Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TAXTRACE_HOMENoThe path to your taxtrace workspace folder (the folder holding your documents and everything derived from them). Defaults to ~/TaxData.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

Reads a person's tax workspace (their own documents, folder by folder, kept on their computer) and gives back only MASKED text: # stands for a digit and a run of * for a word that could identify someone (a name, a street, a town). No tool returns an amount, name, ID or account number; never guess what was masked, and tell the person to open the page (taxtrace ui) or ask the local model for the real values. get_status counts the tax years, folders and documents, and how many were read; list_documents names each document (masked) with an id; get_document_outline lists a document's pages by masked heading, which forms it holds; get_form_checks says which Form 1098, 1099-DIV, 1099-INT and K-1 readings passed their checks (every value traced to its page) and which failed or raised a question; get_todo lists the person's money and tax to-dos by due date (the dates are real, the wording masked). taxtrace never files anything and these tools change nothing.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_statusA

What the person's workspace holds, as counts: tax years (folders named for one), each folder's number of documents, how many documents taxtrace has read, how many files it saved per kind of reading, and whether a to-do list exists. Names are masked. Start here; for the documents themselves use list_documents, for the to-dos use get_todo.

list_documentsA

The workspace's documents, each with an id, its folder and file name (masked), its kind (pdf, csv, ...) and whether it was read. Nothing is opened, so no password is asked for. The id is what get_document_outline and get_form_checks take. For counts only use get_status.

get_document_outlineA

A document's pages, each with its first lines masked: which forms and worksheets it holds, and in what order. A password-protected document is reported as locked, not opened (taxtrace's own commands read it with a password from the Keychain). To see how the forms in it checked out use get_form_checks; to find the id, list_documents.

get_form_checksA

Read the forms of one kind in the workspace's PDFs and report how their checks came out, never a value: per form its document id, page, tax year, how many checks passed of how many, the ones that failed and the questions it leaves the person (box names and masked quotes). Every value taxtrace reads is traced to its page and rejected if its text isn't there, so a failed check means a value to look at by hand. Locked documents are skipped and counted. For a document's other pages use get_document_outline.

get_todoA

The person's open money and tax to-dos from todo.md in their workspace, soonest first: section, due date, days left, group (overdue, today, week, later, undated), and the text, notes and sub-tasks masked (the dates are real; the wording is masked, so ask the person what an item says if it matters). Nothing is changed: the person ticks items on the taxtrace page. For the documents use list_documents.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.5/5.0

Scored across 5 tools

Disambiguation5/5

Each tool has a distinct resource and action: workspace counts, document inventory, per-document outline, form-check results, and to-dos. Descriptions explicitly point to sibling tools for adjacent needs, so an agent can tell which tool to use.

Naming Consistency5/5

All tool names are snake_case verb_noun forms: list_documents, get_status, get_todo, get_document_outline, get_form_checks. The get_/list_ distinction is used consistently for retrieval style.

Tool Count5/5

Five tools are well-scoped for a read-only tax workspace inspection server. Each tool covers a distinct layer of the workspace and none appears redundant.

Completeness4/5

The surface covers workspace overview, document listing, per-document outline, form-check results, and to-do retrieval. The read-only design is intentional, though there is no direct document-content or search tool for deeper inspection.

Maintenance

ActivityMaintained
ResponsivenessOutdated data