base44
Base44 API and MCP integration for creating, listing, and managing AI apps.
What this skill does
## Troubleshooting
If requests fail, run `zero doctor check-connector --env-name BASE44_TOKEN` or `zero doctor check-connector --url https://app.base44.com/api/apps --method GET`
## How to Use
Base44 exposes two useful integration surfaces:
- App REST API at `https://app.base44.com/api/apps`
- MCP endpoint at `https://app.base44.com/mcp`
Use the App REST API for direct app management, and use MCP when an agent needs to discover and call Base44 tools.
## Discover the Full Interface
### MCP Tools and Schemas
`tools/list` is the source of truth for the current MCP interface. It returns every available tool with descriptions and input schemas.
Write to `/tmp/base44_mcp_request.json`:
```json
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/list",
"params": {}
}
```
Then run:
```bash
curl -s -X POST "https://app.base44.com/mcp" --header "Authorization: Bearer $BASE44_TOKEN" --header "Content-Type: application/json" --header "Accept: application/json, text/event-stream" -d @/tmp/base44_mcp_request.json | sed -n 's/^data: //p' | jq '.result.tools[] | {name, description, inputSchema}'
```
Inspect one tool schema before calling it:
```bash
curl -s -X POST "https://app.base44.com/mcp" --header "Authorization: Bearer $BASE44_TOKEN" --header "Content-Type: application/json" --header "Accept: application/json, text/event-stream" -d @/tmp/base44_mcp_request.json | sed -n 's/^data: //p' | jq --arg name "create_base44_app" '.result.tools[] | select(.name == $name) | {name, description, inputSchema}'
```
Current confirmed MCP tools:
- `create_base44_app`
- `edit_base44_app`
- `get_app_status`
- `get_app_preview_url`
- `list_user_apps`
- `list_entity_schemas`
- `create_entity_schema`
- `update_entity_schema`
- `query_entities`
- `create_entities`
- `update_entities`
### App REST API Endpoints
Base44 does not currently expose a machine-readable discovery document for the App REST API. Use the confirmed endpoint map below for common app operations. For edge cases, check the official Base44 CLI source at `https://github.com/base44/cli`.
| Operation | Method | Path |
| --- | --- | --- |
| Create app | `POST` | `/api/apps` |
| List apps | `GET` | `/api/apps` |
| Get app config | `GET` | `/api/apps/{app_id}` |
| Update auth config | `PUT` | `/api/apps/{app_id}` |
| Download app source | `GET` | `/api/apps/{app_id}/eject` |
| Get published URL | `GET` | `/api/apps/platform/{app_id}/published-url` |
| Upload site archive | `POST` | `/api/apps/{app_id}/deploy-dist` |
| Sync entity schemas | `PUT` | `/api/apps/{app_id}/entity-schemas` |
| List backend functions | `GET` | `/api/apps/{app_id}/backend-functions` |
| Deploy backend function | `PUT` | `/api/apps/{app_id}/backend-functions/{function_name}` |
| Delete backend function | `DELETE` | `/api/apps/{app_id}/backend-functions/{function_name}` |
| Fetch function logs | `GET` | `/api/apps/{app_id}/functions-mgmt/{function_name}/logs` |
| List agents | `GET` | `/api/apps/{app_id}/agent-configs` |
| Sync agents | `PUT` | `/api/apps/{app_id}/agent-configs` |
| List connectors | `GET` | `/api/apps/{app_id}/external-auth/list` |
| List available connector integrations | `GET` | `/api/apps/{app_id}/external-auth/available-integrations` |
| Set connector integration | `PUT` | `/api/apps/{app_id}/external-auth/integrations/{integration_type}` |
| Get connector OAuth status | `GET` | `/api/apps/{app_id}/external-auth/status` |
| Remove connector integration | `DELETE` | `/api/apps/{app_id}/external-auth/integrations/{integration_type}/remove` |
| List secrets | `GET` | `/api/apps/{app_id}/secrets` |
| Set secrets | `POST` | `/api/apps/{app_id}/secrets` |
| Delete secret | `DELETE` | `/api/apps/{app_id}/secrets?secret_name={secret_name}` |
| Install Stripe | `POST` | `/api/apps/{app_id}/payments/stripe/install` |
| Get Stripe status | `GET` | `/api/apps/{app_id}/payments/stripe/status` |
| Remove Stripe | `DELETE` | `/api/apps/{app_id}/payments/stripe` |
## App REST API
### List Apps
```bash
curl -s "https://app.base44.com/api/apps?limit=10" --header "Authorization: Bearer $BASE44_TOKEN" | jq .
