Skip to main content
Glama

mcp-knowledge

by io.github.getgapup

transcribe_chapterize_media

Read-onlyIdempotent

Transcription and chapterization of long-form media (YouTube, podcasts, direct audio/video) for content marketing teams, podcast publishers, edu tech, journalists and accessibility/compliance.

Pipeline: • YouTube → timedtext captions (keyless) + oEmbed metadata + native timecode chapters from description • Podcast RSS → episode description + duration + timecodes if embedded in show notes • Direct media → partial (requires Whisper API via OPENAI_API_KEY + force_whisper:true) • Chapters: native YouTube timecodes preferred; heuristic TF-IDF segmentation as fallback • Summary: extractive TF-IDF top-sentences (no LLM required) • Language detection: character-set heuristic (CJK→zh, kana→ja, hangul→ko, accents→fr/de/es)

Output formats: json (full structured object) | text (plain transcript) | srt | vtt

SLA: ≤15s budget total. Cache: 24h TTL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesYouTube URL, podcast RSS feed URL, or direct MP3/MP4 URL. Example: "https://www.youtube.com/watch?v=jNQXAC9IVRw"
langNoISO 639-1 language hint (e.g. "en", "fr", "de"). Default "auto".
asyncNoIf true, returns a job_id immediately (<200ms) instead of waiting for the result. Poll the result with job_result(job_id). Use for slow tools to avoid client timeouts.
chapters_maxNoMaximum number of chapters. Default 8.
output_formatNoTranscript format. Default "json".
include_summaryNoInclude extractive summary. Default true.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYes
statusYes
signalsYes
sourcesYes
summaryNo
chaptersYes
segmentsYes
key_topicsYes
transcriptYes
source_typeYes
lang_detectedYes
quality_scoreYes
duration_secondsYes

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds substantial behavioral context: pipeline steps (TF-IDF fallback, language detection), caching (24h TTL), SLA (≤15s), async option, and output formats. No contradictions with annotations.

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?

The description is well-structured with bullet points and sections, front-loading the main purpose and pipeline details. It is somewhat lengthy but each clause provides necessary information without redundancy. Minor trimming could improve conciseness.

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?

Given the tool's complexity (multiple source types, fallbacks, output formats, async support) and the presence of an output schema, the description covers all critical behavioral aspects: source handling, SLA, cache, language detection, and fallback logic. It is fully adequate for agent decision-making.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all 6 parameters with descriptions. The description adds context about the async parameter and polling via job_result, but does not provide additional semantic nuance beyond what the schema offers. Baseline 3 is appropriate.

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?

The description clearly states it performs transcription and chapterization of long-form media, listing specific sources (YouTube, podcasts, direct audio/video) and target use cases (content marketing, podcast publishers, etc.). It is a specific verb+resource that effectively distinguishes itself from sibling tools, none of which are directly comparable.

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?

The description provides detailed usage guidance for each media source (YouTube keyless captions, Podcast RSS, direct media requiring Whisper API) and mentions fallback mechanisms. It lacks explicit when-not-to-use or alternative tool references, but the context is clear enough for an agent to decide based on source and requirements.

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

All mcp-knowledge toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.8/5.0
Disambiguation2/5

Many tools have overlapping purposes, especially in competitive intelligence, ESG, and risk assessment. For example, there are multiple tools for competitor analysis (competitive_deep_dive, competitor_intel, competitor_moves, etc.) with unclear boundaries. Agents would struggle to select the correct tool without deep understanding of subtle differences.

Naming Consistency2/5

Tool names are a mix of English and French, and follow no consistent pattern. Some use snake_case (e.g., abm_architect, action_plan_esg), while others are verb-focused (e.g., content_catalog, fx_rate). The lack of a uniform naming convention makes it hard for agents to predict tool names.

Tool Count1/5

With 271 tools, the server is excessively large. Even for a broad knowledge domain, this number of tools makes discovery and selection inefficient. Typical coherent servers have 3-15 tools; this has an order of magnitude more, indicating poor scoping.

Completeness3/5

The tool set covers many domains (compliance, finance, marketing, HR, etc.), but the coverage is uneven due to redundancy. Key areas have multiple overlapping tools, while some sub-domains may still have gaps. Overall, the surface is broad but not well-curated.

Resources