
Chaprola
- Updated March 27, 2026
- cletcher/chaprola-mcp
Chaprola is an MCP server that connects agents to a serverless Chaprola API backend for query, join, pivot, batch, email, FHIR, and program operations.
About
Chaprola MCP is a Model Context Protocol bridge to Chaprola’s serverless API backend, advertising query, JOIN, pivot, batch operations, email, FHIR, and custom programs via HTTP. Developers prototyping dashboards, internal tools, or health-adjacent data apps can point an agent at structured backend actions instead of reimplementing client SDKs for each verb. Registration at api.chaprola.org supplies username and API key credentials wired through environment variables in the npm-delivered stdio server. The backend placement reflects that you are standing up logic and data access, not tuning App Store keywords or on-call paging. Intermediate complexity fits teams comfortable with API keys, npm MCP installs, and the security implications of agent-driven batch and email capabilities. Treat it as an integration MCP to a hosted platform, not a local database you fully control on disk.
- npm package @chaprola/mcp-server 1.4.3 with stdio MCP transport
- Serverless API: query, JOIN, pivot, batch operations, email, FHIR, and programs over HTTP
- Requires CHAPROLA_USERNAME and CHAPROLA_API_KEY (chp_ plus 64 hex chars) from https://api.chaprola.org/register
- Repository subfolder mcp-server on GitHub cletcher/chaprola-mcp
- Lets agents orchestrate backend data work without you writing every HTTP client call by hand
Chaprola by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add --env CHAPROLA_USERNAME=YOUR_CHAPROLA_USERNAME --env CHAPROLA_API_KEY=YOUR_CHAPROLA_API_KEY chaprola -- npx -y @chaprola/mcp-serverAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | @chaprola/mcp-server |
|---|---|
| Transport | STDIO |
| Auth | Required |
| Last updated | March 27, 2026 |
| Repository | cletcher/chaprola-mcp ↗ |
What it does
Expose a serverless Chaprola HTTP backend—queries, joins, pivot, batch jobs, email, FHIR, and programs—to your agent without standing up custom infra first.
Who is it for?
Best when you're validating data-heavy MVPs or agent workflows that fit Chaprola’s hosted API model, including FHIR-oriented experiments.
Skip if: Skip if you require exclusively on-prem databases, or anyone unwilling to register and store a Chaprola API key for agent access.
What you get
Once username and API key are set, your agent can call Chaprola backend capabilities through MCP tools instead of bespoke scripts per operation.
- Agent-driven queries, joins, pivots, and batch actions against Chaprola
- Email and program invocation paths exposed through MCP tools
- Faster backend iteration without hand-written HTTP glue for each endpoint
By the numbers
- Server metadata version 1.4.3
- npm identifier @chaprola/mcp-server
- Two required environment variables: CHAPROLA_USERNAME and CHAPROLA_API_KEY
README.md
@chaprola/mcp-server
MCP server for Chaprola — the agent-first data platform.
Gives AI agents 40 tools for structured data storage, querying, web search, URL fetching, scheduled jobs, and execution through the Model Context Protocol.
Quick Start
Claude Code
claude mcp add chaprola-mcp -e CHAPROLA_USERNAME=yourusername -e CHAPROLA_API_KEY=chp_yourkey -- npx @chaprola/mcp-server
Note: After installing, restart Claude Code to load the MCP server. The server description and tools will then be available to Claude.
