slimdown-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SKRYP_API_KEY | No | Set this to read pages that need a real browser (JavaScript apps, bot walls, or country-specific pages) through Skryp instead. A free account includes 1,000 credits a month. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| read_pageA | Read a web page as lean Markdown: its main content only, in as few tokens as possible. url: the page (http or https). focus: return only the sections about this, e.g. "pricing" or "installation". Saves most of the page's tokens. links: false keeps link text but drops the addresses. country: two-letter code to read the page as seen from that country (needs SKRYP_API_KEY). Links to the same site are shortened to their path; resolve them against the Source line. |
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 1 tool
With only one tool, there is no possibility of confusion between tools. Its purpose is clearly distinct and unambiguous.
The single tool name 'read_page' follows a predictable verb_noun pattern. With no other tools, there is no inconsistency.
A single tool is on the thin side for a server; while the tool itself is feature-rich with multiple parameters, the surface could potentially offer additional related operations (e.g., batch reading, link extraction) to be more complete.
For its stated purpose of reading a web page as lean Markdown, the tool covers key parameters (url, focus, links, country) and returns the core output. No obvious gaps exist within this narrow domain.