Mediawork

io.mediawork由 mediawork.io 发布官方发布者v0.1.1更新于 Oct 28, 2026

Search Mediawork's directory of post-production and distribution vendors, plus FAQ and plans.

已验证Streamable HTTP可网页运行网页搜索与抓取商业与电商

概览

AI 生成的概览

只读访问 Mediawork 公开的后期制作与发行供应商目录,以及常见问题、博客和订阅方案。

可以做什么
  • 搜索 Mediawork 公开发布的全部内容,并按 id 读取单条记录的完整内容
  • 按服务类别和地点浏览供应商目录,再查看某供应商的完整资料,包括服务、创作人员、场地与设备
  • 查询服务分类体系以及有供应商入驻的城市、州和国家
  • 检索已发布的常见问题,可带查询词也可不带
  • 按最新优先列出博客文章,并以 markdown 读取单篇全文
  • 获取订阅方案、指定货币的价格以及功能对比表
适用场景
适合按地点或服务调研后期制作、发行或创意供应商,或在规划项目时查阅 Mediawork 公开的常见问题、博客内容和价格信息。
运行要求
远程 Streamable HTTP 端点;客户端无需身份验证、注册、API 密钥或环境变量。需要能访问 Mediawork 端点的网络。
安装前请注意
设计上为只读:仅提供公开发布的目录、常见问题、博客和方案数据,没有写入路径。查询与检索内容会发送到 Mediawork 的服务器,返回记录带有 mediawork.io 的规范链接。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mediawork,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/io.mediawork%2Fmediawork/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": {
    "mediawork": {
      "type": "http",
      "url": "https://mcp.mediawork.io/mcp"
    }
  }
}

README

Mediawork MCP server

Read-only Model Context Protocol access to everything Mediawork publishes publicly: the directory of post-production and distribution vendors, the FAQ, the blog, and subscription plans.

Connector URL: https://mcp.mediawork.io/mcp — Streamable HTTP, no authentication, no sign-up.

Listed in the official MCP Registry as io.mediawork/mediawork.

Connect it

Claude Code:

sh
claude mcp add --transport http mediawork https://mcp.mediawork.io/mcp

Anything that takes a JSON config:

json
{    "mcpServers": {        "mediawork": {            "type": "http",            "url": "https://mcp.mediawork.io/mcp"        }    }}

Tools

ToolWhat it does
searchOne query across the directory, FAQ and blog, returning {id, title, url}
fetchRead one record in full, by an id from search
search_facilitiesThe vendor directory, filtered by service and place
get_facilityA vendor's full public profile
list_servicesThe service taxonomy, for resolving a filter
list_placesCities, states and countries with vendors in them
search_faqPublished FAQ entries
list_blog_posts / get_blog_postThe blog
get_plansSubscription plans and pricing

search + fetch are the generic pair some clients require; the dedicated tools give richer, filterable results where a client can use them.

Directory questions usually chain: list_services or list_places to resolve a filter, then search_facilities, then get_facility. Every result carries its canonical www.mediawork.io URL so an agent can cite the source.

Read-only, structurally

The deployment holds exactly one environment variable, APP_API_URL, and every byte it serves comes from https://app.mediawork.io/api/www/* — the same public contract the marketing site consumes. There are no database credentials and no write path, so "read-only" is a property of the deployment's shape rather than a promise in a comment.

Contributing

Setup, the test commands and the house conventions are in CONTRIBUTING.md.

Licence

MIT © Screen Arts Limited.

来源:README.md,提交 cf0b938

工具

10

list_services

List service categories

The service categories vendors on Mediawork offer, such as Editorial, Sound Post or Visual Effects. Each has a uuid — pass it as `service` to search_facilities to filter the directory to vendors offering that service. Call this first when a question is about a kind of work.

输入参数locale

list_places

List directory places

Cities, states and countries that have at least one vendor listed, with a count of how many. Use a place `slug` as the `place` argument to search_facilities.

输入参数locale

search_facilities

Search the vendor directory

Search publicly listed post-production facilities, distribution vendors and creative companies. Filter by free text, by place slug (from list_places) and by service uuid (from list_services). To find vendors somewhere, prefer `place`; a `query` naming a place is treated as one anyway, and the response reports it as `resolvedPlace`. Results are paginated; when `hasMore` is true, call again with the returned `nextOffset`.

输入参数placequerylocaleoffsetservice

get_facility

Get a vendor profile

The full public profile for one vendor: services offered, creatives on the team and what each of them does, production types, rooms and spaces, equipment by make and model, and addresses. Takes the `companySlug` and `facilitySlug` pair returned by search_facilities.

输入参数localecompanySlug必填facilitySlug必填

search_faq

Search the Mediawork FAQ

Mediawork's published FAQ, grouped by category. With a query, returns matching questions and their answers; without one, returns every question so you can pick which to search for.

输入参数querylocale

list_blog_posts

List blog posts

Published posts from the Mediawork blog, newest first. Use get_blog_post with a returned `slug` to read one in full.

输入参数locale

get_blog_post

Read a blog post

The full body of one published blog post, as markdown.

输入参数slug必填locale

get_plans

Get subscription plans and pricing

Mediawork's subscription plans: what each includes, and its prices, plus `comparison`, a feature-by-feature table of every plan. Prices are published in several currencies — pass `currency` to return just one.

输入参数localecurrency

fetch

Fetch a Mediawork record

Retrieve the full contents of one record by the `id` returned from `search`.

输入参数id必填

版本历史

1
  1. v0.1.1最新Sep 16, 2026

评分

已满足适用检查项的 100%

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
  • 文档15 分
  • 许可证10 分