> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to Strale

The Strale connector lets your AI agent act in each user's Strale account. Each user connects their own Strale access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 18 tools.

**Authentication:** Bearer Token
**Categories:** AI, Developer Tools
**Tools:** 18: 14 read, 4 write, 0 destructive
**Users sign in with:** Access token
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=STRALE)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Strale connection

   In **AgentKit > Connections**, create a Strale connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'strale'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Strale:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'strale_capabilities_health_get',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "strale"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Strale:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="strale_capabilities_health_get",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their Strale credentials there. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'strale_capabilities_health_get',
  toolInput: {},
  connector: 'strale',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="strale_capabilities_health_get",
    tool_input={},
    connection_name="strale",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `strale_capabilities_health_get`

Get Capability Health · Read-only

Get a health summary of the capability catalog.
Returns a summary of capability health and availability.
Use strale_capabilities_health_get to check whether capabilities are currently working.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `strale_capabilities_list`

List Capabilities · Read-only

List every active Strale capability with its price and input schema.
Returns capabilities[], each with slug, name, description, category, price_cents and input_schema.
Use strale_capabilities_list to browse the whole catalog. Use strale_capabilities_suggest to find a capability for a task in plain language.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `strale_capabilities_suggest`

Suggest Capability · Read-only

Find the best capability or solution for a task described in plain language.
Returns an object with recommendation, alternatives, total_matches, query_understood_as.
Use strale_capabilities_suggest to pick a capability for a task. Use strale_capabilities_typeahead for a fast keyword match on names.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): What you want to do, in plain language. Example: check if a company is on a sanctions list
- `limit` (`integer`, optional): Maximum number of alternatives to return. Example: 5

Example input: `{"query":"<query>"}`

### `strale_capabilities_typeahead`

Search Capabilities by Keyword · Read-only

Autocomplete capability and solution names from a keyword.
Returns an object with matches.
Use strale_capabilities_typeahead for a quick name lookup. Use strale_capabilities_suggest to match a full task description.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `q` (`string`, required): Keyword to match, at least 2 characters (only the first 200 are used). Example: vat
- `geo` (`string`, optional): Geography filter, such as a country code. Example: SE
- `limit` (`integer`, optional): Maximum matches to return, 1 to 10 (default 6). Example: 6
- `type` (`string`, optional): Limit matches to capabilities or solutions. One of: capability, solution. Example: capability. One of: `capability`, `solution`.

Example input: `{"q":"<q>"}`

### `strale_capability_get`

Get Capability · Read-only

Get one capability by its slug, including its input and output schema, price and data source.
Returns an object with slug, name, description, category, price_cents, input_schema, output_schema, transparency_tag, geography, data_source, and more.
Use strale_capability_get before strale_capability_execute to learn which inputs a capability needs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `slug` (`string`, required): Capability slug from strale_capabilities_list or strale_capabilities_suggest. Example: iban-validate

Example input: `{"slug":"<slug>"}`

### `strale_capability_limitations_get`

Get Capability Limitations · Read-only

Get the documented limitations of one capability, such as coverage gaps and known failure cases.
Returns the JSON response from the API.
Use strale_capability_limitations_get to judge whether a capability fits your input before running it.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `slug` (`string`, required): Capability slug. Example: iban-validate

Example input: `{"slug":"<slug>"}`

### `strale_solution_get`

Get Solution · Read-only

Get one bundled solution by slug, including its steps, inputs and price.
Returns an object with slug, name, description, category, price_cents, step_count, geography, transparency_tag, compliance_coverage, search_tags, and more.
Use strale_solution_get before strale_solution_execute to learn which inputs a solution needs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `slug` (`string`, required): Solution slug from strale_solutions_list. Example: kyb-essentials-se

