FRENES

Finance and payments · MCP server

Finlynq: MCP server, setup and security

Finlynq is an open-source MCP server published on GitHub that lets an AI agent track and query personal income, expenses, budgets and investments. Its repository has 25 stars and its last commit is from October 24, 2026 and it is licensed under AGPL-3.0.

Score
59/100
Adoption (stars) 14/40
Maintenance 30/30
Framework (licence, registry, official) 15/30
Actively maintained

What Finlynq does

According to its repository: “Self-hostable personal finance app: track and query income, expenses, budgets, investments, loans, subscriptions and goals, with per-user encryption at rest.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. Finlynq is listed under Finance and payments, a category of 202 servers in the directory, where it ranks #77 by stars.

Topics declared by the repository: local-first, nextjs, open-source, personal-finance, postgresql, privacy.

Installing and connecting Finlynq

No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: TypeScript. Listed systems: macOS, Windows, Linux.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Finlynq. 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 April 28, 2026, the finlynq/finlynq repository has 25 stars and 19 forks, with 1 open issues. It has more stars than 42% of the servers in the directory. It received changes this month.

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

Finance ToolkitFinance Toolkit : 5.5K5.5KTradingMCPTradingMCP : 5.1K5.1KTradememory protocolTradememory protocol : 1.4K1.4KCNEquityCNEquity : 846846Metatrader MCP serverMetatrader MCP server : 837837EVMoleEVMole : 473473OpenAccountantsOpenAccountants : 460460AkTools MCP ServerAkTools MCP Server : 391391FinlynqFinlynq : 2525
GitHub stars of the most followed servers in the category (log scale); Finlynq in orange. Checked October 25, 2026.

Verdict

Finlynq is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit

Limitations

  • Install from source

Frequently asked questions

How do I install Finlynq?

No package is declared in the MCP registry: clone the finlynq/finlynq repository, follow its README, then declare the start command in your client's MCP configuration.

Is Finlynq free?

The code is published under the AGPL-3.0 licence and can be used free of charge.

Is Finlynq 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 finlynq on GitHub. Check who maintains it before giving it access.

What are the alternatives to Finlynq?

In the same category: TradingMCP, Finance Toolkit, Tradememory protocol, and Tapetide Indian Stock Market MCP. TradingMCP and Finance Toolkit 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