# Worder

> Find and price AI voices from real, verified voice actors in ten languages. Read-only, no sign-up.

- name: com.worder/worder
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 96/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.worder%2Fworder
- tools: https://api.protogrid.dev/v1/servers/com.worder%2Fworder/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "worder": {
      "type": "http",
      "url": "https://www.worder.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-18d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (strong)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 822 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 1 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 822 tokens to load them all
- tool set hash: 8aa79f1edac3776854b938c102fcbfec
- tools last changed: 2026-10-21T02:18:30.224Z
- badge: [![protogrid quality](https://protogrid.dev/badge/com.worder/worder.svg)](https://protogrid.dev/servers/com.worder/worder)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-21 `search_voices` changed (description)
  - before: Find licensed AI voices on Worder by language, name, accent, actor or sample label. Returns the voice's per-second price in USD, its samples (as page links), the use cases its actor excludes, and links to listen and generate. Use list_languages to see what languages have voices.
  - after: Find licensed AI voices on Worder by language plus free text: name, accent, delivery tag (warm, calm, energetic...), actor or sample label. Each word is matched on its own and the voices matching the most words come first. Returns the voice's per-second price in USD, its samples (as page links), the use cases its actor excludes, and links to listen and generate. Use list_languages to see what languages have voices.

Full history: https://api.protogrid.dev/v1/servers/com.worder%2Fworder/changes

## Remotes

- https://www.worder.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `about_worder`: What Worder is, how voice actors are paid, what happens to voice data, which languages are supported and how pricing works.
- `estimate_cost`: Estimate how many seconds of audio a script will produce with a given voice and what it will cost in USD at that voice's per-second price, the way Worder bills it.
- `get_voice`: Full public details of one voice by id: actor, language, price per second, samples, direction tags, excluded use cases, and the links to listen and generate.
- `how_to_order`: The steps to go from a chosen voice to a downloaded audio file, including pricing, previews, credits and the refund guarantee.
- `list_languages`: The languages Worder voices speak, with the number of public voices per language and per country variant, and a link to each language's catalog page.
- `search_voices`: Find licensed AI voices on Worder by language plus free text: name, accent, delivery tag (warm, calm, energetic...), actor or sample label. Each word is matched on its own and the voices matching the most words come first. Returns the voice's per-second price in USD, its samples (as page links), the use cases its actor excludes, and links to listen and generate. Use list_languages to see what languages have voices.