PrompTessor

Model-aware prompt workflows for AI clients and coding agents: generate, analyze, optimize, refine, and reverse-engineer prompts through secure OAuth.

View on promptessor.comTry this MCPSponsored

Documentation

Prerequisites

  1. 1 Use an eligible PrompTessor account You need a verified PrompTessor account and an active plan that includes Public API and MCP access.
  2. 2 Use the server URL, not an API key All integrations on this page connect to the hosted remote MCP server through OAuth. Sign in to PrompTessor when the client opens your browser; there is no key to copy or paste.
  3. 3 Use a compatible client The client must support remote Streamable HTTP servers and MCP OAuth discovery. Use the current client version when possible.
  4. 4 Allow browser sign-in OAuth requires a browser and, for local CLI clients, access to the localhost callback opened during authorization.
  5. 5 Check workspace policy Managed ChatGPT, Claude, Cursor, VS Code, or Devin workspaces can require an administrator to enable custom MCP connections.

Name

PrompTessor

Server URL

https://mcp.promptessor.com/mcp

Transport

Streamable HTTP

Authentication

OAuth

API key

Not required and not accepted for MCP

  • Use the exact HTTPS URL shown above, including the /mcp path.
  • Choose HTTP or Streamable HTTP. Do not choose the legacy SSE transport.
  • Leave custom client ID, client secret, API key, and headers empty. PrompTessor advertises its OAuth configuration automatically.
  • Review the requested scopes before approving access. Tool, prompt, and resource support can vary by client.

Safe first test

After connecting, ask the client to call get_usage. It confirms the connection, account, scopes, and usage limits without consuming an AI workflow credit.

Choose an MCP client

Open the focused setup guide for your client. Every guide uses the same hosted PrompTessor MCP server and OAuth authorization flow.

[ChatGPT

Configure the PrompTessor MCP connector in ChatGPT web and complete OAuth authorization.

](https://promptessor.com/dev/docs/mcp/integrations/chatgpt)[Claude & Claude Desktop

Add PrompTessor as a custom connector in Claude or Claude Desktop and authorize it with OAuth.

](https://promptessor.com/dev/docs/mcp/integrations/claude)[Codex

Set up PrompTessor in Codex settings or with the Codex command line, then complete OAuth authorization.

](https://promptessor.com/dev/docs/mcp/integrations/codex)[Claude Code

Add the hosted PrompTessor MCP server to Claude Code and choose the appropriate configuration scope.

](https://promptessor.com/dev/docs/mcp/integrations/claude-code)[Gemini CLI

Configure the PrompTessor Streamable HTTP MCP server in Gemini CLI.

](https://promptessor.com/dev/docs/mcp/integrations/gemini-cli)[Cursor

Add PrompTessor as a remote MCP server in Cursor and authorize the connection.

](https://promptessor.com/dev/docs/mcp/integrations/cursor)[VS Code

Use PrompTessor MCP with Visual Studio Code and GitHub Copilot.

](https://promptessor.com/dev/docs/mcp/integrations/vs-code)[Devin

Add PrompTessor as a custom remote MCP server in Devin.

](https://promptessor.com/dev/docs/mcp/integrations/devin)[Others

Use the standard server URL, OAuth discovery, and Streamable HTTP settings in another compatible MCP client.

](https://promptessor.com/dev/docs/mcp/integrations/others)