zRev AI

ai.zrev由 zrev.ai 发布官方发布者v1.0.0更新于 Oct 24, 2026

Grade any llms.txt, cold-read a homepage, run a B2B GTM ROI model, get a GTM diligence checklist.

已验证Streamable HTTP可网页运行商业与电商

概览

AI 生成的概览

让助手查询 zRev 的服务与成效资料、估算 GTM ROI、评分 llms.txt、解读公司首页并留下联系方式。

可以做什么
提供 zRev 的公司简介、典型成效数据、60 天合作时间表以及 GTM 尽职调查清单(47 个问题、十个维度),均为只读静态内容。另有 estimate_roi 依据单个公司的数字推算年度影响,grade_llms_txt 用七项检查为网站的 llms.txt 打分,cold_read 仅根据公开首页可见文字概述该公司。book_call 只返回预约链接,leave_contact 会写入一条潜在客户记录。
适用场景
适用于用户询问 zRev 是什么、提供哪些服务、合作流程或预期成效,或想用自家数字估算 GTM ROI、检查网站的 llms.txt、快速判断某公司首页,或获取 GTM 尽职调查清单时。
运行要求
远程 HTTP 端点,无需安装软件包;未声明认证、环境变量或请求头。grade_llms_txt 与 cold_read 需要联网抓取指定域名的公开页面。
安装前请注意
leave_contact 会把电子邮箱及可选的姓名、公司、备注写入 zRev 侧的潜在客户记录,仅应在当事人同意时使用。estimate_roi 的结果为模型推算,成效数字为典型值并附来源说明。grade_llms_txt 与 cold_read 会向第三方网站发起请求。

安装

在 SourceWeft 中

  1. 打开 控制台中的 zRev AI,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/ai.zrev%2Fzrev/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "zrev-ai": {
      "type": "http",
      "url": "https://go.zrev.ai/mcp"
    }
  }
}

工具

9

about_zrev

About zRev

Returns a plain-text profile of zRev AI: what the firm does, the companies it is the best fit for, who it is not for, its six service lines with a link to each, and contact details. Use this first when a user asks who zRev is, what it offers, or whether it suits their company. Read-only, static content, no arguments, no authentication, no rate limit.

无需输入参数。

get_benchmarks

Typical engagement results

Returns zRev's typical engagement results as plain text: 2x pipeline velocity, 20% lower customer acquisition cost, 10 hours back per rep per week, 60% of GTM busywork automated, results that start inside 30 days and mature by 60. The response always ends with the provenance caveat: these are typical results benchmarked against comparable AI-powered GTM implementations and they vary by stack, data quality and adoption, so present them as typical, not guaranteed. Use when a user asks what results to expect. For an estimate on a specific company's numbers use estimate_roi instead. Read-only, static content, no arguments, no authentication, no rate limit.

无需输入参数。

get_engagement_timeline

The 60-day engagement, phase by phase

Returns the phases of a standard 60-day zRev engagement as plain text: what happens in each phase, what is delivered, and when first results appear. Use when a user asks how an engagement works, how long it takes, or what they would receive and when. Read-only, static content, no arguments, no authentication, no rate limit.

无需输入参数。

estimate_roi

Estimate the ROI of AI across a GTM motion

Runs zRev's ROI model on one company's numbers and returns, as plain text, the projected annual impact in USD split into pipeline lift, customer acquisition cost savings and the value of hours returned to the team, followed by the model's assumptions and a link to the interactive calculator preset to the same inputs. Use when a user wants a number for their own company; all six inputs are required, so ask for any that are missing rather than guessing. The output is an estimate from a fixed model, not a forecast or a quote. Pure calculation: nothing is stored, no external calls, no authentication, no rate limit.

输入参数arr必填cac必填deal_size必填team_size必填monthly_leads必填close_rate_pct必填

grade_llms_txt

Grade a site's llms.txt

Fetches https://<domain>/llms.txt (the file that tells AI systems what a site contains) and grades it with seven deterministic checks. Returns a 0 to 100 score and the pass or miss result of each check as plain text. If the site has no llms.txt the response says so and links to zRev's free generator. Use when a user asks whether a site is readable by AI assistants or wants their llms.txt reviewed. Makes one outbound HTTP request to the public domain you pass; stores nothing about it. No authentication. Shares a fair-use limit per IP address with cold_read, and returns a plain-text notice when that limit is reached.

输入参数domain必填

cold_read

Cold-read a homepage

Fetches a company's public homepage and returns, in two or three sentences, what the company appears to do and who it serves, based only on the visible text of that page and with no outside knowledge. Anything missing from the answer is missing from the homepage, which is the point: it shows what an AI assistant would tell a buyer about that company. Use when a user asks how their site, or a competitor's, reads to an AI. The summary is model-generated and can be wrong where the page is vague. Makes one outbound HTTP request to the public domain you pass; stores nothing about it. No authentication. Shares a fair-use limit per IP address with grade_llms_txt, and returns a plain-text notice when that limit is reached.

输入参数domain必填

gtm_diligence_checklist

GTM due diligence checklist

Returns zRev's go-to-market due diligence checklist for investors and acquirers: 47 questions across ten dimensions, each with the data-room artifact that answers it and the red flag to watch for. Call with no arguments to get the list of ten dimensions; call with a dimension number from 1 to 10, or a keyword such as churn, pipeline or marketing, to get that dimension's questions in full. Use when a user is assessing a company's revenue engine before an investment or acquisition. Read-only reference content, no authentication, no rate limit.

输入参数dimension

book_call

How to book an intro call

Returns the link and instructions for booking a free 30-minute intro call with zRev's founder, plus what the call covers. It does not book anything: it only returns the scheduling link for the human to open themselves. Use when a user says they want to talk to zRev. If they would rather be contacted, use leave_contact instead. Read-only, static content, no arguments, no authentication, no rate limit.

无需输入参数。

leave_contact

Ask zRev to get in touch

Records an email address, with optional name, company and note, so that zRev's founder can reach out, and returns a plain-text confirmation. This is the only tool here that writes data: it creates one lead record on zRev's side and triggers no email to the address given. Use only when the human you are assisting has explicitly asked to be contacted by zRev; never call it speculatively or with an address the user has not given you for this purpose. Submitting the same email again updates the existing record rather than creating a duplicate. No authentication. Rate-limited per IP address.

输入参数namenoteemail必填company

版本历史

1
  1. v1.0.0最新Sep 17, 2026

评分

已满足适用检查项的 72%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分

    请在注册中心条目中发布图标。

  • 文档15 分

    请声明包含 README 的 GitHub 仓库,或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证不适用

    托管服务按其提供方的条款使用,因此这里不要求许可证。此检查项不计入百分比。