Pipefy Members Email Webhooks logo

Pipefy Members Email Webhooks

Organization
pipefy
pipefy-members-email-webhooks

Use this skill when the user wants to manage pipe membership, send or read card inbox emails, use email templates, or manage webhooks.

Overview

Publisherpipefy
Repositoryai-toolkit
Skill namepipefy-members-email-webhooks
Stars
52
Forks
24
Bundled files
2
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by pipefy on GitHub. Read the source before you install it.

Installation

Install the Pipefy Members Email Webhooks AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pipefy/ai-toolkit/tree/main/plugins/pipefy/skills/pipefy-members-email-webhooks
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pipefy/ai-toolkit.git /tmp/ai-toolkit
mkdir -p .claude/skills
cp -r /tmp/ai-toolkit/plugins/pipefy/skills/pipefy-members-email-webhooks .claude/skills/pipefy-members-email-webhooks
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pipefy Members Email Webhooks in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pipefy Members Email Webhooks on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pipefy Members Email Webhooks is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Members, Email & Webhooks

MCP clients: read references/mcp.md. CLI users: read references/cli.md. Examples below describe shared operation arguments.

Manage pipe membership, send emails from card inboxes, read inbox replies, and manage webhooks.


Member management

OperationRead-onlyPurpose
invite_membersNoInvite one or more users by email + role.
add_service_account_to_pipeNoAttach an existing org service account to a pipe by email + role (iPaaS setup). Check membership afterwards.
remove_member_from_pipeNoDestructive; review and approve first. Check afterwards: org-level permissions can override pipe removal.
set_roleNoChange a member's pipe role (member_id = user id).

List existing members with get_pipe_members from pipefy-pipes-and-cards. Id forms: docs/mcp/tools/identifiers.md#members-email-webhooks.

Steps — invite members

  1. Check existing members:

    Operation: get_pipe_members(pipe_id=67890)

  2. Invite new members:

    Operation: invite_members(pipe_id=67890, members='[{"email":"alice@example.com","role_name":"member"},{"email":"bob@example.com","role_name":"admin"}]')

    Before inviting external emails (domain different from the org's known domains), warn the user that this is an external invitation and confirm before proceeding.

    Before granting admin role, confirm with the user — admin is the highest pipe-level role.

Steps — add a service account to a pipe (iPaaS setup)

When setting up an iPaaS (Advanced Automations) flow that runs under a service account, the account must be a member of the target pipe, or pipe-scoped calls under its identity fail with a permission error even though the flow looks configured.

  1. Get the service account's email. Either create one with create_service_account(organization_uuid, name, role) — which returns the account's email plus its OAuth2 client secret and token endpoint once (store them immediately) — or take the email from your organization's service-account settings. A freshly created account has no pipe access until this step. The pipe role defaults to admin (a service account running automations usually needs full pipe access); pass a narrower role only when you deliberately want to limit it.

    One-step alternative: create_service_account(organization_uuid, name, role, pipe_ids=[...]) provisions the account and adds it to the given pipes in one call, returning a pipe_memberships summary. Use it when you already know the target pipes.

  2. Attach it (when not using the pipe_ids shortcut above):

    Operation: add_service_account_to_pipe(pipe_id=67890, email=svc-automations@your-org.pipefy-service.com) (role defaults to admin)

    This attaches an existing service account — create one first with create_service_account if needed. Delete a throwaway account after approval when done. See docs/mcp/tools/service-accounts.md.


Email (card inbox)

OperationRead-onlyPurpose
get_card_inbox_emailsYesRead emails in a card's inbox.
send_inbox_emailNoSend an email from a card inbox. Two-step: preview, then confirm.
get_email_templatesYesList templates for a pipe or table (repo_id numeric).
send_email_with_templateNoSend using a template (email_template_id from that list). Two-step: preview, then confirm.

