Skip to content
DocFig logo

DocFig MCP server

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

read 2026-11-01

← Back to DocFig

Whose server it is
  • Registry namecom.docfig/docfigverified in the MCP registry

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

When we asked itchecked 2026-11-01
  • Stateanswerschecked 2026-11-01
  • Tools4
  • Server calls itselfdocfig
  • Server version0.2.0
  • Protocol version2025-06-18

On 2026-11-01 the server answered initialize and tools/list without a sign-in. First answer in 743 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 1 of the 7 days it takes to judge reliability.

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: 1, the first on 2026-11-01
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer701 ms
  • Space in an agent's context≈ 1,179 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 2026-11-01
  • check_transactions

    Check a bank or credit card statement's transactions table for errors. Free and offline: no API key, nothing is uploaded. Walks the running balance row by row and reports rows where the balance does not follow, swapped debit and credit…

  • convert_statement

    Convert a bank or credit card statement (PDF, scanned PDF, or a JPG, PNG or HEIC photo) into transactions, with every row checked against the balances. Give file_url or file_base64. Returns the bank, period, totals, check status, flagged…

  • combine_statements

    Convert several statements (or reuse statement_ids from the last hour) and combine them into one set of accounts: finds missing months (gaps), overlapping periods, duplicated transactions (kept once) and balances that do not carry over…

  • usage

    Pages used and left this month for the DocFig API key, and when they reset.

How to connect

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

{
  "mcpServers": {
    "docfig": {
      "type": "http",
      "url": "https://mcp.docfig.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http docfig https://mcp.docfig.com/mcp

Add to CursorAdd to VS Code

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

Also shipped through: npm, pypi

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.