ctxlint runs on your own machine — the client starts it, so there is no endpoint to ping. 16 091 installs a week from npm. Last commit 16 Sep 2026.
Lint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase
We read the source, 19 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const out = execFileSync(cmd, ['--version'], {
const body = fs.readFileSync(path.join(REPO_ROOT, meta.spec), 'utf-8');
fail "npm publish failed (non-OTP error -- see output above). If E401/E404, the automation token in ~/.npmrc is missing or stale: restore/verify it (check the //registry.npmjs.org/:_authToken line; 'npm whoami' should answer). Do NOT re-auth via the web login flow -- it ove…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 ctxlint -- npx -y @yawlabs/ctxlint
{
"mcpServers": {
"ctxlint": {
"args": [
"-y",
"@yawlabs/ctxlint"
],
"command": "npx"
}
}
}
[mcp_servers.ctxlint]
command = "npx"
args = ["-y", "@yawlabs/ctxlint"]
{
"mcpServers": {
"ctxlint": {
"args": [
"-y",
"@yawlabs/ctxlint"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ctxlint": {
"args": [
"-y",
"@yawlabs/ctxlint"
],
"command": "npx"
}
}
}
Scores your prompts against your real codebase — context-aware prompt intelligence
Research-backed linting + generation for agent context files (CLAUDE.md, AGENTS.md, Cursor rules).
Lint, measure, and sync AI context files across Cursor, Claude Code, Copilot.
Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.
Index your codebase. AI searches instead of re-reading files. 94% token savings.
Save tokens while coding — your AI agent gets structured code context, not file dumps.
Local file search for AI agents — semantic + keyword indexing over your codebase.
Static linter for CLAUDE.md-style agent constitution files: 10 operational-guardrail checks.
Answers built from our own checks of this server.