Skimless runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 23 Sep 2026.
Reading order for big pull requests: what to read first, what can wait. Offline, no model.
Today is the operative word: we check Skimless every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add skimless -- npx -y skimless
{
"mcpServers": {
"skimless": {
"args": [
"-y",
"skimless"
],
"command": "npx"
}
}
}
[mcp_servers.skimless]
command = "npx"
args = ["-y", "skimless"]
{
"mcpServers": {
"skimless": {
"args": [
"-y",
"skimless"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"skimless": {
"args": [
"-y",
"skimless"
],
"command": "npx"
}
}
}
Lossless skim-then-expand reading of big files, repos, and command output with far fewer tokens
MCP server for Bitbucket API - manage repositories, pull requests, comments, pipelines and more
Local-first MCP that scores your codebase's build readiness. Your code never leaves your machine.
Always-on performance engineering for your own code: proven pull requests, the merge stays yours.
Read-only access to your CodeMouse accounts, repositories, and AI pull-request reviews.
Offline SAP ABAP/RAP tools for AI agents: lint, Cloud readiness, released APIs, knowledge.
Records what an AI agent did in a repo (prompt, model, files) and answers why a line exists.
Model Context Protocol (MCP) server for Cerebras to make coding faster in AI-first IDEs
Answers built from our own checks of this server.