About fnlowl
fnlowl provides agent skills for operating fnlowl lead-capture widgets, leads, follow-up sequences, and analytics. The bundle helps agents build and diagnose widgets, prepare follow-ups, install embeds, and connect to fnlowl's hosted MCP service.
Key features
- 01Build and diagnose capture widgets
- 02Review leads and funnel analytics
- 03Draft and review email sequences
- 04Install embeds on supported site platforms
- 05Connect agents to the remote MCP service
Use cases
- 01Create or troubleshoot a quiz widget
- 02Review widget conversion performance
- 03Draft a lead nurture sequence
- 04Install a widget embed on a website
MCP support
The package includes `.mcp.json` for connecting to fnlowl's hosted remote MCP server at `https://api.fnlowl.com/v1/mcp`. The server uses OAuth and does not provide campaign or transactional email sending tools.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.fnlowl.com/v1/mcpclaude mcp add --transport http com-fnlowl-fnlowl https://api.fnlowl.com/v1/mcp{"mcpServers":{"com-fnlowl-fnlowl":{"type":"http","url":"https://api.fnlowl.com/v1/mcp"}}}Open in Cursor{"servers":{"com-fnlowl-fnlowl":{"type":"http","url":"https://api.fnlowl.com/v1/mcp"}}}Open in VS Code{"mcpServers":{"com-fnlowl-fnlowl":{"type":"http","url":"https://api.fnlowl.com/v1/mcp"}}}{"mcpServers":{"com-fnlowl-fnlowl":{"serverUrl":"https://api.fnlowl.com/v1/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project README@fnlowl/skills
Agent skills for operating fnlowl (pronounced Funnel Owl — Funnel Intelligence, Agentified!) — lead-capture widgets, the leads they produce, and the mail that follows.
Four skills:
fnlowl-capture— build and diagnose widgets, leads, and funnel analytics.fnlowl-follow-up-automation— draft and review delivery, integration handoff, campaigns, and sequences.fnlowl-installation— install embeds on generic sites, WordPress, Shopify, Webflow, and Framer.fnlowl-mcp— connect an agent to the remote MCP surface safely.
Read them in skills/.
Install
npx skills add fnlowl/skills --list
npx skills add fnlowl/skills --global --agent claude-code
npx skills add fnlowl/skills --global --agent claude-code --skill fnlowl-capture
npx skills add fnlowl/skills --global --agent claude-code --skill fnlowl-follow-up-automation
npx skills add fnlowl/skills --global --agent claude-code --skill fnlowl-installation
npx skills add fnlowl/skills --global --agent claude-code --skill fnlowl-mcp
Name your agent with --agent (for example claude-code, codex or cursor). Without it, a
non-interactive run (--yes) installs into every agent the installer supports.
Install from npm
npm i -D fnlowl-skills
npx skills experimental_sync --agent claude-code
The package is fnlowl-skills. The sync links the four skills from node_modules into your project's agent folder; name your agent with --agent.
Pin a release
Releases are tagged on GitHub. For a stable install, pin a tag instead of the default branch:
npx skills add fnlowl/skills#v0.1.0 --global --agent claude-code
The skills are versioned together as one bundle. A release that renames or removes a skill says so in its notes.
Install as a Claude Code plugin
The repo is also a plugin marketplace, so Claude Code can install it directly:
/plugin marketplace add fnlowl/skills
/plugin install fnlowl@fnlowl-plugins
How to invoke skills
| Platform | Typical invocation |
|---|---|
| Claude Code | /fnlowl-capture, /fnlowl-follow-up-automation, /fnlowl-installation, /fnlowl-mcp |
| Cursor | the same names after typing / in Agent chat |
| Codex | describe the task, or $fnlowl-capture and the other skill names |
Verify install
Try a task that should trigger one of the skills:
- "Create a quiz widget for my pricing page."
- "Why is this widget not converting?"
- "Draft a three-email nurture sequence for people who finish the quiz."
- "Add the fnlowl widget to my WordPress site."
- "Connect Claude to fnlowl and list the tools it can use."
What's included
- four skills that load when relevant
- reference files and recipes for the capture and follow-up skills
.mcp.json, which points an agent at the hosted MCP server (OAuth sign-in on first use)
It does not ship slash commands or an MCP server of its own; the server runs at https://api.fnlowl.com/v1/mcp.
Use it
The MCP server is at https://api.fnlowl.com/v1/mcp (streamable HTTP, OAuth). .mcp.json in
this package points there. Your client opens fnlowl's consent screen the first time: sign in and
approve the scopes and website. Tokens are fnla_, revocable under Settings → API →
Connected apps; a connector limited to one website is already project-bound, so x-fnlowl-project is
ignored.
Claude.ai and ChatGPT work the same way: add the URL as a custom connector (OAuth, leave client id and secret blank).
For scripts and the CLI you can use an API key from Settings → API instead. It starts fnlk_,
is shown once, and is sent as Authorization: Bearer fnlk_....
Scope a call to one project with the project argument, or set a default with
the x-fnlowl-project header. list_projects returns the ids.
What it will not do
The remote MCP surface has no campaign or transactional send tool and cannot unsubscribe anyone. Publishing widgets and activating sequences are separate confirmation-required actions; the server cannot verify that conversational confirmation. High-risk Composio connection/action tools are withheld when that optional integration is configured. See references/approval-model.md.
Develop
node scripts/check-skills.mjs
Markdown and JSON, no dependencies — Node 18 or later. The one rule is describe only what is built, and a limitation goes in references/known-gaps.md rather than being left out.
The package also includes Codex, Claude, Cursor, and agent-marketplace plugin manifests.
License
MIT — see LICENSE.
Repository layout
LICENSE
.agents/plugins/marketplace.json
.claude-plugin/marketplace.json
.claude-plugin/plugin.json
.codex-plugin/plugin.json
.cursor-plugin/plugin.json
.github/workflows/validate.yml
assets/logo.svg
skills/
install.sh
Comments
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.