OpenAccountants provides country-specific tax computation skill files for LLMs to classify bank statement transactions and assemble tax working papers. It can be used by uploading jurisdiction folders directly or by connecting through an MCP server that fetches the right skills automatically.
From the registry: Open-source tax skills for AI across 134 countries.
$ git clone https://github.com/openaccountants/openaccountants.git$ cd openaccountants && pip install ./mcpPlease install the `openaccountants-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.10+** — Python 3.10 or newer is required to install and run the OpenAccountants MCP server.
- **Clone the OpenAccountants repository** — The README installs the MCP server from the local repository checkout. Run: `git clone https://github.com/openaccountants/openaccountants.git` (https://github.com/openaccountants/openaccountants)
- **Install the MCP package** — From the cloned repository, install the MCP package so the `openaccountants-mcp` command is available. Run: `cd openaccountants && pip install ./mcp`
Canonical MCP server config (stdio transport):
- command: `openaccountants-mcp`
- args: []
Note: The README shows a stdio MCP server launched via the `openaccountants-mcp` command. No environment variables are specified in the provided README. It also mentions that additional setup details, `uv` instructions, and environment variables may exist in `mcp/README.md`, but they are not included here.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.