A local MCP safety layer that checks repository content and blocks or hides risky information before an AI agent can read it. Repository context means the files and data supplied to the agent.

Use it to protect repository context while an AI agent inspects or works with local project files.

It reduces the chance that secrets or other unsafe files are exposed to the agent during coding work.

contextlock — MCP server by LutaElbert

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add mcp/lutaelbert/contextlock/contextlock

Clone the repo

git clone --depth 1 https://github.com/LutaElbert/contextlock

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

contextlock scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

listed in the official MCP registry · 9 lines

What it actually says

{ "contextlock": { "command": "npx", "args": [ "-y", "contextlock" ] } }

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 9 lines scan A 83d7afff8c74

Subscribe to this mod's changes

contextlock is an MCP server published in the GitHub repository LutaElbert/contextlock (0 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

AI Safety Data and AI Writing and docs coding-agents developer-tools local-first mcp model-context-protocol

contextlock

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

mcp-light-memory

mcp

ithz-mcp

flameox

agentlens

reporelay