nango-toolbox

Included with Lifetime

$97 forever

Universal gateway for any third-party API or SaaS (Google Calendar, Gmail, Slack, Notion, Linear, HubSpot, etc.). TRIGGER on any request to read or modify data in an external product, even when no matching MCP tool is loaded.

Backend & APIs

What this skill does


## When to use

- Any access to an external API.
- External API calls must go through **Nango**.
- Do **not** use MCPs, provider CLIs, or ad-hoc direct API calls outside Nango.

## Configuration (required)

Resolve values in this order.

### Secret key

1. `NANGO_TOOLBOX_SECRET_KEY` in the process environment
2. `NANGO_TOOLBOX_SECRET_KEY` in a local `.env`

If missing, ask the user to:
- create a Nango account: https://app.nango.dev/signup
- copy the secret key from Environment settings → Backend
- set `NANGO_TOOLBOX_SECRET_KEY` in their shell profile (offer to add it)

Compatibility: if other instructions refer to `NANGO_SECRET_KEY`, treat it as `NANGO_TOOLBOX_SECRET_KEY`.

### Base URL

1. `NANGO_SERVER_URL` in the process environment
2. `NANGO_SERVER_URL` in a local `.env`
3. `https://api.nango.dev`

### HTTP headers

- `Authorization: Bearer <NANGO_TOOLBOX_SECRET_KEY>`
- `Content-Type: application/json`
- Prefer JSON bodies over query params when both exist.

## Discovery (use these first)

List integrations:
```
GET <base-url>/integrations
Authorization: Bearer <secret-key>
```

List connections for an integration:
```
GET <base-url>/connections?integrationId=<unique_key>
Authorization: Bearer <secret-key>
```

List deployed actions/syncs:
```
GET <base-url>/scripts/config
Authorization: Bearer <secret-key>
```

## Choose integration (do this before connection)

- Check if an integration for your API is setup in Nango
- If not, set it up for the user:
  - If the API is OAuth and has Nango provided developer credentials, ask the user to enable it manually in the dashboard.
  - If the API is OAuth and doesn't have Nango developer credentials guide the user to get a client id & secret
  - If the API uses "OAuth client credentials", do not ask the user for client id & secret. Set the integration up and the user will enter them with the Connect Link.
  - In all other cases, set the integration up and proceed with creating a Connect link

Do not ask the user for any Connection specific parameters. Always let it enter these in the Connect link.

## Choose integration + connection (required)

- Ensure the integration (provider) exists in Nango; create it via Nango HTTP API if needed.
- Fetch connections for the integration.
- If multiple connections exist and you cannot disambiguate, ask which `connection_id` to use.

If no connection exists, generate a connect session link:
```
POST <base-url>/connect/sessions
Authorization: Bearer <secret-key>
Content-Type: application/json

{
  "tags": { "end_user_id": "<user-firstname>" },
  "allowed_integrations": ["<unique_key>"]
}
```
Share `data.connect_link` directly with the user (expires in ~30 minutes). Do not send them to the dashboard.

Before provider calls, confirm required scopes on the connection (often `credentials.raw.scope`).

If scopes are insufficient, update scopes at the **integration** level, then ask for permission to delete/recreate the connection:
```
PATCH <base-url>/integrations/<unique_key>
Authorization: Bearer <secret-key>
Content-Type: application/json

{
  "credentials": {
    "type": "OAUTH2",
    "client_id": "<client_id>",
    "client_secret": "<client_secret>",
    "scopes": "scope1,scope2,scope3"
  }
}
```
Scopes are comma-separated (no spaces).

## Access strategy

- Use **Nango proxy** for 1–2 simple provider calls and to explore the API.
- Use a **Nango Action** for multi-call logic, transformations, pagination orchestration, retries/error handling, or reuse.

Prefer reusing an existing deployed action (see `GET <base-url>/scripts/config`).

If you must create a new action, use the `building-nango-functions-remotely` skill and deploy before calling it.
If the skill does not exist, offer to install it from https://github.com/NangoHQ/skills

Invoke a deployed action:
```
POST <base-url>/action/trigger
Authorization: Bearer <secret-key>
Provider-Config-Key: <unique_key>
Connection-Id: <connection_id>
Content-Type: application/json

{"action_name": "<action-name>", "input": {...}}
```

## Docs

- https://nango.dev/docs
- https://nango.dev/docs/llms.txt
- https://nango.dev/docs/reference/api
- https://nango.dev/docs/spec.yaml

Nango maintains a docs page for each API it supports (find it in llms.txt). This page contains a link to the external APIs reference.

Files: 1

Size: 4.5 KB

Complexity: 8/100

Category: Backend & APIs

Source: https://github.com/nangohq/skills/tree/main/skills/nango-toolbox

Related in Backend & APIs

jfrog

Included

Interact 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.

Backend & APIsscripts

cupynumeric-migration-readiness

Included

Pre-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.

Backend & APIsscripts

alibabacloud-data-agent-skill

Included

Invoke 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".

Backend & APIsscripts

token-optimizer

Included

Reduce 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.

Backend & APIsscripts

resend-cli

Included

Use 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.

Backend & APIsscripts

alibabacloud-odps-maxframe-coding

Included

Use 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.

Backend & APIsscripts