Confirm every send. Both send operations deliver mail outside Pipefy, often to external addresses, and a sent email cannot be recalled. The first call sends nothing: it returns the message under email (to, subject, body, from_, and cc / bcc under extra when set) with a confirmation_token. Show the user the recipients, the subject and the body from that preview; for send_email_with_template, also name the template. The preview is the template already resolved for the card, so it shows the real recipients even when the template's toEmail is a {{...}} placeholder. After the user approves, repeat the same call with confirm=true and that confirmation_token. The token covers that one message: changing any argument, or a card edit that changes what the template resolves to, returns a fresh preview instead of sending. The template's ccEmail / bccEmail are not sent: to copy someone, pass cc / bcc in the send call. One confirmation covers one send: a request covering several cards still needs a confirmation per email, never one approval for a loop. The token stays valid for its TTL, so repeating the confirmed call sends the email again. If step 2 errors or times out, list the card's sent mail with get_card_inbox_emails(email_type='sent') before retrying, and never blind-retry a send. On the CLI, a send without --yes prints the email and exits 2; add --yes only after approval.

Templates are UI-only. Creating, editing and deleting an email template has no API, MCP or CLI path: the GraphQL schema has no template CRUD mutation. The template must already exist before a flow can send with it. When the process needs a new or changed template, put the manual Pipefy UI step in the plan you give the user instead of promising an end-to-end email flow.

Steps — send a card inbox email

  1. Get the card's inbox emails (see what has been received):

    Operation: get_card_inbox_emails(card_id=12345)

  2. Preview the reply (sends nothing):

    Operation: send_inbox_email(card_id=12345, to=["customer@example.com"], from_="you@example.com", subject="Your request is in progress", body="Hi, we are processing your request.")

    to is a list of addresses, and from_ (the sender address) is required. Show the user the returned email and wait for their approval.

  3. Send the reply (only after approval): repeat the same call with confirm=true and the confirmation_token from step 2.


Webhooks

OperationRead-onlyPurpose
get_webhooksYesList all webhooks for a pipe.
create_webhookNoRegister a new webhook endpoint.
update_webhookNoChange URL, headers, or events.
delete_webhookNoDestructive; review and approve first.

Header values are secrets. get_webhooks returns each webhook's headers unmasked, and they usually hold authorization tokens or API keys. In a reply, name only the header keys (for example Authorization, X-Api-Key), never their values, even when the user asks for them. A lost token comes back from the system that issued it; to replace it, set a new value with update_webhook. update_webhook replaces the whole headers object, so send every header from get_webhooks and change only the lost one, or the others are deleted. An update that leaves headers out deletes them all, so a change to only the URL, name or events must resend the headers too.

Steps — create a webhook

  1. List existing webhooks:

    Operation: get_webhooks(pipe_id=67890)

  2. Create the webhook:

    Operation: create_webhook(pipe_id=67890, url="https://your-server.com/pipefy", actions='["card.create","card.done"]')


Success criteria

  • Invited members appear in get_pipe_members.
  • Sent emails show in the card's inbox thread.
  • Created webhooks receive test payloads from Pipefy on the configured events.

Failure modes

  • invite_members fails with "user not found": verify the email address is correct.
  • send_inbox_email fails: the card must have an inbox enabled in the pipe settings.
  • Webhook never fires: verify the pipe events match the configured actions list; check that the endpoint URL is publicly reachable (not localhost).
  • Deletion: review the affected webhook or member and obtain approval before removal.

See also

  • pipefy-pipes-and-cards — create the pipe and cards before managing membership.
  • pipefy-observability — monitor email and webhook delivery logs.
  • pipefy-ipaas — when a flow's service account needs pipe membership.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Pipefy Members Email Webhooks AI skill do?

Use this skill when the user wants to manage pipe membership, send or read card inbox emails, use email templates, or manage webhooks.

Why use Pipefy Members Email Webhooks on TypingMind?

Because you install it once and use it with any model. Pipefy Members Email Webhooks is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pipefy Members Email Webhooks in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pipefy/ai-toolkit/tree/main/plugins/pipefy/skills/pipefy-members-email-webhooks. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Pipefy Members Email Webhooks?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pipefy Members Email Webhooks?

As many as you like. As long as a model supports skills, you can use Pipefy Members Email Webhooks with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pipefy Members Email Webhooks AI skill free?

Yes. It is published on GitHub by pipefy under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