Parkour MCP
A content exploration toolkit that helps LLMs surface high signal, unsummarized web content. It makes extensive use of clean APIs and Markdown conversion to enable targeted content extraction and knowledge synthesis. A rolling 2Q page cache keeps recently visited pages in memory so that follow-up requests are served quickly.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
Checks and signals
Each line is separate evidence, not a trust score.
- Popularity 5 GitHub stars
What you can do with it
- Surface high signal, unsummarized web content
- Enable targeted content extraction and knowledge synthesis
- Perform section extraction and BM25 search
- Resolve footnote and inline-citation on MediaWiki sites
Source and maintenance
- Last repository push
- Latest release
- v2.4.0
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/blightbow/parkour-mcp/releases/download/v2.4.0/parkour-mcp.mcpb
{
"transport": "stdio",
"fileSha256": "6eb381f6de2e3b635991a77b37160b03ec49fd231e82763703250b841274458b",
"identifier": "https://github.com/blightbow/parkour-mcp/releases/download/v2.4.0/parkour-mcp.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Let your agent find its tools
Find servers like Parkour MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.