mcpField
C
ClassQuill

ClassQuill

Remote
classquill.comProductivity0Updated 15w ago

About ClassQuill

ClassQuill MCP server gives AI tools read-only access to tutoring-business data in ClassQuill, including sessions, people, billing, and reports. Its tools map to public API endpoints and are generated from the OpenAPI spec.

Key features

  1. 01Read-only tutoring-business data access
  2. 02Sessions, students, tutors, and billing
  3. 03Tools generated from OpenAPI spec
  4. 04Hosted OAuth or API-key access
  5. 05Local stdio and HTTP modes
  6. 06Credentials supplied per request

Use cases

  1. 01Review tutoring sessions and bookings
  2. 02Look up student and tutor records
  3. 03Check invoices, payments, and earnings
  4. 04Retrieve reports and lesson plans

MCP support

MCP clients can connect to the hosted server or run the local package in stdio or HTTP mode. The server exposes read-only tools corresponding to ClassQuill public API GET routes.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.classquill.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Packages
npmequateit-mcp1.0.1

Tools

Details

From the project README

ClassQuill MCP server

smithery badge

Give any MCP-aware AI tool — Claude, Codex, Cursor, Windsurf, Composio, and more — read access to your ClassQuill tutoring-business data: sessions, students, tutors, parents, invoices, payments, lesson plans, bookings, earnings, and reports.

It's a thin, read-only proxy over the ClassQuill public API (/v1). Each tool maps 1:1 to a public API endpoint, so the tool list can never drift from the real API. Your credentials never leave your machine (or, in hosted mode, your request).

ClassQuill is the tutoring-business-management platform by EquateIt. The npm package is published as equateit-mcp.

Two ways to use it

1. Hosted (recommended — nothing to install)

Point any remote-MCP client at the hosted server:

https://mcp.classquill.com/mcp
  • Claude / Claude.ai — add it as a custom connector and sign in (OAuth).
  • Codex — codex mcp add classquill --url https://mcp.classquill.com/mcp
  • Any client — pass your API key as a Bearer token: Authorization: Bearer ei_live_…
2. Local (run it yourself via npx)
npx -y equateit-mcp        # stdio, reads EQUATEIT_API_KEY

Claude Code:

claude mcp add classquill -e EQUATEIT_API_KEY=ei_live_xxxx -- npx -y equateit-mcp

Cursor / Claude Desktop / Windsurf (mcpServers config):

{
  "mcpServers": {
    "classquill": {
      "command": "npx",
      "args": ["-y", "equateit-mcp"],
      "env": { "EQUATEIT_API_KEY": "ei_live_xxxx" }
    }
  }
}

Getting an API key

Create one in the ClassQuill app under Settings → Developers (org admins). Keys look like ei_live_… and are read-only for this server.

Tools

One read-only tool per /v1 GET route — sessions, students, tutors, parents, invoices, payments, lesson-plans, homework, questions, subjects, files, results, availabilities, coverage, reports, and more. The list is generated from the public OpenAPI spec (npm run gen:tools) so it always matches the live API.

Options & environment

FlagEnv varDefaultPurpose
--keyEQUATEIT_API_KEY—Your ei_live_… key (stdio mode).
--http—offRun as an HTTP (Streamable HTTP) server instead of stdio.
--port / -pMCP_PORT3000HTTP port.
—EQUATEIT_API_BASE_URLhttps://api.classquill.comAPI base (no trailing /v1).

In HTTP mode, each request supplies its own credential as Authorization: Bearer … — an ei_live_… API key or an OAuth access token.

Develop

npm install
npm run build     # → dist/
npm test          # unit tests (url builder + auth scheme)

Self-hosting the HTTP server is a single container — see Dockerfile.

License

MIT — see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.