content-core
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PROMPT_PATH | No | Path to your custom prompt templates directory | |
| GOOGLE_API_KEY | No | Your Google API key | |
| OPENAI_API_KEY | No | Your OpenAI API key for AI-powered processing and transcription | |
| CCORE_URL_ENGINE | No | Force URL engine selection (auto, simple, firecrawl, jina) | auto |
| CCORE_DOCUMENT_ENGINE | No | Force document engine selection (auto, simple, docling) | auto |
| CCORE_AUDIO_CONCURRENCY | No | Number of concurrent audio transcriptions (1-10, default: 3) | 3 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extract_contentA | 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. |
| summarize_contentB | Summarize content using LLM with optional context. Requires OPENAI_API_KEY (or another LLM provider key) to be configured. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools target clearly distinct actions: extract_content pulls raw content from a source, while summarize_content condenses it via an LLM. An agent can easily tell which to call based on whether it needs raw text or a summary.
Both names follow the same verb_noun snake_case pattern (extract_content, summarize_content), with no deviations in convention or style.
Two tools is on the thin side for even a focused server, though each earns its place in a natural extract-then-summarize pipeline. A couple of supporting operations (e.g. format conversion or output saving) would round out the surface.
The extract and summarize pair covers the core content-processing lifecycle, including multiple input sources (URLs, PDFs, YouTube). Minor gaps exist around batch processing, output formatting, or chunking, but agents can work around these.