witness runs on your own machine — the client starts it, so there is no endpoint to ping. 1 114 installs a week from npm. Last commit 7 Nov 2026.
Distills your sessions or any text corpus into a dated history of how its subject changed.
We read the source, 13 h ago · rules 995398eba69f
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.
child = spawn(runner.cmd, [...runner.args, scriptPath, "--foreground", packageRoot, lock.lock, lock.token], {
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
return filepath.Join(root, subdir)
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 witness -- npx -y @witness-ai/opencode
{
"mcpServers": {
"witness": {
"command": "npx",
"args": [
"-y",
"@witness-ai/opencode"
]
}
}
}
[mcp_servers.witness]
command = "npx"
args = ["-y", "@witness-ai/opencode"]
{
"mcpServers": {
"witness": {
"command": "npx",
"args": [
"-y",
"@witness-ai/opencode"
]
}
}
}
{
"servers": {
"witness": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@witness-ai/opencode"
]
}
}
}
Search and read your local AI chat-history corpus: full-text search, transcripts, inventory.
Forecasts for any US point, with context: alerts, what changed overnight, why, and history.
Mine your AI coding session logs into a you.md profile with dated receipts, for an agent to read.
Workout log your AI fills in: sets from text or notebook photos, daily plans, history and records.
Search Console in your AI IDE: the plan, stored history, and a measured record of every change.
Which danger level has Japan's MOFA set for a country and its regions? Hosted, change history kept.
Talk to any Figma file with your AI: ask what's in it, change it, or turn it into code.
Token-aware message truncation: fit a chat history into your model's context budget.
Answers built from our own checks of this server.