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"chaprola": {
"command": "npx",
"args": ["@chaprola/mcp-server"],
"env": {
"CHAPROLA_USERNAME": "yourusername",
"CHAPROLA_API_KEY": "chp_yourkey"
}
}
}
}
VS Code / Copilot
Add to .vscode/mcp.json:
{
"servers": {
"chaprola": {
"command": "npx",
"args": ["@chaprola/mcp-server"],
"env": {
"CHAPROLA_USERNAME": "yourusername",
"CHAPROLA_API_KEY": "chp_yourkey"
}
}
}
}
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"chaprola": {
"command": "npx",
"args": ["@chaprola/mcp-server"],
"env": {
"CHAPROLA_USERNAME": "yourusername",
"CHAPROLA_API_KEY": "chp_yourkey"
}
}
}
}
Getting Credentials
# Register (returns your API key — save it immediately)
curl -X POST https://api.chaprola.org/register \
-H "Content-Type: application/json" \
-d '{"username": "myname", "passcode": "my-secure-passcode-16chars"}'
Or use the chaprola_register tool after connecting.
Available Tools
| Tool | Description |
|---|---|
chaprola_hello |
Health check |
chaprola_register |
Create account |
chaprola_login |
Login (get new API key) |
chaprola_check_username |
Check username availability |
chaprola_delete_account |
Delete account + all data |
chaprola_sign_baa |
Sign Business Associate Agreement (PHI only) |
chaprola_baa_status |
Check BAA status |
chaprola_baa_text |
Get BAA text |
chaprola_import |
Import JSON to Chaprola format |
chaprola_import_url |
Get presigned upload URL |
chaprola_import_process |
Process uploaded file |
chaprola_import_download |
Import from URL (CSV/Excel/JSON/Parquet) |
chaprola_export |
Export to JSON |
chaprola_list |
List files |
chaprola_compile |
Compile .CS source to .PR bytecode |
chaprola_run |
Execute .PR program |
chaprola_run_status |
Check async job status |
chaprola_publish |
Publish program for public access |
chaprola_unpublish |
Remove public access |
chaprola_report |
Run published program (no auth) |
chaprola_export_report |
Run program and save output |
chaprola_download |
Get presigned download URL |
chaprola_query |
Filter, aggregate, join data |
chaprola_sort |
Sort data file |
chaprola_index |
Build index on field |
chaprola_merge |
Merge two sorted files |
chaprola_optimize |
HULDRA nonlinear optimization |
chaprola_optimize_status |
Check optimization status |
chaprola_email_inbox |
List emails |
chaprola_email_read |
Read email |
chaprola_email_send |
Send email |
chaprola_email_delete |
Delete email |
chaprola_search |
Web search via Brave API |
chaprola_fetch |
Fetch URL content as markdown/text/JSON |
chaprola_schedule |
Create scheduled recurring job |
chaprola_schedule_list |
List scheduled jobs |
chaprola_schedule_delete |
Delete scheduled job |
Resources
The server exposes reference documentation as MCP resources:
chaprola://cookbook— Language cookbook with complete exampleschaprola://endpoints— All 40 API endpointschaprola://auth— Authentication referencechaprola://gotchas— Common mistakes to avoid
Environment Variables
| Variable | Required | Description |
|---|---|---|
CHAPROLA_USERNAME |
Yes | Your registered username |
CHAPROLA_API_KEY |
Yes | Your API key (format: chp_ + 64 hex chars) |
HIPAA / BAA
Non-PHI data works without a signed BAA. If handling Protected Health Information (PHI), a human must review and sign the BAA first. The server includes guardrails that warn agents when the BAA is not signed.
Links
- Website: chaprola.org
- API: api.chaprola.org
- Status: UptimeRobot
Recommended MCP Servers
How it compares
Hosted serverless API MCP, not a raw Postgres MCP or Clerk docs remote.
FAQ
Who is Chaprola MCP for?
Developers and small teams using AI agents to drive a Chaprola serverless backend for queries, transforms, batch jobs, and related HTTP programs.
When should I use Chaprola MCP?
Use it in build while prototyping backend features, pivots, and batch flows before you harden ship-stage security and production monitoring.
How do I add Chaprola MCP to my agent?
Register at https://api.chaprola.org/register, set CHAPROLA_USERNAME and CHAPROLA_API_KEY, install npm @chaprola/mcp-server, and configure stdio MCP in your host.