CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
pofky avatar

Appstore Connect Mcp

pofky/appstore-connect-mcp
authSTDIOregistry active
Summary

Connects your MCP client to the App Store Connect API with eleven focused tools instead of raw endpoint sprawl. You get review status checks, customer review filtering by rating and territory, sales report downloads, and two sampling-based tools that use your own client's model to triage reviews into themes and draft localized responses. Ships with three slash-command prompts for morning briefings, rejection audits, and release go/no-go workflows, plus an optional Claude skill that auto-routes review questions. Authentication requires an App Store Connect API key with App Manager role. Most useful when you're juggling multiple apps and want review signals and sales data without opening the portal.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →

asc-mcp

Ship an App Store release from your coding agent. An MCP server for App Store Connect: 41 tools that edit version metadata, upload screenshots, attach builds, drive TestFlight, create in-app purchases, submit and release, plus an intelligence layer that audits a version before you submit and summarizes your reviews. 6 slash-command workflows and a bundled Claude Skill. Not another API wrapper.

asc-mcp.pages.dev · npm · Pricing: 7-day free trial, then $9/month

Claude Desktop, one click: download the latest asc-mcp.mcpb and open it. Claude asks for your Issuer ID and lets you pick your .p8 with a file picker. No JSON, no restart hunt.

Everything else (Claude Code, Cursor, Windsurf, Cline), one command:

npx @pofky/asc-mcp init --write   # finds your .p8, asks for your Issuer ID, writes your MCP config

Then ask your agent: "start my asc-mcp trial, my email is you@example.com". All 41 tools unlock for 7 days, no card and nothing to cancel, and the trial activates in the session you are already in, so whatever you were blocked on works on the very next call. After that Pro is $9 a month. Six tools stay free, and three of those need nothing but Node.

You sayWhat happens
"Run a preflight check on my app"Audits metadata, character limits, screenshots, build status. Catches the issues that cause 40% of rejections.
"Give me a morning briefing"Summarizes all your apps: who's in review, who got rejected, new low-rating reviews, action items.
"Generate release notes from my git history"Reads commits since last tag, categorizes them, and gives you structured data to write "What's New" text.
"Is my app in review?"Exact review state with context ("typical time: 24-48 hours")
"Show me 1-star reviews"Customer reviews filtered by rating, territory, sorted by date
"What were my downloads this week?"Sales and revenue summary by territory

No context switching. No portal. Just ask.

What Makes This Different

Maintained successor to JoshuaRileyDev/app-store-connect-mcp-server (archived Feb 2026). Different angle, same API surface plus more.

Other ASC MCP servers wrap the API and give you 80 to 982 raw endpoints. This one gives you 41 opinionated tools, 6 slash-command Prompts, and a Claude Skill that all think. The read tools summarize and audit; the Pro control tools actually drive App Store Connect, from editing metadata to submitting and releasing, with the same API key. Two tools use MCP Sampling: your own client's model does the LLM work, so there is no extra cost from this server.

Why full control is possible without fastlane: fastlane's deliver and pilot are just calls to the same App Store Connect REST API this server authenticates against with your .p8. So nearly everything you would script with fastlane is a tool here, no Ruby toolchain required. The only step that needs your Mac is building and signing the binary, which build_and_archive and upload_binary drive via Xcode.

Setup (3 minutes)

Step 1. Create an API key in App Store Connect > Integrations > App Store Connect API (Admin or App Manager role), then grab three things from that same page:

  • Issuer ID (ASC_ISSUER_ID): the UUID shown at the top of the page, with a copy button next to it.
  • Key ID (ASC_KEY_ID): the 10-character ID next to your key, also in the filename AuthKey_XXXXXXXXXX.p8.
  • .p8 file (ASC_PRIVATE_KEY_PATH): click Download and point this at the saved file. Apple lets you download it only once, so keep it safe.

Step 2. Install:

npm install -g @pofky/asc-mcp

No global install needed if you prefer npx (see the manual config below).

