mcpField
D
doubleoh-mcp

doubleoh-mcp

Local
doubleoh.aiAI & Agents1Updated 5w ago
RepositoryVisit website

About doubleoh-mcp

doubleoh-mcp provides an MCP-based fix loop for AI agents. It reuses procedures from prior human fixes, requests human help when needed, and collects outcome reports so ineffective skills stop being offered.

Key features

  1. 01Retrieve procedures from past fixes
  2. 02Request human help when blocked
  3. 03Avoid duplicate requests for known issues
  4. 04Report skill outcomes
  5. 05Stop serving repeatedly failing skills

Use cases

  1. 01Reuse a procedure after a task has failed before
  2. 02Escalate a new blocker to a human
  3. 03Prevent repeated alerts about an existing issue
  4. 04Report whether a suggested procedure worked

MCP support

It exposes the DoubleOh fix loop as three tools to MCP-capable agents. A self-hosted deployment can be selected with DOUBLEOH_BASE_URL.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "cheedli-doubleoh": {
      "command": "npx",
      "args": [
        "-y",
        "doubleoh-mcp"
      ],
      "env": {
        "DOUBLEOH_API_KEY": "<DOUBLEOH_API_KEY>",
        "DOUBLEOH_BASE_URL": "<DOUBLEOH_BASE_URL>"
      }
    }
  }
}
Run commandnpx -y doubleoh-mcp
Environment variables to set
DOUBLEOH_API_KEYSecretYour DoubleOh API key (starts with oo_). Issued in the console under Keys and settings.
DOUBLEOH_BASE_URLYour own DoubleOh, when self-hosting. Defaults to https://api.doubleoh.ai.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmdoubleoh-mcp0.1.1

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

doubleoh-mcp

The DoubleOh fix loop as an MCP server. Any MCP-capable agent — Claude Code, Claude Desktop, and the growing list of clients — gets the loop as three tools with zero integration code.

{
  "mcpServers": {
    "doubleoh": {
      "command": "bunx",
      "args": ["doubleoh-mcp"],
      "env": { "DOUBLEOH_API_KEY": "oo_live_…" }
    }
  }
}

The tools

  • doubleoh_skills_for — before attempting a task it has failed at before, the agent asks what has been learned and receives step-by-step procedures from past human fixes, with each one's track record.
  • doubleoh_request_fix — when stuck, the agent asks for a human. If the fleet already knows the wall, the procedure comes back instantly instead and nobody is paged. Duplicate walls are answered with "already being fixed, N runs blocked" — an agent in a retry loop never spams a team.
  • doubleoh_report_skill — after following a skill, the agent reports whether it worked. Skills that keep failing stop being served.

Refusals (a private URL, a quota) come back as readable tool results, not protocol errors — the model is told what went wrong in a sentence it can act on.

DOUBLEOH_BASE_URL points at a self-hosted deployment; it defaults to the hosted service.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.