Paydirt MCP server
io.github.Paydirt-AI/paydirt-mcp·v2.3.0Agent-native installer and control plane for Paydirt iOS feedback
0 stars59 downloads/wk
Reviews
Write oneNobody has reviewed Paydirt yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Paydirt tools (23, 5 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
paydirt_add_feedback_formUse this when the user asks for a named feedback form at a screen, button, lifecycle moment, or in-app action. Creates or reuses a normalized-title match, preserves the placement verbatim, optionally resolves Slack, and returns exact Swift plus mandatory edit/build/test actions. Remote form creation alone is not completion.
paydirt_askUse this when the user asks a natural-language analytical question about their Paydirt feedback, such as pricing themes or feature requests. Reads actual responses and returns analysis without taking action.
paydirt_begin_setupUse this when installing Paydirt for a new user, machine, or iOS app. Inspect the host first. Without form_plan_confirmed, returns the concise cancellation/Suggest a Feature confirmation and does not start authorization. After confirmation, pass the selected use_cases and placement to receive authorization_url and finish_arguments immediately.
paydirt_connect_slackUse this when the user asks to connect Slack or repair Slack delivery after onboarding. Returns the Slack OAuth URL. Authorization provisions #paydirt-suggest-a-feature for feature forms and #paydirt-cancellations for trial and subscription cancellation forms, then assigns each form automatically when workspace policy allows it.
paydirt_create_appwrite actionUse this when the user explicitly needs a separate Paydirt app and setup cannot reuse or create it. Creates a new app; list existing apps first when duplication is possible.
paydirt_create_formwrite actionUse this when creating a low-level remote form without a host-app placement request. First confirm a matching form does not exist. Map subscription cancellation to cancellation, trial cancellation to trial_expiration, and regular feedback to custom; then wire the returned ID into iOS and assign Slack. Prefer paydirt_add_feedback_form for named screen or action placement.
paydirt_delete_formwrite actionUse this when the user explicitly asks to permanently delete a specific Paydirt form. This is destructive and should only be called after inspecting the form when its identity is uncertain.
paydirt_finish_setupUse this when the user has opened the authorization URL returned by paydirt_begin_setup. Checks one setup session and returns immediately. If pending, do not loop or sleep. When ready, securely saves credentials and returns the host-app build, visible verification, and post-verification delivery-choice contract.
paydirt_get_appUse this when the agent needs the current identity, bundle ID, SDK key, or configuration for one known Paydirt app. Does not modify the app.
paydirt_get_feedback_digestUse this when the user or a scheduled task needs a read-only daily or periodic Paydirt brief. Returns completed-response totals by feedback type, comparison with the previous equal period, and concise highlights. Never turn feedback into code changes or tasks automatically.
paydirt_get_formUse this when the agent needs the current prompt, type, enabled state, or Slack assignment for one known form. Does not modify the form.
paydirt_get_responsesUse this when the user or coding agent needs raw feedback conversations, exact Q/A turns, input type, subscription metadata, or a read-only inbox cursor. Defaults to completed conversations. Use since plus the newest updated_at for incremental reads; never take action from responses automatically.
paydirt_get_summaryUse this when the user asks for an aggregate AI summary of recent Paydirt responses. Raw questions and answers remain the source of truth; this read-only summary is supplementary.
paydirt_health_checkUse this when diagnosing whether the Paydirt API is reachable and stored authentication is valid. Performs a read-only connectivity check.
paydirt_list_appsUse this when the user asks which Paydirt apps exist or when an agent must resolve an app ID after setup. Lists all apps for the authenticated Paydirt account without changing them.
paydirt_list_formsUse this when the user asks which forms exist or the agent needs to resolve or deduplicate forms for a Paydirt app. Does not modify forms.
paydirt_list_slack_channelsUse this when Slack is connected and the agent must resolve a requested channel name to its channel ID. Lists available channels without changing assignments.
paydirt_set_form_channelUse this when a form must deliver completed conversations to a specific Slack channel ID. Replaces that form’s current channel assignment and should be verified afterward.
paydirt_setupUse this when an older client expects the single setup tool. Without session_id it starts setup and immediately returns authorization_url plus finish arguments; with session_id it checks once and returns pending, expired, or the complete installation contract. It never opens a browser or blocks. New agents should prefer paydirt_begin_setup and paydirt_finish_setup.
paydirt_slack_statusUse this when the developer selected Slack or combined delivery and completed authorization. Reports the Paydirt feedback channel and whether every installed form is assigned. Do not call it for agent-only delivery.
paydirt_toggle_formUse this when the user asks to enable or disable an existing form remotely. Disabled forms are not shown by the SDK; calling again with the opposite value reverses the change.
paydirt_update_appwrite actionUse this when the user asks to change an existing Paydirt app’s identity, bundle ID, description, or AI context. Only supplied fields are updated.
paydirt_update_formwrite actionUse this when the user asks to change an existing form’s name, initial question, or AI follow-up guidance. Only supplied fields are updated.