Fastest setup (recommended). Drop your .p8 into Apple's standard path ~/.appstoreconnect/private_keys/ (the file is named AuthKey_XXXXXXXXXX.p8, and the Key ID is in the filename). Then run:

npx @pofky/asc-mcp init --write     # auto-detects the key, asks for your Issuer ID, and writes the config for you
# or: npx @pofky/asc-mcp init       # same, but prints the block to paste yourself

init --write finds your Claude Desktop / Claude Code config, backs it up, and merges in the server block, so there's no JSON editing. The server also auto-discovers the .p8 path at runtime, so you only ever need ASC_ISSUER_ID (and ASC_LICENSE_KEY for Pro).

Running it from an agent, or any pipe. There is no terminal to answer questions in, so pass what would have been asked:

npx @pofky/asc-mcp init --write --issuer <your-issuer-uuid>   # add --config <path> if you keep several client configs

It prints the paste-ready block either way, and it never invents a value: if the Issuer ID is missing it says so instead of writing a config that fails at Apple's auth. --key-path, --key-id and --license are there for the same reason, and every one of them also reads from the matching ASC_* environment variable.

Stuck? Run npx @pofky/asc-mcp doctor (or ask your agent to call asc_setup_check). It checks your key, Issuer ID, a live connection to App Store Connect, and your license, and prints the exact fix for anything wrong. In your agent, the /asc-start command walks a first-time user through all of this.

Manual setup. Add to your agent's MCP config (Claude Desktop config, or ~/.claude.json for Claude Code). Use npx for zero-install, or asc-mcp if you installed globally:

{
  "mcpServers": {
    "appstore-connect": {
      "command": "npx",
      "args": ["-y", "@pofky/asc-mcp"],
      "env": {
        "ASC_ISSUER_ID": "YOUR_ISSUER_ID"
      }
    }
  }
}

With the .p8 in ~/.appstoreconnect/private_keys/, ASC_ISSUER_ID is the only required env var (Key ID and key path are auto-detected). Add ASC_LICENSE_KEY to unlock Pro.

Step 3. Ask your agent: "List my App Store Connect apps"

Step 4, to try the paid half. Ask your agent: "start my asc-mcp trial, my email is you@example.com". It calls asc_start_trial, which unlocks all 41 tools for 7 days with no card and nothing to cancel. The key activates in the running session, so whatever you were blocked on works on the very next call, and it is written into your MCP config so it survives a restart. One trial per Apple developer account.

Works with Claude Code, Cursor, Windsurf, Cline, and any MCP-compatible client.

Tools

Free (no signup, no license key)

ToolWhat it does
asc_start_trial7 days of everything, no card. Ask your agent to run it with your email. Unlocks all 41 tools in the running session, no restart, nothing to cancel.
asc_setup_checkRun first if anything's off. Checks your key, Issuer ID, a live App Store Connect connection, and license tier, and prints the exact fix for each failure.
asc_guideStart here. The in-agent playbook for every flow (first release, update, IAP, subscriptions, reviews, TestFlight, binary), with each manual App Store Connect website step flagged inline. See also USER_GUIDE.md and LIMITATIONS.md.
list_appsList all your apps with name, bundle ID, SKU and App ID
app_detailsVersion history, build status, release state, dates
review_statusCurrent review state with human-readable context

Pro (free 7-day trial, then $9/month)

ToolWhat it doesWhy it matters
list_reviewsCustomer reviews filtered by rating, territory, sort orderSee what users say without opening the portal
sales_reportDaily/weekly/monthly downloads and revenue by territoryKnow your numbers instantly
release_preflightPre-submission audit: metadata, char limits, screenshots, buildsCatches 40%+ of common rejection causes before you submit
daily_briefingMorning summary across all apps: status, reviews, rejectionsOne call replaces 10 minutes of portal clicking
release_notesGit commits since last tag, categorized for writing "What's New"Your AI agent writes release notes from your actual changes
keyword_insightsAnalyze keywords against iTunes search competition, difficulty ratingsSee which keywords are worth targeting at a glance
competitor_snapshotLook up any app: ratings, reviews, version, price, release notesCompetitive intelligence without leaving your editor
metadata_diffCompare live vs pending version metadata across all localesVerify exactly what changed before submitting
triage_reviewsPulls recent reviews and clusters them into 3 to 5 themes with counts, action buckets, and quotes, using MCP SamplingZero extra cost: your client's model does the clustering
draft_review_responseDrafts a public reply to a single review in the review's locale, via Sampling. Elicits tone if your client supports it. Never auto-posts.Apple guideline 1.2 respected; you paste into ASC yourself

Control & Ship (Pro)

These tools write to App Store Connect. Every outward-facing action (submit, release, upload binary) requires an explicit confirm: true, so nothing leaves your machine by accident.

