mcpField
F
fizlog-mcp

fizlog-mcp

Local
github.com/firmalemonyDeveloper Tools0Updated 4w ago

About fizlog-mcp

fizlog-mcp is an MCP server for publishing and reading changelog entries in Fizlog, a changelog widget for indie SaaS. It supports publishing, scheduling, or drafting entries and retrieving recent public updates.

Key features

  1. 01Publish, schedule, or draft entries
  2. 02Read recent public changelog entries
  3. 03Optional subscriber email
  4. 04Configurable self-hosted Fizlog URL

Use cases

  1. 01Announcing a newly shipped feature
  2. 02Scheduling a release update
  3. 03Saving a changelog draft
  4. 04Checking recent entries before publishing

MCP support

The server exposes tools to publish or save Fizlog entries and read the public changelog through MCP clients such as Claude and Cursor. It uses API and public keys for authentication and access.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"firmalemony-fizlog": {
"command": "npx",
"args": [
"-y",
"fizlog-mcp"
],
"env": {
"FIZLOG_API_KEY": "<FIZLOG_API_KEY>",
"FIZLOG_PUBLIC_KEY": "<FIZLOG_PUBLIC_KEY>",
"FIZLOG_BASE_URL": "<FIZLOG_BASE_URL>"
}
}
}
}
Run commandnpx -y fizlog-mcp
Environment variables to set
FIZLOG_API_KEYSecretProject API key from fizlog.com
FIZLOG_PUBLIC_KEYSecretProject public key (default for reading the changelog)
FIZLOG_BASE_URLBase URL for self-hosted Fizlog

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmfizlog-mcp0.1.0

Tools

2

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
bodystringNoDetails in Fizlog's Markdown subset.
typeenumNonew = feature, improved = enhancement, fixed = bug fix.new | improved | fixed
draftbooleanNoSave as an unpublished draft instead of publishing.
titlestringYesShort, user-facing headline, e.g. 'Dark mode is here'.
published_atstringNoISO 8601 date-time. A future value schedules the entry.
notify_subscribersbooleanNoAlso email the project's subscribers (only for immediate, non-draft entries).

Details

From the project README

fizlog-mcp

MCP server for Fizlog — the changelog widget for indie SaaS. Let Claude, Cursor or any MCP client announce what you just shipped:

"Publish a changelog entry for the CSV export I just finished."

Tools

ToolWhat it does
publish_entryPublishes (or schedules / saves as draft) an entry — shows up in your in-app widget, public changelog page and RSS. Optional subscriber email.
get_public_changelogReads your latest published entries, so the assistant can avoid duplicates or summarize releases.

Setup

  1. In Fizlog, open your project and copy the API key (and the public key from the embed snippet).
  2. Add the server to your MCP client:

Claude Code

claude mcp add fizlog -e FIZLOG_API_KEY=fz_xxx -e FIZLOG_PUBLIC_KEY=your_public_key -- npx -y fizlog-mcp

Claude Desktop (claude_desktop_config.json) / Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "fizlog": {
      "command": "npx",
      "args": ["-y", "fizlog-mcp"],
      "env": { "FIZLOG_API_KEY": "fz_xxx", "FIZLOG_PUBLIC_KEY": "your_public_key" }
    }
  }
}
Env varRequiredDefault
FIZLOG_API_KEYfor publish_entry—
FIZLOG_PUBLIC_KEYno (default for get_public_changelog)—
FIZLOG_BASE_URLno (self-hosted Fizlog)https://fizlog.com

Related

  • publish-to-fizlog — GitHub Action that posts a Fizlog entry for every GitHub release.
  • Fizlog migration guides — move your changelog from Beamer, Headway, AnnounceKit, Canny and others.
  • Listed in the official MCP Registry as io.github.firmalemony/fizlog-mcp.

Development

npm install
npm run build
FIZLOG_BASE_URL=http://localhost:8888/fizlog FIZLOG_API_KEY=... FIZLOG_PUBLIC_KEY=demo npm run smoke

The smoke test creates one draft entry in the target project — run it against a local/test instance.

MIT © Lemony Apps

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.