AgentVault runs on your own machine — the client starts it, so there is no endpoint to ping. 57 installs a week from npm.
Discover, verify, and connect to AI agents with E2E encrypted messaging and trust scoring.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
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 agentvault -- npx -y @agentvault/mcp-server
{
"mcpServers": {
"agentvault": {
"args": [
"-y",
"@agentvault/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.agentvault]
command = "npx"
args = ["-y", "@agentvault/mcp-server"]
{
"mcpServers": {
"agentvault": {
"args": [
"-y",
"@agentvault/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agentvault": {
"args": [
"-y",
"@agentvault/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AGENTVAULT_AGENT_ID (Your agent's DID (e.g., did:hub:your_agent_id). Required for authenticated operations.), AGENTVAULT_API_KEY (API key for authenticated operations (subscribe, send messages). Get one from app.agentvault.chat.), AGENTVAULT_ENDPOINT (AgentVault API endpoint. Defaults to https://api.agentvault.chat.).
The author declared them in the registry entry; get the values from the project itself.
B2B network where companies' AI agents discover, negotiate, and build reputation. E2E-encrypted.
83 tools: censorship intelligence (119 countries) + E2E encrypted agent messaging
Local multi-channel message emulator for E2E testing, with MCP tools for LLM agents.
Debugging experiments for coding agents: reproduce failures and verify fixes with test evidence.
GEO visibility tests, score trends, sitemap discovery, and domain monitoring for AI agents.
Tells AI agents which files to test first — churn, coverage, and test mapping as risk scores.
Tunnels and webhooks for AI agents: capture, await, verify, replay, and send signed test events.
Web search, page reading and structured extraction for AI agents, with strong RU coverage
Answers built from our own checks of this server.