RecourseOS MCP Server

by recourseos Your server? Claim it

local only

RecourseOS runs on your own machine — the client starts it, so there is no endpoint to ping. 285 installs a week from npm.

Consequence evaluation for AI agents. Check recoverability before destructive actions.

The linked repository no longer exists on GitHub — it was deleted or made private.

Installs per day peak 78 · avg 16 · -45% w/w

a month agotoday

285

Installs / week

npm · recourse-cli

—

Stars

on GitHub

—

Last commit

0 releases in 90 days

—

License

language unknown

This one has been quiet for a while

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.

Connect this server

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 Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add recourse -- npx -y recourse-cli

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "recourse": {
      "args": [
        "-y",
        "recourse-cli"
      ],
      "command": "npx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.recourse]
command = "npx"
args = ["-y", "recourse-cli"]

.cursor/mcp.json

{
  "mcpServers": {
    "recourse": {
      "args": [
        "-y",
        "recourse-cli"
      ],
      "command": "npx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "recourse": {
      "args": [
        "-y",
        "recourse-cli"
      ],
      "command": "npx"
    }
  }
}

Alternatives to RecourseOS

same job, measured the same way

Decionis

by decionis

Authorize consequential AI agent actions before execution

317 installs/wk answering

AgentPing

by agentping

Production observability for AI agents: search runs, read evaluations, acknowledge incidents.

answering

MUJ428 Trust Layer — VERIFY BEFORE ACT

by wmujahid428-web

MUJ428 verifies intent and evidence before consequential AI-agent actions.

14 tools answering

Cleotic

by generaldataworks

AI brand visibility, competitor mentions and citation evidence for agents. Cleotic account required.

answering

Fidacy MCP

by lucaslubi

AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required.

585 installs/wk local only

Domain & Company Intel MCP

by datakoot

Domain intel for AI agents: RDAP registration, DNS, email deliverability, tech stack.

6 tools answering

Agent Guard

by ipezygj

Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

33 installs/wk local only

Undo MCP

by agentutil

Reversibility intelligence — check if actions can be undone before executing them.

23 installs/wk local only

RecourseOS — questions

Answers built from our own checks of this server.

Why is there no uptime for RecourseOS?

RecourseOS runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package recourse-cli was installed 285 times last week.

Is RecourseOS still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

How do I connect RecourseOS?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls recourse-cli straight from npm; nothing to host, nothing to sign up for.

How many people use RecourseOS?

The npm package recourse-cli was installed 285 times in the last week. Week over week that is -45%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.