Public scan report
scanner v0.1.10 · 2026-11-03 · same rubric, same numbers if you re-run it
- Code scan10 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 18 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How Paydirt compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 88% of 4,460 AI and agents servers
- Tools
- 23
- the typical AI and agents server has 6
- Tools that change things
- 22%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 59
- more than 49% of 1,538 AI and agents servers with a package
What its tools let an agent do: 23 change
Install Paydirt in Claude Code, Cursor or VS Code
Runs npx -y paydirt-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add paydirt-mcp -- npx -y paydirt-mcp
What the publisher says
From the Paydirt repository's README, as published. We do not edit it. Read it on GitHub
Paydirt MCP
MCP Registry name: io.github.Paydirt-AI/paydirt-mcp
The agent-native installer and control plane for Paydirt, an iOS SDK for Suggest a Feature, trial cancellation, and subscription cancellation.
Paydirt MCP lets a coding agent create forms, place them in an iOS app, connect Slack, build and launch the host app, leave a Debug-only requested-form setup check open for immediate verification, and read raw feedback. Paydirt supports native StoreKit, RevenueCat, Superwall, app-owned billing, and apps without subscriptions.
A generic installation first confirms cancellation feedback and Suggest a Feature, then creates the selected forms after Google sign-in. Browser onboarding asks whether completed feedback should go to Slack and coding agents (recommended), Slack only, or coding agents only. The agent then builds and opens the requested-form setup check on a simulator or connected iPhone.
One browser flow, from either entry point
Paydirt provides voice-first cancellation feedback and voice Suggest a Feature forms for iOS, working with the app's existing RevenueCat or StoreKit setup and connected to Slack and coding agents.
form plan, and open the authorization URL from paydirtbeginsetup.
- Agent start: inspect the iOS project, use the developer's explicitly requested
their app, and connects Slack. They then receive an installation prompt with the prepared appid. Pass that ID to paydirtbegin_setup; never create a second app merely because setup began on the website.
- Website start: the developer signs in at https://www.paydirt.ai/setup, selects
delivery preferences and healthy Slack assignments are reused. Only request Slack authorization when missing, incomplete, or explicitly requested.
- In both paths, the human authorizes Paydirt and Slack in the browser. Existing
Continue in the same project and conversation using the exact app/form IDs. Preparing forms is not proof that the SDK is installed or delivery is verified.
- After authorization, paydirtfinishsetup returns the installation contract.
An explicit request to install specified forms counts as confirmation of that scope. Set formplanconfirmed: true; ask only about missing or ambiguous choices, not whether to repeat work already requested.
Example request:
Add Paydirt voice cancellation feedback and a voice Suggest a Feature form to
my iOS app. Use my existing RevenueCat or StoreKit setup, connect Slack during
browser authorization, then build and verify my app.
Install in Codex
codex mcp add paydirt -- npx --yes --prefer-online paydirt-mcp@latestAfter first registration, follow the refresh requested by your Codex client. Current Codex desktop builds may require you to quit and reopen Codex before a brand-new MCP server becomes visible. Return to the same task and ask:
Add Paydirt and show me it working.
This is a one-time Codex tool-discovery refresh, not a Paydirt authentication requirement. Once Paydirt is visible, Paydirt and Slack authorization do not require another restart. The already loaded paydirtbeginsetup and paydirtfinishsetup tools complete browser authorization in the same task and the same MCP process.
To remove the server later:
codex mcp remove paydirtInstall in Claude Code
claude mcp add paydirt -- npx --yes --prefer-online paydirt-mcp@latestThe public Paydirt Claude plugin marketplace is also included in this repository. After the public repository is available:
/plugin marketplace add Paydirt-AI/paydirt-mcp
/plugin install paydirt@paydirt-pluginsShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Paydirt: common questions
- Is Paydirt MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the Paydirt safety report
- How do I install Paydirt?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Paydirt need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Paydirt maintained?
- The last commit was 19 days ago (2026-10-16). The latest release is v2.3.0.
- What can I use instead of Paydirt?
- Servers from other publishers that do the same job: agent-device MCP server, DCC-MCP Core MCP server and agent-device MCP server.
- How does Paydirt compare with other AI and agents MCP servers?
- safety score 91/100 (higher than 88% of 4,460 AI and agents servers); tools 23 (the typical AI and agents server has 6); tools that change things 22% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Paydirt
Same job from other publishers: the closest match first, then the best rated.
- agent-deviceLet AI agents inspect, control, and debug real iOS, Android, desktop, and TV appsnot reviewedWidely usedA
- DCC-MCP CoreAgent control plane for DCC and engine hosts: one MCP endpoint, one tool contract.not reviewedEstablishedA
- agent-deviceOpen source device layer for AI agents: control mobile, web, TV, and desktop apps over MCPnot reviewedWidely usedA
- Agent-Native SlidesAgent-Native Google Slides - generate and edit React presentationsnot reviewedEstablishedA
- Ts CoreAgent-native TypeScript framework for building MCP servers.not reviewedEstablishedA