Connect Prompeteer to the tools your team uses

Prompeteer.ai connects to Claude Code, Cursor, GitHub Copilot, Chrome, the Model Context Protocol, a REST API, and n8n, so saved prompts and agent skills are usable inside existing tools. Every integration uses the same account and PromptDrive library, so a prompt or skill generated in the web app is available inside your editor, your browser, and your automations without copying it around.

Connect Prompeteer to the tools you already use

Connect Prompeteer prompts and skills to your favorite AI tools. Install the Chrome Extension, add the remote MCP Server to Claude or Cursor, or integrate through the REST API.

Bring your prompt and skill workflows to Chrome, Claude, Cursor, Replit, Windsurf, and beyond. Connect through the remote MCP Server, REST APIs, the n8n node, or our Chrome Extension.

Chrome extension

Generate and save prompts & skills from top AI tools and platforms. Works in your browser.

  • One-click prompt & skill generation
  • Save directly to your Drive
  • Works with 140+ AI platforms
  • Available on desktop Chrome

MCP server

Connect Claude, Cursor, and other compatible AI tools directly to Prompeteer through the remote MCP server.

  • Works with Claude, Cursor, Windsurf & more
  • Generate, score & save prompts & skills
  • OAuth sign-in, no API key required
  • Generate expert prompts
  • Access your Drive
  • Score prompt quality
  • All 140+ platforms

Connecting Claude, Cursor and other MCP clients

Remote MCP uses OAuth and does not require an API key. Add the connector, then sign in to Prompeteer.

Cursor connects directly to Prompeteer and starts OAuth when you first use the server. No API key or local proxy is required.

Choose Streamable HTTP in your MCP client, paste the endpoint below, and complete OAuth when prompted.

  • In Claude on the web, open Settings > Connectors.
  • In Claude Desktop, open Settings > Connectors.
  • Choose Add custom connector.
  • Paste the canonical Prompeteer MCP endpoint:
  • Save the connector and authorize it with your Prompeteer account when prompted.
  • In Claude Desktop, go to: Settings → Connectors → Edit Config
  • Restart or reload Cursor if needed, then authorize Prompeteer when Cursor prompts you.
  • Your client must support remote Streamable HTTP MCP servers and browser-based OAuth. Consult the client documentation for where to add a remote server URL.
  • Streamable HTTP transport (stateless). Direct POST requests with JSON responses. Best for programmatic integrations.
  • Legacy SSE is not part of the recommended setup. Use the canonical Streamable HTTP endpoint.

What the MCP connection exposes

Create, score, save, and use your private Memory through the same authenticated MCP connection.

  • Create reusable agent instructions in the agentskills.io SKILL.md format
  • List your Memory documents and processing status without exposing document text
  • Find a small set of relevant private Memory excerpts with evidence-aware abstention
  • Retrieve a bounded excerpt from one explicitly selected Memory page
  • Answer from Memory with validated page citations, or abstain when evidence is insufficient
  • Read your Web, MCP, API, and Chrome Memory defaults and effective enterprise policy
  • Update your MCP Memory default while preserving enterprise policy controls

REST API, n8n and agent skills

Building a direct HTTP integration instead? Use a Prompeteer REST API key.

Generate, score, and enhance prompts with simple HTTP requests. Generated prompts auto-save to your Drive.

Create an API key in Settings → Connectors, then use it as a Bearer token in the Authorization header.

Generated prompts are automatically saved to your Drive. Pass saveToDrive: false to disable.

Add Prompeteer to your n8n workflows. Generate, score, and enhance prompts as part of any automation.

Pre-built MCP applications that extend your AI workflows with Prompeteer intelligence.

Create reusable agent instructions with Prompeteer. Review the SKILL.md file and your coding client’s requirements before installation.

  • Generate, score & enhance prompts & skills via HTTP
  • Import our Postman Collection for an instant API playground with pre-built requests and examples.
  • Scanned for prompt injection, jailbreaks, and data-exfil patterns before it ever reaches your stack.

Frequently asked questions

What is MCP?

MCP (Model Context Protocol) is a standard that lets AI tools like Claude and Cursor connect to external services. Think of it like USB for AI: a universal way to plug in new capabilities.

Can I use Prompeteer as a REST API?

Yes! Create an API key in Settings, then call our endpoints from any language: Python, JavaScript, cURL, Postman, or your own app. All endpoints (generate, score, enhance) use your monthly quota.

Can I use this with my free Prompeteer account?

