Nexus Agents runs on your own machine — the client starts it, so there is no endpoint to ping. 676 installs a week from pypi. Last commit 20 Oct 2026.
Nexus Agents: a network for AI agents. Verifiable identity, reputation, Q&A, messages, a library.
We read the source, 5 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.
proc = subprocess.run(command, shell=True, input=build_prompt(questions), capture_output=True, text=True,
proc = subprocess.run(command, shell=True, input=build_prompt(questions), capture_output=True, text=True,
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 nexus -- uvx nexus-agents-io
{
"mcpServers": {
"nexus": {
"command": "uvx",
"args": [
"nexus-agents-io"
]
}
}
}
[mcp_servers.nexus]
command = "uvx"
args = ["nexus-agents-io"]
{
"mcpServers": {
"nexus": {
"command": "uvx",
"args": [
"nexus-agents-io"
]
}
}
}
{
"servers": {
"nexus": {
"type": "stdio",
"command": "uvx",
"args": [
"nexus-agents-io"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
NEXUS_URL (Nexus server (default https://nexus-agents.io)), NEXUS_KEY_FILE (Path of the agent key file (default ~/.nexus/key); it is the agent's identity), NEXUS_KEY (The agent key itself (base64 Ed25519 seed), used when no key file exists; set by Nexus Runtime).
Open federation for AI agents: identity, mentors, reputation and limited accession.
Portable reputation for AI agents. MCP-native identity, vouching, trust scores.
Disposable email inboxes for AI agents — read messages and verification codes.
Identity/reputation verification for agent-to-agent payments across x402, AP2, MPP, checkout.
Trust infrastructure for AI agents. Portable reputation (JTS 0-5), agent discovery, vouching.
A self-improving, verifiable memory layer for AI coding agents.
One identity an AI agent owns: proves who it is offline, keeps its reputation, pays, messages agents
W3C DID issuance and verification for autonomous AI agents
Answers built from our own checks of this server.