ToolWhat it does
create_versionCreate a new editable App Store version for your next release
update_version_metadataEdit description, keywords, what's-new, promo text, URLs, app name, subtitle. Validates Apple's character limits and refuses over-limit writes
upload_screenshotsUpload screenshots for a device display type (reserve, upload, commit, with checksum)
list_buildsList recent builds and their processing state (VALID = ready)
wait_for_buildPoll until a build finishes processing, so the chain does not need a manual pause
attach_buildAttach a build to the editable version (defaults to newest processed build)
submit_for_reviewSubmit the version to App Review (modern reviewSubmissions flow). confirm: true required
release_versionRelease an approved version to the public App Store. confirm: true required
manage_phased_releaseStart, pause, resume, or complete the 7-day phased rollout
list_beta_groupsList your TestFlight beta groups
assign_build_to_groupPush a build to a beta group so testers can install it
invite_beta_testerInvite an external tester by email and add them to a group
set_app_metadataSet primary/secondary category, copyright, content-rights, and export-compliance (encryption) in one call
set_app_priceSet the base price by creating the price schedule (price_usd: 0 for free), auto-equalized to all territories
set_app_availabilityMake the app available in all App Store territories (or a subset), with auto-include for future ones
set_review_contactSet the App Review contact and optional demo account on the version
set_age_ratingSet the v2 age-rating declaration (full content-descriptor set)
set_privacy_nutritionGuidance + deep link for the App Privacy nutrition labels (not API-addressable)
set_eu_trader_statusGuidance + deep link for the EU DSA trader status (not API-addressable)
create_iapCreate a non-consumable/consumable IAP with localization, availability, and an auto-equalized price
create_subscriptionCreate a subscription group, sub, localization, availability, price, and free trial
set_iap_review_screenshotAttach the App Review screenshot to a subscription or IAP
setup_app_store_signingDownload the app's App Store provisioning profiles and write a manual-signing ExportOptions.plist (works with a least-privilege API key)
build_and_archiveBuild, archive, and export a signed .ipa via xcodebuild (needs Xcode on your Mac)
upload_binaryUpload the .ipa to App Store Connect via altool, using your API key. confirm: true required

The whole flow chains: setup_app_store_signing to build_and_archive to upload_binary to wait_for_build (blocks until VALID) to attach_build to update_version_metadata to upload_screenshots to set_app_metadata/set_app_price/set_app_availability/set_age_rating/set_review_contact to release_preflight to submit_for_review to release_version. The /asc-ship-release slash command drives it for you.

release_preflight is the single source of truth for "is this submittable": it checks every API-addressable field and ends with a tailored "Manual steps to finish" list for the few things Apple only allows in the website (first-IAP bundling, App Privacy nutrition labels, EU trader status).

Get Pro | Retrieve your license key

What stays manual (and why)

A handful of things Apple does not expose to API keys. The MCP never pretends otherwise: it either returns the exact website steps plus a deep link, or detects the case and aborts so nothing is half-done. Full detail in LIMITATIONS.md (and asc_guide topic:limitations):

  • Create an app record / App Group. POST /v1/apps is forbidden for API keys; do it once in the website.
  • App Privacy nutrition label. Not in the API. set_privacy_nutrition returns the checklist plus a deep link.
  • EU DSA trader status. Not in the API. set_eu_trader_status returns the steps. Legal decision.
  • An app's first IAPs/subscriptions. Must be submitted with the version in the website; submit_for_review aborts rather than orphan the version. Later products submit via the API.
  • Certificate creation / cloud signing. Least-privilege keys can't; setup_app_store_signing uses manual-signing profiles instead.
  • Compiling the binary. Needs Xcode on your Mac (build_and_archive runs it locally).
  • Posting a public review reply. draft_review_response writes it; you paste it in the website.

How Sampling works (zero extra cost)

triage_reviews and draft_review_response use the MCP Sampling primitive. When you call one of these tools, this server sends a sampling/createMessage request back to your own MCP client. Your client runs the LLM locally (Claude Desktop uses your account; Claude Code uses its session). We never call Anthropic from our side.