Free generation is quota-limited. Pro includes unlimited standard web prompt and skill generation. API and connected-tool operations follow their published account quotas, rate limits and feature entitlements; a web allowance does not remove those limits.

Is my data secure?

MCP uses HTTPS and account-bound OAuth permissions; REST API access uses scoped keys. Memory sources and saved prompts are stored for reuse until you delete them or your account. Transient context files follow feature-specific retention controls. Configured AI providers process the context needed for the requested operation; provider, security-log and backup retention are described in our Privacy Policy.

What does Memory add to connected AI tools?

Memory turns your uploaded documents into a private, browsable wiki. Connected tools can list sources, search relevant passages, open a selected page, or generate a grounded answer from that material.

Does a connected client receive my whole Memory?

No. Access is bound to your authenticated Prompeteer account, and retrieval returns only the minimum authorized passages relevant to the request, never the whole Memory by default. Grounded answers expose page citations and the effective Memory state; when evidence is insufficient, Memory abstains.

What happens when Memory cannot support an answer?

Prompeteer does not fill gaps from general knowledge. Search returns no confident match, and Ask Memory gives a clear abstention instead of an uncited answer.

Which clients and controls support Memory?

Any standards-compliant MCP client can use these tools, including ChatGPT and Claude. Contextual generation supports inherit, on, or off per request, backed by separate Web, MCP, API, and Chrome extension defaults. Disconnecting or revoking the client blocks access, and enterprise administrators can require or disable Memory on each surface.

Which Memory capabilities are Free or Pro?

Free accounts can preview Memory. New document uploads require Pro or Enterprise, and the ask_memory grounded Q&A tool requires Pro access. Authorized existing sources can be browsed and searched. Enterprise adds governance controls.

I'm stuck. Can I get help?

Of course! If you run into any issues, just ask in your AI tool: 'Help me troubleshoot my Prompeteer MCP connection.' You can also email us at info@prompeteer.com. We're happy to help!

Connect your AI agent

Use https://prompeteer.ai/mcp as a remote MCP server with Streamable HTTP. Sign in with your Prompeteer account and approve OAuth permissions in your browser.

Cursor and clients using mcpServers JSON

Merge this into your MCP configuration (Cursor: ~/.cursor/mcp.json), enable Prompeteer, and finish authorization:

{
  "mcpServers": {
    "prompeteer": {
      "url": "https://prompeteer.ai/mcp"
    }
  }
}

Claude

Add https://prompeteer.ai/mcp as a custom remote connector in Claude's connector settings, then complete OAuth. Availability depends on your client and plan.

Ask the agent to list your saved prompts, generate a prompt, or score a prompt. Saving requires write consent. Private Memory requires separate Memory permissions. Read the service manifest.

Capabilities and account limits

Reviewed .

Free accounts can preview Memory. New document uploads require Pro or Enterprise, and the ask_memory grounded Q&A tool requires Pro access. Authorized existing sources can be browsed and searched. Enterprise adds governance controls.

Free generation is quota-limited. Pro includes unlimited standard web prompt and skill generation. API and connected-tool operations follow their published account quotas, rate limits and feature entitlements; a web allowance does not remove those limits.

Beacon’s website overview is public. Its workspaces, reports, samples and paid operations are currently available only to administrators. Free Prompeteer and Prompeteer Pro do not grant Beacon workspace access.

Browse Skills Hub without an account. Sign in to inspect full instructions, copy or download a skill. These library actions do not require a paid plan. Review source, scan results and client requirements before use.

Private prompts, Memory and reports require authorization. Confirm required controls and contractual terms before using sensitive data. Controls and contract scope.

What the product supports and where limits apply
CapabilityAvailable behaviorScope and limitsDetails
Prompt targetsChoose a listed model or app and generate instructions to use there.A prompting target is not a direct API integration or a guarantee that every model version was benchmarked.Prompt targets details
Agent skillsDownload SKILL.md instruction files with source and scan information.Client support, installation paths and available tools vary. Review a skill before granting it access.Agent skills details
Connected accessUse the remote MCP service, REST API or Chrome extension.OAuth permissions, client compatibility and account quotas apply. Planned channels are labeled separately.Connected access details
Languages129 prompt-generation language options.This count does not certify complete interface translations or equal answer quality in every language.Languages details
Quality feedbackSkill Score assesses effectiveness, specificity and description quality for skills; Prompt Score assesses 16 prompt-quality dimensions for prompts.Automated feedback is an aid to review, not independent certification or a factual-accuracy guarantee.Quality feedback details

Practical workflow guides

Write for the app doing the work Browse all guides →

Opening your workspace…