Fulcru

io.github.gsmmediaro由 GitHub 帳號 gsmmediaro 發布v2.0.0更新於 Oct 25, 2026

Find where ChatGPT names your competitor, write the page that closes the gap, measure it.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取資料與分析

概覽

AI 產生的概覽

Fulcru 是託管式 MCP 伺服器,用來找出 AI 搜尋中提及競爭對手而非你品牌的提問,起草補足差距的頁面,並追蹤 AI 能見度變化。

可以做什麼
找出 AI 助理提及競爭對手而非你品牌的提問,依差距由大到小排序,並起草一篇補足該差距的 Markdown 頁面。將草稿頁面連同網址標記為已發布,並記錄用於衡量的基準快照。報告已發布頁面帶來的 AI 能見度變化,以及概覽、競爭對手、來源與提及報告。
適用情境
當你希望助理執行 AI 搜尋能見度閉環時使用:排查哪些提問提及競爭對手、產出補足差距的內容,並衡量發布前後的變化。適合需要持續追蹤各 AI 助理中品牌提及的團隊,而非一次性檢查。
執行需求
透過 streamable HTTP 存取的遠端端點,使用 Authorization 標頭中的 bearer 權杖驗證,權杖來自服務商的 Integrations 頁面;也支援搭配動態用戶端註冊的 OAuth 2.1。持續衡量閉環需要 Fulcru 帳號,並需能存取託管服務的網路。
安裝前請注意
Authorization 中的 bearer 權杖是帳號憑證,請勿放入共用設定或日誌。發布操作會將頁面標記為上線並記錄基準快照,會改變帳號狀態。差距、頁面與能見度資料會傳送到託管的 Fulcru 服務,內容與網站網址會離開本機。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Fulcru,將其新增到工作區。
  2. 連接 Authorization token 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 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.gsmmediaro%2Ffulcru/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": {
    "fulcru": {
      "type": "http",
      "url": "https://api.fulcru.app/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

fulcru

Get named by AI search engines.

When someone asks ChatGPT "what's the best CRM for a small team", the answer names two or three products. Those get the customer. Everyone else is invisible.

fulcru finds the questions where an AI assistant names a competitor instead of you, writes the page that closes the gap, and measures what publishing it did. It runs as a CLI, an MCP server, and an agent skill, so a human or an agent can run the whole loop.

This repo is the open, self-hostable agent surface. The measurement engine is the hosted Fulcru service; everything here is a thin client that talks to it with your token.

We run it on ourselves and publish the result, whichever way it goes. Today it scores us 0 out of 34 prompts: we sell AI visibility and we score zero on our own product, with the full run and the source data.

bash
npm install -g fulcruexport FULCRU_TOKEN=pk_...        # Settings -> Integrations at fulcru.app

Or run it in Docker, with nothing installed on the host:

bash
docker build -t fulcru .docker run --rm -e FULCRU_TOKEN=pk_... fulcru gaps

No secrets are baked into the image; the token is passed at run time. Verified on node:20-alpine, 2026-07-27.

The loop

bash
$ fulcru gaps  0%  k57jc...  best AI visibility tracker for a SaaS startup -> AI names Profound, Peec AI  0%  k57bw...  how do I know if ChatGPT recommends my brand -> AI names Otterly AI 33%  k57xz...  tools to track brand mentions in Perplexity -> AI names Semrush
Write the top one:  fulcru write k57jc...
$ fulcru write k57jc... > page.md     # the drafted article, grounded in what AI cites$ fulcru publish k57jc... https://mysite.com/blog/ai-visibility-trackersPublished. Baseline: AI names you in 0% of 9 measured answers.
$ fulcru delta    0% ->  44%  +44pts  Best AI Visibility Trackers, Compared

That last line is the whole point.

Commands

CommandWhat it does
fulcru gaps [n]Questions where AI names a competitor and not you, worst first
fulcru write <promptId>Writes the page that closes one gap; Markdown to stdout
fulcru publish <pageId> <url>Marks it live and snapshots the baseline to measure from
fulcru deltaWhat your published pages actually did
fulcru report [section]overview, competitors, sources, mentions, prompts

Add --json to any command for the raw payload.

Built for agents

Output is terse lines, not JSON blobs, because the caller is usually an LLM and its context is the scarce resource. fulcru gaps costs an agent about 50 tokens; the same data as raw API JSON costs about 800. fulcru write sends the Markdown to stdout and everything else to stderr, so fulcru write <id> > page.md gives a clean file.

MCP

Two ways to wire the five Fulcru tools into an agent.

Remote (hosted). Point any MCP client at the hosted endpoint with your token:

json
{  "mcpServers": {    "fulcru": {      "url": "https://little-orca-977.convex.site/mcp",      "headers": { "Authorization": "Bearer pk_..." }    }  }}

Local (stdio). For hosts that prefer a subprocess, this package ships a stdio MCP server that proxies to the hosted endpoint:

json
{  "mcpServers": {    "fulcru": {      "command": "npx",      "args": ["-y", "-p", "fulcru", "fulcru-mcp"],      "env": { "FULCRU_TOKEN": "pk_..." }    }  }}

The -p is not decoration. This package ships two commands, and without it npx runs the one named after the package, which is the CLI: the host gets a usage screen instead of an MCP server.

Tools: fulcru_gaps, fulcru_write_page, fulcru_publish_page, fulcru_delta, fulcru_visibility.

Both speak protocol revision 2026-07-28 and the older handshake-based revisions, and pick per request from what the client sends. A client on the new revision gets server/discover, per-request _meta, and a cacheable tool list; one still sending initialize is served exactly as before. Nothing needs configuring either way.

Skill

The skills/fulcru skill runs the whole playbook using nothing but web access — audit a domain, find the gaps, write the page, re-measure — with no account and no token. Install it into an agent that supports skills:

bash
# Claude / OpenClawnpx skills add gsmmediaro/fulcru
# Hermeshermes skills install gsmmediaro/fulcru

Hermes scans third-party skills before installing and prints the verdict, so you can see what you are agreeing to run. If you would rather track this repo as a source and pick up updates, tap it instead:

bash
hermes skills tap add gsmmediaro/fulcruhermes skills install fulcru

The CLI and MCP above are what you use when you want it measured continuously across every engine, with the before/after delta tracked for you.

Configuration

Env varRequiredDefaultPurpose
FULCRU_TOKENfor the CLI + local MCP—Your account token (Settings -> Integrations)
FULCRU_ENDPOINTnohttps://little-orca-977.convex.site/mcpPoint at a self-hosted or custom-domain endpoint

No secrets are baked into this repo. The token is read from the environment only.

Self-hosting

The skill needs nothing. The CLI and MCP need a Fulcru account for the continuous, measured loop; point FULCRU_ENDPOINT at your own instance if you run one.

A Docker image is provided:

bash
docker build -t fulcru .docker run --rm -e FULCRU_TOKEN=pk_... fulcru gaps

Contributing

Issues and PRs welcome. The tool logic lives in the hosted service; this repo is the CLI, the stdio MCP proxy, and the skill. If AI names a competitor instead of you, open an issue with the question — that is exactly the gap this is built to close.

If this is useful, a ⭐ genuinely helps.

License

AGPL-3.0-or-later. See LICENSE.

來源:README.md,提交 56903ae

工具

0
SourceWeft 尚未讀取此伺服器的工具。

版本歷史

1
  1. v2.0.0最新Sep 16, 2026

評分

已滿足適用檢查項的 85%

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

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分