readability-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| extractA | Extract the main article from already-rendered (post-JavaScript) HTML and return clean Markdown plus metadata and diagnostics. The server fetches nothing: |
| html_to_markdownA | Convert an arbitrary HTML fragment to Markdown WITHOUT Readability article extraction (e.g. a snippet already isolated via chrome-devtools). Same Turndown + DOMPurify path as |
| outlineA | Return the document outline (h1-h6 headings with stable anchor ids) of already-rendered (post-JavaScript) HTML as a cheap pre-check before full extraction. No Readability scoring, no Turndown, no sanitization — a pure heading walk. The server fetches nothing: |
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 3 tools
Each tool has a distinct purpose: 'extract' performs full article extraction with Readability, 'html_to_markdown' converts arbitrary HTML without extraction, and 'outline' provides a heading-based preview. No overlap exists, making it easy for agents to select the right tool.
The names are all lowercase with underscores and convey the action clearly, but the patterns differ: 'extract' is a verb, 'html_to_markdown' describes the transformation, and 'outline' is a noun. Minor inconsistency, but overall predictable.
With 3 tools, the server covers the essential operations for HTML-to-Markdown conversion: article extraction, arbitrary snippet conversion, and outline preview. The count feels well-scoped and reasonable for the domain.
The tool surface covers the primary use cases. A minor gap is the lack of a tool to fetch raw HTML from a URL, but the server explicitly declares it does not fetch, so that's by design. Including diagnostics in 'extract' partially compensates.