Wistia MCP Server

List Captions

list_all_captions

Read-onlyIdempotent

Retrieve caption tracks and transcripts from Wistia accounts by media ID, language, or metadata-only filters, with pagination for bulk transcript access.

Instructions

Lists captions belonging to the account. Results can be narrowed to a specific media with media_id, or to several media and languages at once with media_ids[] and languages[]. Each caption includes its text, so combining these filters with pagination fetches transcripts for many media in a few requests. Pass include=metadata to omit transcript text when only track and language information is needed.

Requires api token with one of the following permissions

Read all folder and media data

Tokens with the "Act with a team member's permissions" permission (all:delegate_to_contact_permissions scope) can also be used. Requests made with such a token are authorized using the permissions of the contact assigned to the token. Read-only account operation.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`page`	No	The page number to retrieve. This cannot be combined with `cursor`, pagination.
`cursor`	No	If `cursor[enabled]` is set to 1 then cursor pagination is enabled and the first set of records are fetched up to the `per_page`. Cursor pagination will also be turned on if `cursor[before]` or `cursor[after]` are set. Records returned will have a `cursor` property set which can be used to fetch more records in the same `sort_by` ordering. The cursor value of the last record can be used to fetch records after the current result set and the cursor of the first record can be used to fetch records before the result set. NOTE: a cursor value is only valid if the `sort_by` value hasn't changed from the last fetch. For example, you cannot fetch using `sort_by` id and then pass that cursor value to a `sort_by` name.
`account`	No	Named private Wistia account; selects credentials, not a remote account ID.
`include`	No	Set to `metadata` to omit caption text and return only track metadata. Omitting this parameter preserves the existing response, including SRT text.
`sort_by`	No	Ordering. When using cursor pagination (see cursor param), only `id` is supported.	id
`media_id`	No	Find captions for a particular media by providing the media hashed ID
`per_page`	No	The number of medias per page. Use this for both offset pagination and cursor pagination.
`all_pages`	No	Read bounded page/per_page pages; each request consumes API quota. Not a snapshot or guaranteed complete backup.
`languages`	No	Find captions in any of these languages, using the codes returned in each caption's `language` field (for example `eng` or `spa`). When combined with `media_ids[]`, captions must match both.
`max_items`	No	Maximum returned records with all_pages=true, default 1000. At most 100 requests; output includes continuation state.
`media_ids`	No	Find captions belonging to any of these media hashed IDs. IDs that don't match a media the token can access are ignored rather than returning an error.
`sort_direction`	No	Ordering Sort Direction (0 = desc, 1 = asc; default is 1)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.0.0Oct 2, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the description's main added value is the auth context: the required token permission and the delegate_to_contact_permissions scope behavior. It does not disclose pagination or result-count behavior, but the schema does, so this is a solid addition.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core behavior and filters in the first sentences and defers the auth boilerplate to a clear trailing block. Every substantive sentence earns its place, though the verbatim permission block is lengthy relative to the functional content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter read-only list tool with full schema coverage and no output schema, the description covers scope, filtering strategy, transcript-vs-metadata tradeoff, and auth requirements. It could be a 5 if it also addressed pagination interaction or listed-value behavior, but nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns an extra point by explaining how media_id, media_ids[] and languages[] interact (filters combine, non-matching IDs are ignored) and what include=metadata does to the payload. That is genuine semantic value beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Lists captions belonging to the account') and immediately scopes it with the available filters, so the agent knows exactly what it returns. It does not differentiate itself from the sibling list_captions, which is the one real ambiguity, keeping it just below a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operational guidance: combine media_ids[] and languages[] with pagination to fetch transcripts in bulk, and pass include=metadata when only track/language info is needed. It stops short of saying when to prefer this tool over list_captions or get_captions, so there is no explicit alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server