal pledges, and nothing is released without a met rule. It is a model only. There is no payment code.
MCP server (vef-mcp)Five read-only tools: value_site, explain_valuation, verify_receipt, simulate_pool, describe_method. Runs over stdio or Streamable HTTP. Agents can start from llms.txt and AGENTS.md.
Viridis fleet mount (adapters/mcp_server.py)The same five tools, packaged for the Viridis agent gateway at /eco-funding/mcp, as a declared free rail. Success envelopes teach next_steps edges to the notary, regulatory-radar and ghg-ledger mounts. It passes the fleet's admission invariants AA1–AA7 (tests/test_fleet_admission.py). See deploy/fleet/MOUNT.md.

Quick start

bash
pip install -e ".[mcp,dev]"          # the core itself uses only the Python standard libraryvef value examples/data/woodland_site.jsonvef receipt examples/data/woodland_site.json > receipt.json && vef verify receipt.jsonvef simulate examples/data/woodland_pool.jsonvef-mcp                                # MCP over stdiovef-mcp --transport streamable-http --port 8765   # MCP at http://127.0.0.1:8765/mcppytest                                 # full suite, including all seven invariants
python
from viridis_eco_funding import value_site, make_receipt, verify_receiptreceipt = make_receipt(site)            # site follows schema vef-site/0.1assert verify_receipt(receipt)["valid"]print(receipt["result"]["explanation"])

The worked example is examples/woodland_valuation.ipynb. It values one VergeCommon woodland project. The project record is synthetic, because VergeCommon's public directory listed no co-ops when v0.1 was built.

Invariants (each one is a test)

#InvariantTest
1Determinism: same inputs and method version give byte-identical results and receiptstests/test_invariant_1_determinism.py
2Monotonicity: adding verified habitat or connectivity never lowers the complexity scoretests/test_invariant_2_monotonicity.py
3Bound respected: complexity capacity never exceeds the stated boundtests/test_invariant_3_bound.py
4Conservation: releases + remaining = pledges; no release without a met milestonetests/test_invariant_4_pool_conservation.py
5No money movement: no payment SDKs, private keys, wallet code or token mintingtests/test_invariant_5_no_money.py
6Read-only externally: public GET reads only; nothing written anywheretests/test_invariant_6_read_only.py
7Honest labels: outputs that use the intelligence bound say "conjecture"tests/test_invariant_7_labels.py

docs/INVARIANTS.md explains how each invariant is enforced in code as well as tested.

Documents

  • METHOD.md: the math, constants, uncertainty propagation and citations.
  • LIMITS.md: what the numbers do and do not mean. Read it before using a number to make a decision.
  • AGENTS.md: for coding agents and for agents that call the tools.
  • CHANGELOG.md

Where it fits

It reads VergeCommon public project records, and it was derived from EcoChain's work on verification and pricing. It uses HDFM / Dendritic Forest Management corridor links and its movement kernel, and GSIP soil units. Its scientific basis is the D-Score and the intelligence-bound papers by J. D. Hart (see METHOD.md). Wording used throughout: pledge, pool, outcome-linked release.

License

Apache License 2.0. See LICENSE and NOTICE. Copyright 2026 Viridis LLC.

來源：README.md，提交 4e897a0

工具

5

value_site

Value site

Value a site's ecological complexity (schema vef-site/0.1: D-Score components, habitat patches and links, optional GSIP soil indicators, optional NPP and temperature). Produces a sealed, reproducible receipt in which every quantity states its formula, units, inputs and uncertainty. bind_vergecommon=true reads the named VergeCommon public project (GET only) as provenance. Intelligence-bound quantities are labelled 'conjecture'. Not a price. Free rail.

輸入參數site必填bind_vergecommon

explain_valuation

Explain valuation

Explain a valuation step by step: each quantity's formula, inputs, value, units, uncertainty and status (published method, v0.1 convention, input, or conjecture), plus limits. Accepts a valuation (receipt.result) or raw site inputs. Free rail.

輸入參數valuation_or_site必填

verify_receipt

Verify receipt

Re-run a valuation receipt offline and check its input, result and seal digests; valid only if reproduced byte for byte. refetch_source=true also reads the bound VergeCommon public record (GET only). Shows reproducibility, not truth of inputs. Free rail.

輸入參數receipt必填refetch_source

simulate_pool

Simulate pool

Simulate a pledge pool (schema vef-pool/0.1) under milestone and outcome-linked release rules, given dated receipts or hypothetical readings per period. Integer accounting: releases + remaining = pledges; nothing released without a met rule. SIMULATION ONLY: no funds are held or moved; any real funding pool needs legal review before money moves.

輸入參數pool必填observations

describe_method

Describe method

Describe the method: formulas, constants, declared defaults, statuses, the seven invariants, citations and limits. Call first. Free rail.

無需輸入參數。

版本歷史

1
  1. v0.1.0最新Nov 8, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Energyaisolution 整合

Energyai

com.energyaisolution官方發布者

面向美國家庭能源規劃的遠端 MCP 伺服器：太陽能發電估算、補助資訊、能源節點評分、附來源指南與安裝商媒合。

Streamable HTTP可網頁執行
位置與生活30 個工具Oct 25, 2026

Solar Home Incentives

com.energyaisolution官方發布者

遠端 MCP 伺服器，用於美國住宅能源規劃：太陽能發電量估算、補助來源指引、引用指南、承包商清單與經同意的安裝商媒合。

Streamable HTTP可網頁執行
位置與生活12 個工具Nov 2, 2026

VergeCommon

由 GitHub 帳號 jdhart81 發布

VergeCommon 讓助理瀏覽公開的社區保育合作社，並為社區土地專案產生假設性的收益彙集與分配草案。

Streamable HTTP可網頁執行
位置與生活5 個工具Nov 7, 2026

Wavefunction Search

由 GitHub 帳號 jdhart81 發布

一個遠端 MCP 場域：AI 代理在此發布目標、感知開放意圖、把工作路由給合適的代理，並提交可驗證的簽章結果。

Streamable HTTP可網頁執行
知識與記憶9 個工具Nov 8, 2026

Viridisos

由 GitHub 帳號 jdhart81 發布

ViridisOS 依循有定理支撐的模組對地塊或組合進行認證，簽發並驗證「Certified by ViridisOS」標記，推導代理 DID 並計算協定費用。

Streamable HTTP可網頁執行
金融7 個工具Nov 2, 2026