E3d Pilot runs on your own machine — the client starts it, so there is no endpoint to ping. 796 installs a week from npm. Last commit 24 Oct 2026.
Multi-model debate with named dissent, plus decision provenance queries for AI coding work.
We read the source, 1 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.
const child = spawn(cmd, args, { cwd, env, stdio: [input === undefined ? 'ignore' : 'pipe', 'pipe', 'pipe'] });
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 e3d-pilot -- npx -y e3d-pilot
{
"mcpServers": {
"e3d-pilot": {
"command": "npx",
"args": [
"-y",
"e3d-pilot"
]
}
}
}
[mcp_servers.e3d-pilot]
command = "npx"
args = ["-y", "e3d-pilot"]
{
"mcpServers": {
"e3d-pilot": {
"command": "npx",
"args": [
"-y",
"e3d-pilot"
]
}
}
}
{
"servers": {
"e3d-pilot": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"e3d-pilot"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
E3D_MCP_MAX_ROUNDS (Maximum debate rounds per call (default 3)), E3D_MCP_MAX_PROVIDERS (Maximum model providers per debate (default 4)), E3D_MCP_MAX_CONCURRENT (Maximum concurrent debates (default 2)), E3D_MCP_TIMEOUT_SEC (Per-debate timeout in seconds (default 900)).
Multi-model AI brainstorming debates with code review and quick perspectives
Free market data with provenance and paid decision intelligence for AI agents.
Tested, version-pinned code recipes for AI coding agents, each with its last-passed receipt.
Context integrity for AI agents: evaluate freshness, confidence, provenance, and decision readiness.
Multi-model AI orchestration MCP server with code review, compare, and debate tools.
Professional network for AI agents. Discover and connect with professionals.
Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.
AI agent governance with resolved business context, current decisions, provenance, and supersession.
Answers built from our own checks of this server.