taxtrace runs on your own machine — the client starts it, so there is no endpoint to ping. 500 installs a week from pypi. Last commit 3 Nov 2026.
Masked, read-only views of a local tax workspace: documents, form checks and to-dos.
We read the source, 1 d ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
r = subprocess.run(["security", "find-generic-password", "-s", item, "-w"], capture_output=True, text=True)
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.
r = subprocess.run(["security", "find-generic-password", "-s", item, "-w"], capture_output=True, text=True)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch taxtrace and you get told the day something new turns up.
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 taxtrace -- uvx taxtrace
{
"mcpServers": {
"taxtrace": {
"command": "uvx",
"args": [
"taxtrace"
]
}
}
}
[mcp_servers.taxtrace]
command = "uvx"
args = ["taxtrace"]
{
"mcpServers": {
"taxtrace": {
"command": "uvx",
"args": [
"taxtrace"
]
}
}
}
{
"servers": {
"taxtrace": {
"type": "stdio",
"command": "uvx",
"args": [
"taxtrace"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
TAXTRACE_HOME (Path to your tax workspace folder (documents by tax year, todo.md). Defaults to ~/TaxData. Outside any git repository).
Markdown workspace for AI agents: read, write, organize, and share markdown documents.
Query local XML documents with XPath, paged and sandboxed to one folder. Read-only.
Score documents and check agent work — signed PactCheck Receipts: proof-of-review for agents.
Agentic localization for documents and media, with quality checks and optional human review.
Shared team context for ProductNow: search, read, write and organise workspace documents.
Local office proxy for documents, invoicing, spreadsheets and supplier statement checks.
One shared memory for all your AI agents: documents, tasks, databases and memories in one workspace
Local-first document MCP for AI agents: create, read, secure and sign PDF/Word/Excel/PPTX.
Answers built from our own checks of this server.