content-core

Overview Schema Source Related Servers Discussions Admin

extract_content

Extract text from web pages, PDFs, documents, and YouTube videos. Optionally enable formula, image, or OCR extraction with engine selection.

Instructions

Extract content from a URL or file. Does not require an API key for most sources (web pages, PDFs, documents, YouTube transcripts). API key is only needed for audio/video transcription.

Args: url: URL to extract content from (web page, YouTube video, PDF link, etc.) file_path: Local file path to extract content from engine: Optional extraction engine override, routed by input type. With url: auto, simple, firecrawl, jina, crawl4ai. With file_path: auto, simple, docling — docling requires pip install "content-core[docling]" and fails with a configuration error when the extra is missing, in which case use auto or simple. Any other value is rejected with an error naming the accepted ones. formulas: Enable formula extraction via Docling (requires engine=docling) pictures: Enable image description + chart data extraction via Docling (requires engine=docling) no_ocr: Disable OCR in Docling (requires engine=docling)

Returns: Extracted text content

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	No
`engine`	No
`no_ocr`	No
`formulas`	No
`pictures`	No
`file_path`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv2.0.4Jul 13, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / engine

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedInput schema / properties / formulas

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

addedInput schema / properties / no_ocr

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

addedInput schema / properties / pictures

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / properties

Added value: +{
+  "result": {
+    "type": "string"
+  }
+}

addedOutput schema / required
```
Added value: +[
+  "result"
+]
```
addedOutput schema / x-fastmcp-wrap-result
```
Added value: +true
```

Changed2 schema fields changedv1.0.0Jan 3, 2026
- removedInput schema / properties / file_path / title
```
Removed value: -"File Path"
```
- removedInput schema / properties / url / title
```
Removed value: -"Url"
```
First observedAug 15, 2025

TDQS

B3.3/5.0

Behavior3/5

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

With no annotations, the description carries the burden. It discloses API key requirements, engine behavior, and the docling extra failure mode, but it does not explicitly state that the operation is read-only or describe the return format beyond 'Extracted text content'. The engine error message is useful but other behavioral aspects remain implicit.

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-organized with an Args/Returns structure and front-loads the purpose. It is detailed but each line earns its place, covering engine specifics and error conditions without excessive verbosity.

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?

For a tool with six optional parameters and no required ones, the description omits guidance on whether at least one of url or file_path must be provided. The return description is minimal, and error handling for missing inputs is not covered. While engine behavior is well documented, these input-requirement gaps reduce completeness.

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 0%, so the description must compensate. It explains url, file_path, engine with valid values and routing, and clarifies that formulas, pictures, and no_ocr require engine=docling. This adds substantial meaning beyond the bare schema.

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?

The description clearly states the tool extracts content from a URL or file and lists common source types. It does not explicitly contrast with the sibling summarize_content, but the verb 'extract' and the scope are unambiguous.

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

Usage Guidelines2/5

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

No guidance is given on when to use this tool versus summarize_content. While it explains engine selection and API key conditions, it never addresses tool-level choice, which is a gap given the sibling exists.

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

Deploy Server