Example input: `{"slug":"<slug>"}`

### `strale_solutions_list`

List Solutions · Read-only

List active bundled solutions (multi-step workflows built from capabilities) with pricing and step counts.
Returns an object with solutions, total.
Use strale_solutions_list to browse solutions. Use strale_capabilities_list for single capabilities.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `category` (`string`, optional): Category slug to filter by. Example: compliance

Example input: `{}`

### `strale_transaction_dispute_get`

Get Transaction Dispute · Read-only

Get the dispute filed on a transaction, if any.
Returns the JSON response from the API.
Use strale_transaction_dispute_get to check a dispute you filed with strale_transaction_dispute_create.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `transaction_id` (`string`, required): Transaction ID (UUID). Example: 3f2b1c4d-5e6f-4a1b-9c8d-7e6f5a4b3c2d

Example input: `{"transaction_id":"<transaction_id>"}`

### `strale_transaction_get`

Get Transaction · Read-only

Get one capability run, including its inputs, output, price and provenance.
Returns an object with id, status, capability_slug, output, error, price_cents, latency_ms, provenance, transparency_marker, data_jurisdiction, and more.
Use strale_transaction_get to read a run returned by strale_transactions_list or strale_capability_execute.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `transaction_id` (`string`, required): Transaction ID (UUID). Example: 3f2b1c4d-5e6f-4a1b-9c8d-7e6f5a4b3c2d

Example input: `{"transaction_id":"<transaction_id>"}`

### `strale_transaction_verify`

Verify Transaction · Read-only

Check the integrity chain of a transaction record.
Returns an object with transaction_id, verified, hash_valid, chain, transaction_metadata, methodology_url.
Use strale_transaction_verify to confirm a run record has not been altered.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `transaction_id` (`string`, required): Transaction ID (UUID). Example: 3f2b1c4d-5e6f-4a1b-9c8d-7e6f5a4b3c2d
- `depth` (`integer`, optional): Max chain depth to verify (default 20, max 50). F-A-012: values >50 are clamped to 50. Example: 20

Example input: `{"transaction_id":"<transaction_id>"}`

### `strale_transactions_list`

List Transactions · Read-only

List the capability runs made by this account.
Returns an object with transactions.
Use strale_transactions_list to find a run. Use strale_transaction_get for one run in full.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `strale_wallet_balance_get`

Get Wallet Balance · Read-only

Get the prepaid wallet balance of the account.
Returns balance_cents and currency.
Use strale_wallet_balance_get to check funds before running paid capabilities.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `strale_wallet_transactions_list`

List Wallet Transactions · Read-only

List wallet top-ups and credits.
Returns an object with transactions.
Use strale_wallet_transactions_list for money added to the wallet. Use strale_transactions_list for capability runs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `strale_capability_execute`

Execute Capability · Write

Run a Strale capability, either by its slug with its inputs or by describing the task in plain language. Paid capabilities are charged to the wallet.
Returns result (status, output, price_cents, provenance) plus meta and usage. With dry_run true it returns the matched capability without running it.
Use strale_capability_execute to run a single capability. Use strale_solution_execute to run a bundled multi-step solution.
Call strale_capability_get first to see the inputs a capability expects.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `callback_url` (`string`, optional): Public https URL that receives one signed POST when an asynchronous job finishes. Example: https://example.com/strale-callback
- `capability_slug` (`string`, optional): Slug of the capability to run. Give this or task. Example: iban-validate
- `dry_run` (`boolean`, optional): If true, returns the matched capability and its price without running it. Example: true
- `inputs` (`object`, optional): Capability-specific inputs as a JSON object, matching the capability input_schema. Example: {"iban": "DE89370400440532013000"}
- `max_price_cents` (`integer`, optional): Highest price you accept for this call, in EUR cents. Required for paid capabilities when calling with an API key. Example: 10
- `task` (`string`, optional): Plain-language description of what to do; Strale picks and runs the best matching capability. Give this or capability_slug. Example: Validate the IBAN DE89370400440532013000
- `timeout_seconds` (`integer`, optional): Execution budget for a synchronous paid call, in seconds. Example: 30

