protect-context MCP Server

by xjtlumedia Your server? Claim it

local only

protect-context runs on your own machine — the client starts it, so there is no endpoint to ping. 828 installs a week from pypi. Last commit 6 Nov 2026.

Agent guardrails: contract, evidence ledger, loop brake, diff-scope warnings, durable journal.

Installs per day peak 411 · avg 27

a month agotoday

828

Installs / week

pypi · protect-context

Stars

0 open issues

6 Nov 2026

Last commit

from GitHub

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check protect-context every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add protect-context -- uvx protect-context

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "protect-context": {
      "command": "uvx",
      "args": [
        "protect-context"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.protect-context]
command = "uvx"
args = ["protect-context"]

.cursor/mcp.json

{
  "mcpServers": {
    "protect-context": {
      "command": "uvx",
      "args": [
        "protect-context"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "protect-context": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "protect-context"
      ]
    }
  }
}

Alternatives to protect-context

same job, measured the same way

Lore Context

by lore-context

Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.

34 installs/wk local only

Guard

by codapult

Local-first architecture guardrails and project context for JS/TS AI coding agents.

1 847 installs/wk local only

KnowledgeRail

by deviank88

Persistent, evidence-backed project knowledge and task context for coding agents.

local only

Agent Guard

by mdfifty50-boop

Constitutional guardrails and loop detection for AI agents

58 installs/wk local only

Kubeleash

by kubeleash

Kubernetes MCP server with RBAC-style, context-scoped guardrails for AI agents.

local only

Basecite

by paxton888

Tenant-scoped evidence intake and controlled AI context over MCP.

3 tools answering

Trail

by usetrail

Issue tracker and durable project memory for your coding agent, scoped to the folder you open.

129 installs/wk local only

Aethelgard Ledger

by aethelgard

Double-entry, multi-entity, tamper-evident ledger for AI agents. Unbalanced journals are rejected.

local only

protect-context — questions

Answers built from our own checks of this server.

Why is there no uptime for protect-context?

protect-context runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package protect-context was installed 828 times last week.

How do I connect protect-context?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls protect-context straight from pypi; nothing to host, nothing to sign up for.

How many people use protect-context?

The pypi package protect-context was installed 828 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is protect-context open source?

Yes — it is published under the MIT licence, written in TypeScript and 2 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.