Outcome: review clustering and reply drafting cost you exactly what you would pay for any other Claude request, not a penny more from this server.

If your MCP client does not support Sampling yet, both tools return a structured degraded: true result with a clear explanation. Upgrade Claude Desktop or Claude Code to a recent version for full functionality.

Slash Commands (Prompts)

Type these in Claude Desktop or Claude Code and the agent runs a pre-built multi-tool workflow:

Slash commandWhat it does
/asc-startNew here? Verifies the connection, lists your apps, explains free vs Pro in plain language, and recommends your next step. No App Store Connect knowledge assumed.
/asc-weekly-reviewCalls daily_briefing then list_reviews (low-rating, last 7 days) for every app, clusters themes, returns a single digest with 3-bullet action list.
/asc-rejection-auditGiven an app_id, calls release_preflight + metadata_diff + review_status, reads the result against the top 2026 rejection drivers (guideline 2.3 metadata, 4.0 design, privacy-AI 5.1.2). Produces Blocking / Likely-flagged / Safe sections.
/asc-release-go-no-goGiven an app_id, combines preflight + review queue + metadata diff + top competitors in the same category. Returns a direct GO or NO-GO with three supporting reasons.
/asc-ship-releaseGiven an app_id, drives the full release: locate or create the editable version, push metadata, attach the newest build, upload screenshots, run preflight, then submit. Stops to confirm before every outward-facing step.
/asc-first-appGiven an app_id, drives a brand-new app's first 1.0 from existing app record to submitted, handling every first-time-only constraint and stopping at each manual website step (privacy label, trader status, first-IAP bundling).

These are MCP Prompts per the spec. Zero other App Store Connect MCP ships with them.

Claude Skill (one-line install)

After installing the MCP, run:

npx @pofky/asc-mcp install-skill

This copies a small asc-review-triage Skill to ~/.claude/skills/ so Claude automatically picks up review-related questions ("any bad reviews lately?", "what do my users say?", "ratings this week?") and calls the right ASC tools without you having to explain the workflow each time.

Works on macOS, Linux, and Windows. To remove: npx @pofky/asc-mcp uninstall-skill.

Real Output Examples

"Run a preflight check before I submit"

Release Preflight: v2.3

State: PREPARE_FOR_SUBMISSION
Platform: IOS

PASS (with 1 warning)

Warnings (recommended):
- Missing screenshot set for APP_IPHONE_67. May be required.

Passing checks: 4
- [en-US] Description OK (3874/4000 chars).
- [en-US] Keywords OK (96/100 chars).
- 2 screenshot set(s) found across 1 locale(s).
- Build 40 attached and valid.

Total: 4 pass, 1 warn, 0 fail

"Morning briefing"

Daily Briefing - 2026-04-13

2 apps in your account

Tempo: Habit Builder
- Latest: v2.3 (IOS) - Waiting for Review
- Action needed: v2.3 is Waiting for Review
- Reviews (last 3d): 5 new, avg 4.2 stars

NightOwl Weather
- Latest: v1.1 (IOS) - Live
- No new reviews in the last 3 days

"Generate release notes from git"

Git History for Release Notes

Since: v2.2.0
Commits: 8
Character limit: 4000 chars for "What's New"

New Features (3)
- feat: add habit streak calendar view
- feat: dark mode support
- add widget for home screen

Bug Fixes (2)
- fix: notification timing off by 1 hour
- fix: crash on iPad when rotating

Instructions: Write user-facing "What's New" text.
Lead with the most impactful change. Keep under 4000 chars.

Why This One Over the Free Alternatives?

Raw API wrappers (free)This server
Tool count80 to 98241 opinionated tools (read + control)
MCP Prompts (slash commands)NoYes, 6 pre-built workflows
MCP Sampling (zero server-side LLM cost)NoYes, review triage + response drafts
Claude Skill bundledNoYes, one-line install
Pre-submission auditNoYes, catches rejections before you submit
Cross-app briefingsNoYes, one call, all apps
Git-aware release notesNoYes, reads your project's commit history
Smart review summariesNoYes, theme clustering, action items
SetupBuild from source (Swift or Node)One command, init --write writes your config
Free tierSomeYes, 6 tools, no signup. Three of them need nothing but Node
Try the paid halfn/a7 days, no card, started from inside your agent

Raw wrappers give you endpoints. This gives you answers.

