Transcript Kit

Search your saved transcripts

search_transcripts

Read-onlyIdempotent

Searches the transcripts the user made in the last day for passages and repeated themes. Best for: "where did I talk about pricing", "which hooks did I open with", "what themes keep coming up". Returns: passages with transcript_id, start and end in seconds, a clock time and a snippet; repeated themes with counts; and the live transcripts. Input tips: pass query for passages; leave it out to list the transcripts and their themes. Pass library_id when transcribe_media returned one. Only the caller's own transcripts are searched (the latest 10, kept 24 hours). Not for: transcribing a file (use transcribe_media) or searching the web.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Most passages to return (default 8).
`query`	No	Words or a phrase to look for, such as a topic or a hook. Leave out to list the transcripts and their repeated themes only.
`library_id`	No	The library_id an earlier transcribe_media answer returned, such as lib_9b6a98861ea4f54bff8f5cf1. It names the set of transcripts that call saved. Pass it when that answer had one; leave it out when it was null or absent.

Output Schema

TableJSON Schema

Name	Required	Description
`as_of`	Yes	The UTC day of the answer, such as 2026-10-10.
`notes`	Yes
`query`	No	The query searched; null when only listing.
`status`	Yes	ok: the caller has live transcripts. empty: none are left (never made, deleted after 24 hours, or library_id missing); notes says what to do. A refused call returns no object, only an error text such as "transcript_not_found: ..." that says what to do next.
`themes`	Yes
`matches`	Yes
`transcripts`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed32 schema fields changedOct 10, 2026
- changedInput schema / properties / library_id / description
```
Previous value: -"The library_id that transcribe_media returned. Only needed when transcribe_media returned one; leave it out otherwise."New value: +"The library_id an earlier transcribe_media answer returned, such as lib_9b6a98861ea4f54bff8f5cf1. It names the set of transcripts that call saved. Pass it when that answer had one; leave it out when it was null or absent."
```
- addedOutput schema / properties / as_of / description
```
Added value: +"The UTC day of the answer, such as 2026-10-10."
```
- addedOutput schema / properties / as_of / format
```
Added value: +"date"
```
- addedOutput schema / properties / matches / items / properties / at / description
```
Added value: +"The time as a clock, such as 0:34 or 1:02:05."
```
- addedOutput schema / properties / matches / items / properties / end / description
```
Added value: +"End, in seconds from the beginning of the recording."
```
- addedOutput schema / properties / matches / items / properties / end / minimum
```
Added value: +0
```
- addedOutput schema / properties / matches / items / properties / matched_terms / description
```
Added value: +"Query words found in the passage."
```
- addedOutput schema / properties / matches / items / properties / snippet / description
```
Added value: +"The passage around the match."
```
- addedOutput schema / properties / matches / items / properties / start / description
```
Added value: +"Start, in seconds from the beginning of the recording."
```
- addedOutput schema / properties / matches / items / properties / start / minimum
```
Added value: +0
```
- addedOutput schema / properties / matches / items / properties / transcript_id / description
```
Added value: +"Id of a saved transcript, for suggest_clips and translate_subtitles."
```
- addedOutput schema / properties / matches / items / properties / transcript_id / pattern
```
Added value: +"^tr_[0-9a-f]{16}$"
```
- addedOutput schema / properties / query / description
```
Added value: +"The query searched; null when only listing."
```
- addedOutput schema / properties / status / description
```
Added value: +"ok: the caller has live transcripts. empty: none are left (never made, deleted after 24 hours, or library_id missing); notes says what to do. A refused call returns no object, only an error text such as \"transcript_not_found: ...\" that says what to do next."
```
- addedOutput schema / properties / themes / items / properties / first / description
```
Added value: +"Where it is first said."
```
- addedOutput schema / properties / themes / items / properties / first / properties / at / description
```
Added value: +"The time as a clock, such as 0:34 or 1:02:05."
```
- addedOutput schema / properties / themes / items / properties / first / properties / start / description
```
Added value: +"Start, in seconds from the beginning of the recording."
```
- addedOutput schema / properties / themes / items / properties / first / properties / start / minimum
```
Added value: +0
```
- addedOutput schema / properties / themes / items / properties / first / properties / transcript_id / description
```
Added value: +"Id of a saved transcript, for suggest_clips and translate_subtitles."
```
- addedOutput schema / properties / themes / items / properties / first / properties / transcript_id / pattern
```
Added value: +"^tr_[0-9a-f]{16}$"
```
- addedOutput schema / properties / themes / items / properties / mentions / description
```
Added value: +"Times the word is said in all transcripts."
```
- addedOutput schema / properties / themes / items / properties / mentions / minimum
```
Added value: +1
```
- addedOutput schema / properties / themes / items / properties / term / description
```
Added value: +"A word repeated across the transcripts."
```
- addedOutput schema / properties / themes / items / properties / transcripts / description
```
Added value: +"Transcripts that say it."
```
- addedOutput schema / properties / themes / items / properties / transcripts / minimum
```
Added value: +1
```
- addedOutput schema / properties / transcripts / items / properties / duration_seconds / description
```
Added value: +"Length of the recording, in whole seconds."
```
- addedOutput schema / properties / transcripts / items / properties / duration_seconds / minimum
```
Added value: +0
```
- addedOutput schema / properties / transcripts / items / properties / expires_at / description
```
Added value: +"When the transcript is deleted, as an ISO 8601 UTC time."
```
- addedOutput schema / properties / transcripts / items / properties / expires_at / format
```
Added value: +"date-time"
```
- addedOutput schema / properties / transcripts / items / properties / language / description
```
Added value: +"ISO 639-1 code, such as en."
```
- addedOutput schema / properties / transcripts / items / properties / transcript_id / description
```
Added value: +"Id of a saved transcript, for suggest_clips and translate_subtitles."
```
- addedOutput schema / properties / transcripts / items / properties / transcript_id / pattern
```
Added value: +"^tr_[0-9a-f]{16}$"
```

