courtreserve-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@courtreserve-mcpRegister Sarah for the Tuesday evening pickleball clinic."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
CourtReserve MCP
First MCP server for CourtReserve — the racquet-sports club management platform that runs tennis, pickleball, padel, racquetball, squash, and badminton clubs. Talk to your club's members, reservations, events, and transactions from Claude, Cursor, or any MCP-compatible AI client.
What you can do with it
You: "Find every active member at our downtown location whose membership
expires this month and tell me which ones haven't booked a court
in the last 30 days."
Claude: *calls list_memberships + list_reservations, joins the results, replies*
You: "Register Sarah for the Tuesday evening pickleball clinic."
Claude: *calls register_for_event, confirms the result*
You: "Cancel reservation 8888 and refund the booking fee."
Claude: *calls cancel_reservation + create_transaction (credit), reports back*The MCP covers the same surface CourtReserve uses internally: members, memberships, families, court reservations, events (clinics, lessons, tournaments, round robins, open play), event registrations, transactions, courts, and locations.
Related MCP server: mindbody-mcp
Install
pip install -e .For local development:
pip install -e ".[dev]"Configure
CourtReserve's API uses HTTP Basic auth with two values issued from the club admin UI:
Log in to
app.courtreserve.comas a club admin.Go to Settings -> Additional Features -> Integrations -> API Access.
Click Create API Key. Enable the API access checkbox first if it's off.
Choose Full Access (read + write) or Restricted Access (pick specific roles).
Copy the Username (format:
Org_<numeric>) and Password (long opaque string).
export COURTRESERVE_USERNAME="Org_12345"
export COURTRESERVE_PASSWORD="98765_550e8400-e29b-41d4-a716-446655440000"The API key must be enabled on an Advance / Momentum / Enterprise plan (per CourtReserve's docs, the API add-on is paid). The key's role-based permissions control which endpoints the MCP can call.
Claude Desktop / Cursor
Add to your claude_desktop_config.json (or ~/.cursor/mcp.json):
{
"mcpServers": {
"courtreserve": {
"command": "courtreserve-mcp",
"env": {
"COURTRESERVE_USERNAME": "Org_12345",
"COURTRESERVE_PASSWORD": "your-password"
}
}
}
}Tools (22)
Group | Tool | Purpose |
Diagnostic |
| Verify credentials + returns locations list |
Members |
| Member CRUD + search |
Memberships |
| Tier assignment + lifecycle |
Families |
| Linked-member accounts |
Reservations |
| Court bookings |
Events |
| Clinics, tournaments, lessons, round robins |
Transactions |
| Payments, credits, refunds |
Courts |
| Court surface + rate info |
Locations |
| Sites/branches |
Run courtreserve-mcp --help (or start the server and inspect tools/list from your client) for the full JSON schema.
Engineering standards
This MCP inherits the engineering playbook applied across the sanjibani MCP portfolio:
Shared
httpx.AsyncClientwith connection pooling + transport-level retries.Typed exception hierarchy (
CourtReserveAuthError,NotFoundError,RateLimitError,APIError,ConnectionError) with structured fields (http_status,request_id,retry_after).Application-level retry with exponential backoff + full jitter on 429/5xx, honoring
Retry-After.isError-compliance (per the Blackwell Systems MCP security audit): tools
raiseexceptions, FastMCP wraps them withisError=trueon the wire. AI agents can distinguish failures from successful responses returning error-shaped strings.JSONL audit logging via
src/courtreserve_mcp/audit.py— one record per tool call to stderr (or<PKG>_AUDIT_LOGfile). Fail-open: sink failure never breaks the tool. Secret redaction onpassword/api_key/token/etc.respx for httpx mocking + hypothesis property tests + pytest-asyncio.
mypy --strict clean, ruff full rule set clean, py.typed marker (PEP 561).
src/layout, dynamic version from__init__.py, hatchling backend.
Development
pip install -e ".[dev]"
# Lint
ruff check src tests
ruff format --check src tests
# Type
mypy src
# Test
pytest
# All three
ruff check src tests && ruff format --check src tests && mypy src && pytestLicense
MIT — see LICENSE.
Author
Sanjibani Choudhury schoudhury1991@gmail.com. Independent community build — not affiliated with CourtReserve or Storable. PRs welcome if CourtReserve renames an endpoint; open an issue if you find a gap in coverage.
This MCP is part of the sanjibani MCP portfolio — 28+ vertical-specific MCPs (insurance, dental, veterinary, legal, home service, church, auto-dealership, title/escrow, pest control, golf, self-storage, laundromat, youth sports, etc.). All MIT-licensed, all ruff + mypy + pytest clean, all isError-compliant.
Need a custom MCP built for a niche SaaS you use? See engagement options.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sanjibani/courtreserve-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server