mcp-dom-extract
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_DOM_EXTRACT_CACHE_TTL_MS | No | How long a fetched page is reused before re-fetching (in milliseconds). | 300000 |
| MCP_DOM_EXTRACT_IGNORE_ROBOTS | No | Set to '1' to disable robots.txt compliance checks (e.g. for internal test sites). | 0 |
| MCP_DOM_EXTRACT_CACHE_MAX_BYTES | No | Total cache size limit in bytes. Set to '0' to disable caching. | 52428800 |
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 |
|---|---|
| extract_data_from_urlB | Fetches a web page and extracts precise data from its DOM using CSS selectors. |
| extract_page_textB | Fetches a web page and returns its readable text, optionally scoped to a CSS selector. |
| inspect_page_structureA | Fetches a web page and returns a condensed structural outline of its DOM (tags, ids, classes, short text samples, repeated siblings aggregated). Lets the model pick relevant CSS selectors without loading the full page into context. |
| discover_selectorsA | Fetches a web page and finds CSS selectors for elements whose text matches the given keywords. The model describes what it is looking for with keywords; the server returns candidate selectors with short samples, without the full page entering the context. |
| probe_selectorsA | Fetches a web page and reports, for each CSS selector, how many elements match and a short sample of the first match. Use it to verify or refine candidate selectors cheaply. |
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 5 tools
Most tools have clear, distinct roles: structure inspection, selector discovery, selector probing, and extraction. The only slight overlap is between extract_data_from_url and extract_page_text, since both can retrieve content via CSS selectors, but the former emphasizes precise structured data while the latter focuses on readable text.
All tool names follow a consistent snake_case verb_noun pattern: extract_data, extract_page, inspect_page, discover_selectors, probe_selectors. The 'from_url' suffix on one tool is a minor variation but does not break the overall predictability.
Five tools is well-scoped for a DOM extraction server. Each tool represents a distinct step in the workflow of inspecting, discovering, probing, and extracting, with no redundancy or bloat.
The tool surface covers the full practical workflow for DOM extraction: inspect structure to understand the page, discover candidate selectors, probe selectors to verify them, then extract either precise data or readable text. There are no obvious dead ends or missing critical operations.