Security

Your credentials never leave your machine:

  • The .p8 private key is read locally. JWT tokens are generated on your computer.
  • API calls go directly from your machine to api.appstoreconnect.apple.com.
  • The license server sees only your license key string. Zero Apple data, zero credentials.
  • Fully open source. Read the code.

Works With

  • Claude Code (Anthropic)
  • Cursor
  • Windsurf
  • Cline
  • Any client supporting the Model Context Protocol

Requirements

  • Node.js 18+
  • Apple Developer Program membership
  • App Store Connect API key (Admin or App Manager role)

Legal

  • Privacy Policy
  • Terms of Service

This project is not affiliated with, endorsed by, or sponsored by Apple Inc. Apple, App Store, App Store Connect, TestFlight, iOS, and macOS are trademarks of Apple Inc.

License

MIT

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →

Configuration

ASC_KEY_ID*

App Store Connect API Key ID (10-char alphanumeric from ASC portal)

ASC_ISSUER_ID*

App Store Connect Issuer ID (UUID from ASC portal)

ASC_PRIVATE_KEY_PATH*

Path to .p8 private key file downloaded from App Store Connect

ASC_LICENSE_KEYsecret

Pro license key for reviews and sales tools (optional, get at buy.polar.sh)

Categories
Sales & Marketing
Registryactive
Package@pofky/appstore-connect-mcp
TransportSTDIO
AuthRequired
UpdatedApr 13, 2026
View on GitHub

Related Sales & Marketing MCP Servers

View all →
potarix avatar
Potarix Enricher

potarix/potarix-mcp

Find company websites and verified business emails through the Potarix Enricher API.
promptfax avatar
promptfax

promptfax/promptfax

PromptFax is a pay-per-use remote MCP server that lets an AI assistant send a real fax to a US fax number. Your assistant uploads a PDF or image, enters the destination, reviews a quote, opens Stripe Checkout, and queues the transmission. Pricing is $2.00 for the first 5 pages, then $0.10 per page after that, capped at $4.50 for up to 35 pages. Payment is captured only after the fax is recorded as delivered. There is no PromptFax account, no subscription, and no API key to manage. PromptFax uses OAuth and Streamable HTTP, so users install once and their assistant can start a fax workflow when needed. Inside ChatGPT, PromptFax opens a connector widget that handles document review, destination entry, Stripe Checkout, and the delivery report. Inside Claude or other MCP hosts, PromptFax falls back to an agent-friendly hosted session page that handles the same flow without requiring the host to pass files directly. Every real send requires a user-reviewed quote and Stripe authorization. The assistant cannot silently complete a fax. The `send_fax` and `cancel` tools are marked as destructive so well-behaved MCP hosts can surface confirmation steps. ## Capabilities - Send outbound faxes to US fax numbers - Attach a PDF or image from the host, widget, hosted session page, or HTTPS URL - Generate a pay-per-use quote before payment - Open Stripe Checkout for payment authorization - Queue a paid fax for transmission - Check workflow, payment, and delivery status - Retry eligible failed faxes - Cancel an active send while cancellation is still possible ## Tools - `start_session` — Create or resume a PromptFax MCP session. - `attach_document` — Bind a PromptFax document or HTTPS PDF URLs to an MCP session. - `get_quote` — Create a fax quote from a session, document, or HTTPS PDF URL. - `checkout` — Open Stripe Checkout after the user accepts a quote. - `send_fax` — Queue a paid fax for transmission. - `get_status` — Fetch workflow, payment, and transmission status. - `retry_failed_fax` — Prepare a retry flow after a retry-eligible failed fax. - `cancel` — Cancel the active send while cancellation is still possible. ## Common use cases - Sending a one-off medical record, referral, or intake form to a clinic's fax line. - Returning a signed contract to a small business or law office that still operates by fax. - Sending insurance claim forms, prior-authorization paperwork, or appeal letters. - Sending a benefits or HR form to a payroll vendor that requires fax submission. - Sending court filings or notarized documents to a filing office. ## Data handling PromptFax does not require an email address, does not provision a PromptFax account, and stores uploaded documents only as long as the fax workflow needs them. Server-side working copies are deleted after transmission. The browser-local delivery report persists for up to 24 hours unless cleared sooner. PromptFax is outbound-only and currently supports US fax numbers only. Payments are processed by Stripe for Cogint Labs LLC. ## Links - Homepage: https://promptfax.app/ - MCP endpoint: https://promptfax.app/mcp - Setup docs: https://promptfax.app/mcp-setup - Tool catalog: https://promptfax.app/mcp-tools - Demo: https://promptfax.app/mcp-demo - Pricing: https://promptfax.app/pricing - Privacy: https://promptfax.app/privacy - Terms: https://promptfax.app/terms
promptfax avatar
promptfax

