Conector runs on your own machine — the client starts it, so there is no endpoint to ping. 1 094 installs a week from npm. Last commit 25 Oct 2026.
Self-hosted MCP gateway: connect 1,178 apps once and use them from any AI agent.
We read the source, 3 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.
if (["169.254.169.254", "fd00:ec2::254", "metadata.google.internal"].includes(h)) return false;
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.
const onPath = (bin) => spawnSync(process.platform === "win32" ? "where" : "sh", process.platform === "win32" ? [bin] : ["-c", `command -v ${bin}`],
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 Conector 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 conector -e 'CONECTOR_URL=<CONECTOR_URL>' -e 'CONECTOR_TOKEN=<CONECTOR_TOKEN>' -- npx -y conector
{
"mcpServers": {
"conector": {
"command": "npx",
"args": [
"-y",
"conector"
],
"env": {
"CONECTOR_TOKEN": "<CONECTOR_TOKEN>",
"CONECTOR_URL": "<CONECTOR_URL>"
}
}
}
}
[mcp_servers.conector]
command = "npx"
args = ["-y", "conector"]
env = { CONECTOR_URL = "<CONECTOR_URL>", CONECTOR_TOKEN = "<CONECTOR_TOKEN>" }
{
"mcpServers": {
"conector": {
"command": "npx",
"args": [
"-y",
"conector"
],
"env": {
"CONECTOR_TOKEN": "<CONECTOR_TOKEN>",
"CONECTOR_URL": "<CONECTOR_URL>"
}
}
}
}
{
"servers": {
"conector": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"conector"
],
"env": {
"CONECTOR_TOKEN": "<CONECTOR_TOKEN>",
"CONECTOR_URL": "<CONECTOR_URL>"
}
}
}
}
Put your own values in place of
<CONECTOR_URL> (MCP endpoint of your Conector server), <CONECTOR_TOKEN> (Access token (cnr_…) created in the Conector panel under Connect agents).
The author’s registry entry marks them as required.
Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors — no code.
One connector for 15,000+ MCP servers plus your team's private MCPs, from any AI client.
Self-hosted federated MCP gateway: one OAuth 2.1 MCP server in front of N apps, user-level scopes.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
One remote MCP connection: 39,500+ ranked MCP servers, agent delegation, hosted tool gateway.
Self-hosted AI gateway that governs MCP servers, LLM traffic, and A2A agents behind one endpoint
Self-hosted MCP gateway for Codex, Cursor, and Cline with provider-free prompt enhancement.
Connect AI agents to 580+ APIs with OAuth or API-key auth. Hosted gateway; API pricing varies.
Answers built from our own checks of this server.