Example input: `{}`

### `strale_solution_execute`

Execute Solution · Write

Run a bundled solution with its inputs. The run is charged to the wallet.
Returns the JSON response from the API.
Use strale_solution_execute for a multi-step workflow. Use strale_capability_execute for a single capability.
Call strale_solution_get first to see the inputs the solution expects.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `inputs` (`object`, required): Solution inputs as a JSON object. Example: {"org_number": "5560125790"}
- `slug` (`string`, required): Solution slug from strale_solutions_list. Example: kyb-essentials-se
- `max_price_cents` (`integer`, optional): Highest price you accept for this run, in EUR cents. Example: 200

Example input: `{"inputs":{"org_number":"5560125790"},"slug":"<slug>"}`

### `strale_transaction_dispute_create`

Dispute Transaction · Write

Submit a dispute about a capability result for human review.
Returns the JSON response from the API.
Use strale_transaction_dispute_create when a run returned wrong or harmful data.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `reason` (`string`, required): Why the result is wrong. Example: The company address in the output is outdated.
- `transaction_id` (`string`, required): Transaction ID (UUID) to dispute. Example: 3f2b1c4d-5e6f-4a1b-9c8d-7e6f5a4b3c2d
- `affected_field` (`string`, optional): Output field the dispute is about. Example: address
- `contact_email` (`string`, optional): Email address for follow-up. Example: jane@example.com

Example input: `{"reason":"<reason>","transaction_id":"<transaction_id>"}`

### `strale_web3_assurance_check`

Check On-chain Counterparty · Write

Get a decision-ready verdict (proceed, review, block or insufficient_evidence) on an on-chain counterparty: a wallet, contract, token, DeFi protocol or bridge. The check is charged to the wallet.
Returns an object with target, target_type, chain, mode, verdict, reason_codes, confidence, evidence_completeness, evidence_status, critical_flags, and more.
Use strale_web3_assurance_check before sending funds to or interacting with an on-chain address.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `target` (`string`, required): Wallet address, contract, token, protocol or bridge to check. Example: 0x742d35Cc6634C0532925a3b844Bc454e4438f44e
- `action` (`string`, optional): What you plan to do with the target. One of: send_payment, swap, stake, mint, interact, bridge. Example: send_payment. One of: `send_payment`, `swap`, `stake`, `mint`, `interact`, `bridge`.
- `agent_id` (`string`, optional): Optional ERC-8004 agent identifier. Example: agent-42
- `amount_usd` (`number`, optional): Value of the planned action in US dollars; larger amounts get stricter checks. Example: 500
- `caller_jurisdiction` (`string`, optional): Optional ISO country code (US, EU, UK, etc.). Adds a jurisdiction-specific note to mixer findings; it does not change the verdict. Example: US
- `chain` (`string`, optional): Blockchain the target lives on. Example: ethereum
- `mode` (`string`, optional): Check mode: outbound (default) vets a recipient before you pay or interact, with every check; reverse-call gates an inbound buyer in real time with critical checks only. Example: outbound One of: outbound, reverse-call. One of: `outbound`, `reverse-call`.
- `target_type` (`string`, optional): What the target is, if known; Strale detects it when left empty. One of: wallet, contract, token, protocol, bridge, domain. Example: wallet. One of: `wallet`, `contract`, `token`, `protocol`, `bridge`, `domain`.

Example input: `{"target":"<target>"}`

## Related

Other AI connectors ([all 216](/agentkit/connectors/?category=ai)):

- [Chorus](/agentkit/connectors/chorus/): Scalekit connector, Username and password, 9 tools
- [Gong](/agentkit/connectors/gong/): Scalekit connector, OAuth, 69 tools
- [Jiminny](/agentkit/connectors/jiminny/): Scalekit connector, Access token, 27 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
