Skip to main content
Glama
OmniExtract MCP

OmniExtract MCP

omni_extract_url

Extract long-form articles, videos, transcripts, and code from X, TikTok, YouTube, GitHub, or anti-bot pages into clean Markdown. Turns any shared URL into readable text for AI agents.

Instructions

Universal, cookie-free content & transcript extractor for AI Agents. Extracts full long-form X (Twitter) Articles/Tweets, watermark-free Douyin/TikTok videos & photo galleries, YouTube/Bilibili video subtitles/transcripts with timestamps, GitHub READMEs/code, and anti-bot web pages into clean Markdown.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "omni_extract_url"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesTarget URL or share text containing a URL (X/Twitter, Douyin, TikTok, YouTube, Bilibili, GitHub, or any web page).
api_keyNoOptional OmniExtract API key (omni_live_...) for paid credit packs.
output_formatNoReturn formatted Markdown ('markdown') or full structured JSON metadata ('json'). Default: 'markdown'.markdown
include_transcriptNoWhether to extract full video subtitles/transcripts for video URLs (default: true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose meaningful traits: cookie-free operation (no auth/cookies required), watermark stripping, timestamped transcripts, and anti-bot page handling. It says nothing about rate limits, credit costs, failure modes, or whether extraction is synchronous, which are the operational facts an agent still lacks.

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?

Two sentences, front-loaded with the core capability and then the platform list. Minor filler in 'Universal' and 'for AI Agents', but no sentence is wasted.

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

Completeness3/5

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

There is no output schema, so the description must convey return shape; 'clean Markdown' does that partially, and the schema covers the JSON alternative. For a 4-parameter, no-annotation tool spanning many platforms, it is missing cost/credit behavior, error handling, and size or length limits.

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 all four parameters (url, api_key, output_format, include_transcript) are already documented in structured data. The description adds no parameter-level meaning beyond the schema — it never mentions the json/markdown switch, transcript toggle, or the paid credit-pack key.

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 ('Extracts') and enumerates the exact resources handled: X Articles/Tweets, Douyin/TikTok video and photo galleries, YouTube/Bilibili transcripts, GitHub READMEs/code, and anti-bot web pages, all into Markdown. It never names or contrasts with the sibling omni_extract_batch, so an agent cannot tell from this text alone whether single-URL vs batch is the dividing line.

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

Usage Guidelines3/5

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

Usage is only implied: a single 'url' parameter suggests one-URL-at-a-time, which is the natural contrast with omni_extract_batch, but the description never says so. There are no exclusions, no prerequisites, and no guidance on when to pick omni_check_quota or the batch tool instead.

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