Jev agent tools runs on your own machine — the client starts it, so there is no endpoint to ping. 499 installs a week from npm. Last commit 7 Oct 2026.
Evidence-oriented code questions, diff review and test selection via a Jev endpoint.
We read the source, 4 d ago · rules ccca72095570
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.
execFile(
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 jev-agent-tools -- npx -y jev-agent-tools
{
"mcpServers": {
"jev-agent-tools": {
"args": [
"-y",
"jev-agent-tools"
],
"command": "npx"
}
}
}
[mcp_servers.jev-agent-tools]
command = "npx"
args = ["-y", "jev-agent-tools"]
{
"mcpServers": {
"jev-agent-tools": {
"args": [
"-y",
"jev-agent-tools"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"jev-agent-tools": {
"args": [
"-y",
"jev-agent-tools"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
JEV_TOOLS_URL (Complete endpoint URL compatible with the Jev API format.), JEV_TOOLS_API_KEY (Bearer credential for the endpoint.), JEV_TOOLS_MODEL (Requested Jev model.), JEV_TOOLS_ALLOW_COMMAND (Set to 0 to remove shell commands from jev_ask.).
The author declared them in the registry entry; get the values from the project itself.
Runs coding-agent workers on a codebase question; every claim in the answer carries evidence.
Self-hosted code intelligence: cross-repo Q&A, dependency audits and PR review, over MCP
Bounded agent tools: time, hash, UUID, codec, JSON, request identity, and service discovery.
Your code review comments from Reado, the read-first IDE, as context and tools for your agent.
Multi-model AI orchestration MCP server with code review, compare, and debate tools.
Selects the minimum code an LLM needs to review a git diff
63 semantic Java analysis tools via Eclipse JDT: navigation, refactoring, code intelligence.
Mines your Claude Code and Cursor sessions into evidence-based CLAUDE.md / AGENTS.md rules.
Answers built from our own checks of this server.