FRENES

Developer tools · MCP server

MCP Fiscal Brasil: MCP server, setup and security

MCP Fiscal Brasil is an open-source MCP server that lets an AI agent access Brazilian tax tools without providing an API key. Its repository has 335 stars and its last commit is from October 23, 2026 and it is licensed under MIT.

Actively maintained

What MCP Fiscal Brasil does

According to its repository: “Ferramentas fiscais brasileiras: CNPJ, NF-e, IBS/CBS, ICMS, Simples Nacional, NCM/CFOP. Sem API key.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. MCP Fiscal Brasil is listed under Developer tools, a category of 475 servers in the directory, where it ranks #82 by stars.

Topics declared by the repository: brasil, claude, cnpj, fiscal, nfe, python.

Installing and connecting MCP Fiscal Brasil

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Python.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to MCP Fiscal Brasil. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on March 27, 2026, the DeHor-Labs/mcp-fiscal-brasil repository has 335 stars and 71 forks, with 9 open issues. It has more stars than 84% of the servers in the directory. It received changes this month. Version published in the registry: 0.5.1 (October 17, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

StorybookStorybook : 91.4K91.4KFront End ChecklistFront End Checklist : 74.6K74.6KTldrawTldraw : 51.1K51.1KCodebase MemoryCodebase Memory : 47.4K47.4KCCXTCCXT : 44.5K44.5KPostHog MCP ServerPostHog MCP Server : 40.4K40.4KClaude task masterClaude task master : 28.3K28.3KAgent Skills Search ServerAgent Skills Search Server : 26.6K26.6KMCP Fiscal BrasilMCP Fiscal Brasil : 335335
GitHub stars of the most followed servers in the category (log scale); MCP Fiscal Brasil in orange. Checked October 25, 2026.

Verdict

MCP Fiscal Brasil is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Widely followed: 335 stars
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Frequently asked questions

How do I install MCP Fiscal Brasil?

MCP Fiscal Brasil is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of DeHor-Labs/mcp-fiscal-brasil.

Is MCP Fiscal Brasil free?

The code is published under the MIT licence and can be used free of charge.

Is MCP Fiscal Brasil safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Nothing says so: it is a project published by DeHor-Labs on GitHub. Check who maintains it before giving it access.

What are the alternatives to MCP Fiscal Brasil?

In the same category: Radar Kubernetes MCP Server, Repowise, Jscpd, and Apify MCP server. Radar Kubernetes MCP Server and Repowise score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score