MCP / privacy proxy / open source

Your AI sees aliases.
Your secrets stay yours.

OpenMaskit is an MCP proxy that strips sensitive values from tool responses before they reach your AI agent — and puts them back when the agent calls home.

§ 01

Every MCP tool response your agent reads becomes part of its context window. Hostnames, tokens, customer emails, internal IPs — once they're in the prompt, they're somewhere: in transit, in logs, in someone else's training pipeline. The agent doesn't need the real values to do its job. It just needs something to refer to them by.

§ 02
CLIENT AI agent Claude · Cursor · Codex · …
mcp / http
PROXY OpenMaskit localhost · open source
stdio / http
UPSTREAM MCP server Slack · GitHub · Postgres · …

Drop OpenMaskit between your agent and the MCP servers it already talks to. Responses pass through; sensitive values are replaced with stable aliases on the way out, and swapped back to real values on the way in.

§ 03

Everything runs on your machine.

Masking happens locally. Aliases are computed locally. The audit log is local, encrypted at rest. Real values, masked values, tool-call payloads — none of it ever crosses the wire to us. Read the privacy policy →

§ 04
# requires Python 3.10+ (uvx fetches one if needed)
UV_INDEX_URL=https://test.pypi.org/simple/ \
UV_EXTRA_INDEX_URL=https://pypi.org/simple/ \
uvx --from openmaskit==0.1.0 openmaskit

Pre-release. OpenMaskit is currently published to TestPyPI while we finalize the first release; once 0.1.0 lands on PyPI proper this becomes uvx openmaskit. Don't have uv? curl -LsSf https://astral.sh/uv/install.sh | sh. Then open http://127.0.0.1:9473 — the README has the full reference.

§ 05

Running this across a team?

We're building a version of OpenMaskit for organizations — central policy, shared masking rules, audit retention, SSO, and support. The shape of it is still being drawn, and the earliest conversations carry the most weight. If that sounds like you, write to business@maskitmcp.com — tell us what you'd need it to do.