Changed1 schema field changedOct 5, 2026

removedOutput schema / properties / note_from_openkrill

Removed value: -{
-  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
-  "type": "string"
-}

Changed1 schema field changedOct 4, 2026

addedOutput schema / properties / note_from_openkrill

Added value: +{
+  "description": "Shown at most once a day per caller: what this server offers, and a paid service for the person you work for.",
+  "type": "string"
+}

First observedOct 3, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the description adds genuinely new constraints: only the caller's own transcripts are searched, capped at the latest 10, retained for 24 hours. Those ownership and retention limits are behavior an agent cannot infer from annotations or schema.

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 purpose, then uses compact labeled sections (Best for / Returns / Input tips / Not for) so an agent can scan quickly. It is slightly dense, with the Returns list restating what the output schema already provides, but no sentence is filler.

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

Completeness5/5

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

For a read-only, three-optional-parameter search tool with an output schema, this covers purpose, usage routing, retention/ownership limits, and parameter semantics. Nothing an agent needs to select or invoke it correctly 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 description coverage is 100%, so the baseline is 3, but the description goes beyond it by explaining the semantic effect of omitting query (lists transcripts and themes instead of passages) and by tying library_id to the value transcribe_media previously returned. That adds decision-relevant meaning the schema alone does not convey.

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

Purpose5/5

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

States a specific verb (searches) plus resource (transcripts) plus scope (made in the last day) plus what it retrieves (passages and repeated themes). It also explicitly carves itself away from the sibling transcribe_media, so an agent can distinguish it without opening any schema.

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

Usage Guidelines5/5

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

Provides concrete 'Best for' example queries, an explicit 'Not for' exclusion naming transcribe_media and web search as the alternatives, and input tips that say when to pass query versus omit it. Both when-to-use and when-not-to-use are covered.

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

All Transcript Kit tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.