Connect Mediawork and your agent gets 10 tools, among them fetch, get_blog_post, get_facility. It answers at https://mcp.mediawork.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Search Mediawork's directory of post-production and distribution vendors, plus FAQ and plans.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
fetch | Retrieve the full contents of one record by the `id` returned from `search`. Inputs: id |
get_blog_post | The full body of one published blog post, as markdown. Inputs: slug, locale |
get_facility | The full public profile for one vendor: services offered, creatives on the team and what each of them does, production types, rooms and spaces, and addresses. Takes the `companySlug` and `facilitySlug` pair returned by search_facilities. Inputs: companySlug, facilitySlug, locale |
get_plans | Mediawork's subscription plans: what each includes, and its prices. Prices are published in several currencies — pass `currency` to return just one. Inputs: currency, locale |
list_blog_posts | Published posts from the Mediawork blog, newest first. Use get_blog_post with a returned `slug` to read one in full. Inputs: locale |
list_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. Inputs: locale |
list_services | 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 Inputs: locale |
search | Search everything Mediawork publishes — vendor directory listings, FAQ entries and blog posts — and return matching records as {id, title, url}. Pass an `id` to `fetch` to read one in full. If your client supports them, the dedicated tools Inputs: query |
search_facilities | 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 `qu Inputs: query, place, service, offset, locale |
search_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. Inputs: query, locale |
Every block below points at https://mcp.mediawork.io/mcp. Pick your client and copy.
claude mcp add --transport http mediawork https://mcp.mediawork.io/mcp
{
"mcpServers": {
"mediawork": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.mediawork.io/mcp"]
}
}
}{
"mcpServers": {
"mediawork": {
"url": "https://mcp.mediawork.io/mcp"
}
}
}{
"servers": {
"mediawork": {
"type": "http",
"url": "https://mcp.mediawork.io/mcp"
}
}
}{
"context_servers": {
"mediawork": {
"url": "https://mcp.mediawork.io/mcp"
}
}
}{
"mcpServers": {
"mediawork": {
"serverUrl": "https://mcp.mediawork.io/mcp"
}
}
}{
"mcpServers": {
"mediawork": {
"url": "https://mcp.mediawork.io/mcp"
}
}
}name: Mediawork
version: 0.0.1
schema: v1
mcpServers:
- name: Mediawork
type: streamable-http
url: https://mcp.mediawork.io/mcp{
"mcpServers": {
"mediawork": {
"httpUrl": "https://mcp.mediawork.io/mcp"
}
}
}{
"mcpServers": {
"mediawork": {
"type": "http",
"url": "https://mcp.mediawork.io/mcp"
}
}
}{
"mcpServers": {
"mediawork": {
"url": "https://mcp.mediawork.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.mediawork.io%2Fmcp&type=streamable_http&id=mediawork&name=Mediawork
It answered our last check on 24 October 2026 in 178 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by mediawork.io and served from mcp.mediawork.io, the vendor's own domain: https://mcp.mediawork.io/mcp.
10, as returned by the server's own tools/list on 22 September 2026: fetch, get_blog_post, get_facility, get_plans, list_blog_posts, list_places, list_services, search, and 2 more.
It answered our last check on 24 October 2026 in 178 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.mediawork.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.mediawork. Endpoint host: mcp.mediawork.io. ARD identifier: urn:air:io.mediawork:mcp:mediawork.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.