Witnessed runs on your own machine — the client starts it, so there is no endpoint to ping. 16 installs a week from npm.
Signed, reproducible market facts for agents, verifiable without trust.
The linked repository no longer exists on GitHub — it was deleted or made private.
What the code does
We have not read this server's code yet, 4 d 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.
этот файл ставится пользователю, но в репозитории его нет
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
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 mcp add witnessed -- npx -y witnessed-sdk{
"mcpServers": {
"witnessed": {
"command": "npx",
"args": [
"-y",
"witnessed-sdk"
]
}
}
}[mcp_servers.witnessed]
command = "npx"
args = ["-y", "witnessed-sdk"]{
"mcpServers": {
"witnessed": {
"command": "npx",
"args": [
"-y",
"witnessed-sdk"
]
}
}
}{
"servers": {
"witnessed": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"witnessed-sdk"
]
}
}
}Optional settings from the registry entry, left out of the block above:
WITNESSED_BASE (Base URL of the publication (default https://api.witnessed.workers.dev)).
Alternatives to Witnessed
same job, measured the same wayVerifiable text/code/measurement tools for agents, each reproducing a named authority.
Marketplace and payment rail for AI agents: list, buy and settle with signed receipts.
Trust gate for AI agents: multi-model adversarial consensus, signed and verifiable verdicts.
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
Verifiable execution for AI agents: Ed25519-signed work contracts and audit trails.
Verifiable agent memory with signed ledger receipts — verify every write offline.
Marketplace-evidence trust scores for AI agents: a 0-100 Evidence Score with signal breakdown.
Tamper-proof audit trail for AI agents. Signed receipts, offline-verifiable, zero backend.
Witnessed — questions
Answers built from our own checks of this server.