GRC Lake runs on your own machine — the client starts it, so there is no endpoint to ping. 4 833 installs a week from pypi. Last commit 1 Nov 2026.
Read-only connectors; local writes. Evidence and assessments for agents. Only people approve.
We read the source, 14 h ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
completed = subprocess.run(
trap 'rm -rf "$terraform_dir"' EXIT
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.
completed = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch GRC Lake and you get told the day something new turns up.
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 grc-lake -- uvx grc-lake
{
"mcpServers": {
"grc-lake": {
"command": "uvx",
"args": [
"grc-lake"
]
}
}
}
[mcp_servers.grc-lake]
command = "uvx"
args = ["grc-lake"]
{
"mcpServers": {
"grc-lake": {
"command": "uvx",
"args": [
"grc-lake"
]
}
}
}
{
"servers": {
"grc-lake": {
"type": "stdio",
"command": "uvx",
"args": [
"grc-lake"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
GRC_LAKE_LAKE (Path to a local lake directory (default ./lake)), GRC_LAKE_MCP_MODE (local, remote or auto (default); use remote on shared machines), GRC_LAKE_API_URL (GRC Lake API URL for remote mode), GRC_LAKE_API_KEY (API key for remote mode).
Fast, bounded, read-only Git evidence for local AI coding agents.
Read-only observable merchant evidence for people and agents, without scores or safety verdicts.
Read-only MCP access to a local append-only evidence ledger for AI agent sessions.
Local context and engineering evidence for AI coding agents.
One record of code, files and pages that people and agents read and write, with lanes and git.
Preventive human-approval write-gate for AI agents: writes commit only after a human approves.
Local-first Ownly evidence and repeatable Planner visits with preview-before-commit writes.
Governance maturity assessment, compliance gap analysis, and evidence-linked briefs for AI agents.
Answers built from our own checks of this server.