MCP Cci MCP Server

<h1 align="center">SFCore TH Dev: CumulusCI Integration for AI Agents</h1>

Local serverstdioPython

What is the MCP Cci MCP server?

What it actually does

This project demonstrates how to build an MCP server that enables AI agents to execute CumulusCI operations for Salesforce development workflows. It serves as a foundation for creating more comprehensive CCI integrations.

Configuration

You will need 2 environment variables: TRANSPORT, GITHUB_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • Python 3.12+ - Access to a Salesforce org (Dev Hub for scratch orgs) - Docker if running the MCP server as a container (recommended)

Adding it to your client

The server ships on PyPI as cumulusci-plus-azure-devops, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

When to reach for it

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. It is maintained by jorgesolebur; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp cci mcp server does with a few real requests.

How to install the MCP Cci MCP server

### Docker with Stdio Configuration

```json
{
  "mcpServers": {
    "sfcore-th-dev": {
      "command": "docker",
      "args": ["run", "--rm", "-i", 
               "-e", "TRANSPORT", 
               "ghcr.io/jorgesolebur/mcp-sfcore-th-dev:latest"],
      "env": {
        "TRANSPORT": "stdio"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Python 3.12+ - Access to a Salesforce org (Dev Hub for scratch orgs) - Docker if running the MCP server as a container (recommended)
VariableDescriptionRequired
TRANSPORTConfiguration value read at startup.Optional
GITHUB_TOKENCredential the server authenticates with.Yes

Frequently asked questions

It connects MCP Cci to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with MCP Cci directly.