Mcp Media Inbox Triage logo

Mcp Media Inbox Triage

Organization
zapier
mcp-media-inbox-triage

Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.

Overview

Publisherzapier
Repositorygtm-cheat-codes
Skill namemcp-media-inbox-triage
Stars
349
Forks
21
Bundled files
4
LicenseMIT
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.

  • 4 bundled files

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

  • Open source

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

Installation

Install the Mcp Media Inbox Triage 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/zapier/gtm-cheat-codes/tree/main/skills/marketing/mcp-media-inbox-triage
  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/zapier/gtm-cheat-codes.git /tmp/gtm-cheat-codes
mkdir -p .claude/skills
cp -r /tmp/gtm-cheat-codes/skills/marketing/mcp-media-inbox-triage .claude/skills/mcp-media-inbox-triage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mcp Media Inbox Triage 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 Mcp Media Inbox Triage 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 Mcp Media Inbox Triage 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.

MCP Media Inbox Triage

Use this skill when a marketing, PR, community, or partnerships team needs a lightweight triage layer for a shared Gmail inbox.

What This Skill Does

  1. Searches a configured Gmail inbox or label in a bounded window.
  2. Reads only the message context needed for classification.
  3. Classifies each message as media request, partnership inquiry, customer/community lead, urgent executive risk, vendor pitch, spam/no action, or unclear.
  4. Scores urgency and recommends the right owner.
  5. Routes relevant requests to Slack, Google Sheets, or a triage doc.
  6. Drafts suggested replies only for human review.

When You Need This Pattern

  • A shared inbox mixes press requests, creator pitches, partnership notes, customer signals, newsletters, and vendor spam.
  • One person spends time each week skimming every email just to find the real asks.
  • The team needs human review before any reply is sent.
  • The team already works in Gmail, Slack, and Google Sheets.
  • You want a practical Zapier MCP workflow that saves attention, not just time.

Architecture

text
Shared Gmail inbox
  -> Zapier MCP Gmail search and read
  -> AI classification
  -> Slack summary, Google Sheets triage log, or Gmail draft

Required Connections Through Zapier MCP

  • Gmail: search and read messages from the shared inbox.
  • Slack: post triage summaries or urgent alerts.
  • Google Sheets: append a persistent triage log.
  • LLM: classify and summarize.

Optional:

  • Google Docs: create a weekly media-request digest.
  • Google Calendar: check deadline windows or schedule follow-ups.
  • CRM or advocacy database: match senders to known customers, partners, or advocates.

Core Workflow

1. Define The Inbox Window

Start with a bounded search:

text
to:{SHARED_INBOX} newer_than:7d -label:triaged

Adjust the inbox address, label, and time window for your team.

2. Pull Minimal Email Context

For each candidate message, read only:

FieldWhy
Sender name and emailIdentify source and possible owner
SubjectFast classification signal
Date receivedUrgency and SLA
Plain-text bodyExtract the ask
Thread countSpot follow-ups and repeated requests
Gmail thread linkSource of truth

Do not dump full email bodies into Slack.

3. Classify The Request

CategorySignalDefault action
Media requestJournalist, publication, interview, quote, deadlineRoute to PR or comms
Partnership inquiryCo-marketing, integration, affiliate, event, sponsorshipRoute to partnerships or marketing
Customer/community leadCustomer story, testimonial, community invite, user feedbackRoute to advocacy or community
Urgent executive riskLegal threat, brand risk, sensitive complaint, public escalationAlert owner immediately
Vendor pitchAgency, list purchase, ad buy, unrelated service offerLog or ignore
Spam/no actionGeneric blast, irrelevant outreach, phishing indicatorsArchive or leave unassigned
UnclearNot enough context to decideSend to human review

4. Score Urgency

UrgencySignalsResponse target
HighDeadline within 48 hours, named journalist, public brand risk, customer escalationSame day
MediumSpecific ask, relevant sender, no immediate deadlineTwo business days
LowUseful but exploratory, vague timing, non-criticalWeekly batch
IgnoreSpam, irrelevant vendor pitch, duplicateNo response

5. Output The Summary

text
Media inbox triage: 14 messages scanned, 4 need action

High urgency
- Jane Lee, TechWeekly: asks for comment on AI workflow story by Friday.
  Owner: PR
  Suggested action: reply with availability and approved spokesperson.
  Source: Gmail thread link

Ignored
- 8 vendor pitches
- 2 unrelated newsletters

Google Sheets Log

ColumnPurpose
received_atMessage timestamp
sender_nameHuman-readable sender
sender_email_domainDomain only if privacy matters
subjectEmail subject
categoryClassification
urgencyHigh / Medium / Low / Ignore
summaryOne-sentence ask
suggested_ownerTeam or person
suggested_next_actionConcrete next step
gmail_thread_linkSource link
statusNew / Routed / Done / Ignored

Classification Prompt

text
You are triaging a shared media inbox.

Classify this email for a human team. Do not draft a reply unless the email needs action.

Return JSON:
{
  "category": "media_request|partnership_inquiry|customer_community_lead|urgent_executive_risk|vendor_pitch|spam_no_action|unclear",
  "urgency": "high|medium|low|ignore",
  "sender_name": "string or unknown",
  "sender_org": "string or unknown",
  "deadline": "string or null",
  "summary": "One sentence describing the actual ask",
  "why_it_matters": "One sentence explaining relevance",
  "suggested_owner": "PR|Community|Marketing|Partnerships|Support|Leadership|Human review|Ignore",
  "suggested_next_action": "Concrete next action",
  "draft_reply_needed": true,
  "confidence": "high|medium|low"
}

Rules:
- Do not expose private email content in team channels.
- If the message is vague, classify as unclear.
- If the message is a generic vendor pitch, classify as vendor_pitch or spam_no_action.
- If the message mentions legal risk, public complaint, a journalist deadline, or a customer escalation, mark high urgency.

Zapier MCP And SDK Role

  • Use Zapier MCP to search Gmail, read message context, post Slack summaries, append Google Sheets rows, and create Gmail drafts when approved.
  • Use Zapier SDK for recurring runs, owner routing, retry handling, status logging, follow-up reminders, and weekly reporting when the workflow becomes productionized.

Guardrails

  • Never auto-send replies.
  • Do not expose full private email threads in Slack.
  • Keep Gmail thread links as the source of truth.
  • Route uncertain messages to a human.
  • Treat generic vendor pitches as vendor_pitch or spam_no_action unless there is a specific relevant ask.
  • Keep ignored messages auditable during tuning.

Inspired By

Generalized from Matt Canning and NoPlex. The reference workflow uses Zapier MCP and Gmail to reduce media inbox review from about 4 hours per week to about 15 minutes.

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 Mcp Media Inbox Triage AI skill do?

Find media, partnership, and high-intent requests buried in a shared Gmail inbox, summarize the useful ones, and route them to the right owner through Zapier MCP.

Why use Mcp Media Inbox Triage on TypingMind?

Because you install it once and use it with any model. Mcp Media Inbox Triage 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 Mcp Media Inbox Triage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zapier/gtm-cheat-codes/tree/main/skills/marketing/mcp-media-inbox-triage. 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 Mcp Media Inbox Triage?

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 Mcp Media Inbox Triage?

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

Is the Mcp Media Inbox Triage AI skill free?

Yes. It is published on GitHub by zapier under the MIT 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 👇