promptfax/promptfax-d2a8bd34

PromptFax is a pay-per-use remote MCP server that lets an AI assistant send a real fax to a US fax number. Your assistant uploads a PDF or image, enters the destination, reviews a quote, opens Stripe Checkout, and queues the transmission. Pricing is $2.00 for the first 5 pages, then $0.10 per page after that, capped at $4.50 for up to 35 pages. Payment is captured only after the fax is recorded as delivered. There is no PromptFax account, no subscription, and no API key to manage. PromptFax uses OAuth and Streamable HTTP, so users install once and their assistant can start a fax workflow when needed. Inside ChatGPT, PromptFax opens a connector widget that handles document review, destination entry, Stripe Checkout, and the delivery report. Inside Claude or other MCP hosts, PromptFax falls back to an agent-friendly hosted session page that handles the same flow without requiring the host to pass files directly. Every real send requires a user-reviewed quote and Stripe authorization. The assistant cannot silently complete a fax. The `send_fax` and `cancel` tools are marked as destructive so well-behaved MCP hosts can surface confirmation steps. ## Capabilities - Send outbound faxes to US fax numbers - Attach a PDF or image from the host, widget, hosted session page, or HTTPS URL - Generate a pay-per-use quote before payment - Open Stripe Checkout for payment authorization - Queue a paid fax for transmission - Check workflow, payment, and delivery status - Retry eligible failed faxes - Cancel an active send while cancellation is still possible ## Tools - `start_session` — Create or resume a PromptFax MCP session. - `attach_document` — Bind a PromptFax document or HTTPS PDF URLs to an MCP session. - `get_quote` — Create a fax quote from a session, document, or HTTPS PDF URL. - `checkout` — Open Stripe Checkout after the user accepts a quote. - `send_fax` — Queue a paid fax for transmission. - `get_status` — Fetch workflow, payment, and transmission status. - `retry_failed_fax` — Prepare a retry flow after a retry-eligible failed fax. - `cancel` — Cancel the active send while cancellation is still possible. ## Common use cases - Sending a one-off medical record, referral, or intake form to a clinic's fax line. - Returning a signed contract to a small business or law office that still operates by fax. - Sending insurance claim forms, prior-authorization paperwork, or appeal letters. - Sending a benefits or HR form to a payroll vendor that requires fax submission. - Sending court filings or notarized documents to a filing office. ## Data handling PromptFax does not require an email address, does not provision a PromptFax account, and stores uploaded documents only as long as the fax workflow needs them. Server-side working copies are deleted after transmission. The browser-local delivery report persists for up to 24 hours unless cleared sooner. PromptFax is outbound-only and currently supports US fax numbers only. Payments are processed by Stripe for Cogint Labs LLC. ## Links - Homepage: https://promptfax.app/ - MCP endpoint: https://promptfax.app/mcp - Setup docs: https://promptfax.app/mcp-setup - Tool catalog: https://promptfax.app/mcp-tools - Demo: https://promptfax.app/mcp-demo - Pricing: https://promptfax.app/pricing - Privacy: https://promptfax.app/privacy - Terms: https://promptfax.app/terms
purahmanian avatar
Junglescout Mcp

purahmanian/junglescout-mcp

Jungle Scout MCP server: keyword volumes, product database, sales estimates, share of voice
purahmanian avatar
Keepa Mcp

purahmanian/keepa-mcp

MCP server for Keepa Amazon price and sales rank history API
quadratik-ai avatar
Quadratik

quadratik-ai/quadratik

Search and manage 220M+ B2B contacts. Filter by title, industry, location, and more.