```
### Create an App
Write to `/tmp/base44_create_app.json`:
```json
{
"name": "hello",
"user_description": "Backend for 'hello'",
"is_managed_source_code": false,
"public_settings": "public_without_login"
}
```
Then run:
```bash
curl -s -X POST "https://app.base44.com/api/apps" --header "Authorization: Bearer $BASE44_TOKEN" --header "Content-Type: application/json" -d @/tmp/base44_create_app.json | jq .
```
### Get an App
Replace `<app-id>` with the Base44 app ID.
```bash
curl -s "https://app.base44.com/api/apps/<app-id>" --header "Authorization: Bearer $BASE44_TOKEN" | jq .
```
### Download App Source
Replace `<app-id>` with the Base44 app ID. This downloads a tar archive of the app source.
```bash
curl -s "https://app.base44.com/api/apps/<app-id>/eject" --header "Authorization: Bearer $BASE44_TOKEN" --output /tmp/base44-app.tar
```
### Get Published URL
Replace `<app-id>` with the Base44 app ID.
```bash
curl -s "https://app.base44.com/api/apps/platform/<app-id>/published-url" --header "Authorization: Bearer $BASE44_TOKEN" | jq .
```
### List App Secrets
Replace `<app-id>` with the Base44 app ID. The API lists secret metadata, not secret values.
```bash
curl -s "https://app.base44.com/api/apps/<app-id>/secrets" --header "Authorization: Bearer $BASE44_TOKEN" | jq .
```
### List Backend Functions
Replace `<app-id>` with the Base44 app ID.
```bash
curl -s "https://app.base44.com/api/apps/<app-id>/backend-functions" --header "Authorization: Bearer $BASE44_TOKEN" | jq .
```
### List Agents
Replace `<app-id>` with the Base44 app ID.
```bash
curl -s "https://app.base44.com/api/apps/<app-id>/agent-configs" --header "Authorization: Bearer $BASE44_TOKEN" | jq .
```
### List Connectors
Replace `<app-id>` with the Base44 app ID.
```bash
curl -s "https://app.base44.com/api/apps/<app-id>/external-auth/list" --header "Authorization: Bearer $BASE44_TOKEN" | jq .
```
## MCP API
### Initialize MCP
```bash
curl -s -X POST "https://app.base44.com/mcp" --header "Authorization: Bearer $BASE44_TOKEN" --header "Content-Type: application/json" --header "Accept: application/json, text/event-stream" -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"vm0","version":"1.0.0"}}}' | sed -n 's/^data: //p' | jq .
```
### List MCP Tools
Write to `/tmp/base44_mcp_request.json`:
```json
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/list",
"params": {}
}
```
Then run:
```bash
curl -s -X POST "https://app.base44.com/mcp" --header "Authorization: Bearer $BASE44_TOKEN" --header "Content-Type: application/json" --header "Accept: application/json, text/event-stream" -d @/tmp/base44_mcp_request.json | sed -n 's/^data: //p' | jq '.result.tools[] | {name, description}'
```
### List User Apps with MCP
Write to `/tmp/base44_mcp_request.json`:
```json
{
"jsonrpc": "2.0",
"id": 3,
"method": "tools/call",
"params": {
"name": "list_user_apps",
"arguments": {}
}
}
```
Then run:
```bash
curl -s -X POST "https://app.base44.com/mcp" --header "Authorization: Bearer $BASE44_TOKEN" --header "Content-Type: application/json" --header "Accept: application/json, text/event-stream" -d @/tmp/base44_mcp_request.json | sed -n 's/^data: //p' | jq .
```
### Create an App with MCP
Write to `/tmp/base44_mcp_request.json`:
```json
{
"jsonrpc": "2.0",
"id": 4,
"method": "tools/call",
"params": {
"name": "create_base44_app",
"arguments": {
"name": "hello"
}
}
}
```
Then run:
```bash
curl -s -X POST "https://app.base44.com/mcp" --header "Authorization: Bearer $BASE44_TOKEN" --header "Content-Type: application/json" --header "Accept: application/json, text/event-stream" -d @/tmp/base44_mcp_request.json | sed -n 's/^data: //p' | jq .
```
## Guidelines
1. Use `BASE44_TOKEN` in examples. The vm0 connector maRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.