Skip to content
TaxCompass logo

TaxCompass MCP server

Which servers in the official MCP registry are TaxCompass's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-20

← Back to TaxCompass

Whose server it is
  • Registry nameit.taxcompass/taxcompassverified in the MCP registry

The registry name sits under taxcompass.it. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-20
  • Stateanswerschecked 2026-10-20
  • Tools4
  • Server calls itselfTaxCompass
  • Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 514 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 3 of 4 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-20
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer559 ms
  • Space in an agent's context≈ 1,023 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsB · 88 of 100
  • Typed results4 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 4

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers4 tools · read 2026-10-20
  • search_italian_tax_sources

    Search TaxCompass's primary-source corpus and return passages to cite. Hybrid semantic + keyword retrieval over Italian tax & company-law primary sources: Normattiva (statute), Agenzia delle Entrate (circolari & guidance), INPS (social…

  • list_tax_sources

    List the primary sources the corpus can search, and what each covers. Use this to discover the valid `sources` filter values for `search_italian_tax_sources` and to understand the corpus's coverage.

  • calculate_italian_tax

    Compute exact Italian tax for one regime at a given annual revenue. Deterministic calculation (not an estimate): substitute/income tax, INPS social contributions, net income, and effective rate. `breakdown.eligible` is False when the…

  • compare_italian_regimes

    Compare all Italian regimes side by side at one revenue level. Runs forfettario (5% & 15%), ordinario, and ordinario + impatriati through the deterministic engine and returns them sorted by net income (best first), each with its full…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "taxcompass": {
      "type": "http",
      "url": "https://api.taxcompass.it/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http taxcompass https://api.taxcompass.it/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://api.taxcompass.it/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.