LeadBoxer MCP connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   .env

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Set up the connector

   Register your LeadBoxer MCP credentials with Scalekit so it handles the token lifecycle. You do this once per environment.

   Dashboard setup steps

   LeadBoxer MCP uses Dynamic Client Registration (DCR) with PKCE — no client ID or secret is needed. Scalekit automatically registers the OAuth client on first use and handles the full token lifecycle.

   1. Create a connection in Scalekit

      In the Scalekit dashboard, go to AgentKit > Connections > Create Connection. Find LeadBoxer MCP and click Create.

      Copy the redirect URI — it looks like https://<SCALEKIT_ENVIRONMENT_URL>/sso/v1/oauth/<CONNECTION_ID>/callback.

   2. Authorize the connection

      Use the redirect URI from Scalekit to initiate the OAuth 2.1 authorization flow. LeadBoxer MCP’s DCR endpoint will register Scalekit as a client automatically during this step.

      No manual app registration needed

      Because LeadBoxer MCP supports Dynamic Client Registration, you do not need to create an OAuth app in the LeadBoxer developer portal. Scalekit handles registration on your behalf.

   3. Verify the connection is active

      Back in the Scalekit dashboard, go to AgentKit > Connections and confirm the LeadBoxer MCP connection shows a status of Active.

4. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'leadboxermcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize LeadBoxer MCP:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'leadboxermcp_list_specs',
     toolInput: {},
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "leadboxermcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize LeadBoxer MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="leadboxermcp_list_specs",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Discover available APIs — list all OpenAPI specs published by LeadBoxer to understand what data is accessible
• Browse API endpoints — list all paths and HTTP methods for a spec, organized for quick lookup
• Inspect endpoint details — retrieve full parameter definitions, security schemes, and server info for any endpoint
• Search across endpoints — perform deep searches through paths, operations, and parameters to find relevant APIs
• Execute API requests — call any LeadBoxer API endpoint directly using a HAR request object

Common workflows

Get your cloud ID

Most LeadBoxer MCP tools require a cloudId — the UUID that identifies your Atlassian cloud site. Call leadboxermcp_getaccessibleatlassianresources once to retrieve it, then pass the id field value in every subsequent tool call.

Call this tool first

Run leadboxermcp_getaccessibleatlassianresources before calling any Jira or Confluence tool. The response lists every Atlassian site the user has access to. Use the id field as cloudId.

Node.js

// Step 1 — get the cloud ID
const resources = await actions.executeTool({
  connectionName: 'leadboxermcp',
  identifier: 'user_123',
  toolName: 'leadboxermcp_getaccessibleatlassianresources',
  toolInput: {},
});
const cloudId = resources[0].id;

// Step 2 — use cloudId in subsequent calls
const issue = await actions.executeTool({
  connectionName: 'leadboxermcp',
  identifier: 'user_123',
  toolName: 'leadboxermcp_getjiraissue',
  toolInput: {
    cloudId,
    issueIdOrKey: 'KAN-1',
  },
});
console.log(issue);

Python

# Step 1 — get the cloud ID
resources = actions.execute_tool(
    connection_name="leadboxermcp",
    identifier="user_123",
    tool_name="leadboxermcp_getaccessibleatlassianresources",
    tool_input={},
)
cloud_id = resources[0]["id"]

# Step 2 — use cloud_id in subsequent calls
issue = actions.execute_tool(
    connection_name="leadboxermcp",
    identifier="user_123",
    tool_name="leadboxermcp_getjiraissue",
    tool_input={
        "cloudId": cloud_id,
        "issueIdOrKey": "KAN-1",
    },
)
print(issue)

The leadboxermcp_getaccessibleatlassianresources response looks like this:

[
  {
    "id": "a4c9b3e2-1234-5678-abcd-ef0123456789",
    "name": "My Company",
    "url": "https://mycompany.atlassian.net",
    "scopes": ["read:jira-work", "write:jira-work", "read:confluence-content.all"]
  }
]

Use id as the cloudId parameter. If the user belongs to multiple Atlassian sites, the list contains one entry per site — pick the one matching the target url.

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

leadboxermcp_list_specs#Lists all available OpenAPI specs. Use the title to select a spec.0 params▾

Lists all available OpenAPI specs. Use the title to select a spec.

leadboxermcp_list_endpoints#Lists all API paths and their HTTP methods with summaries, organized by path. Results can be passed directly into 'get-endpoint'.1 param▾

Lists all API paths and their HTTP methods with summaries, organized by path. Results can be passed directly into 'get-endpoint'.

NameTypeRequiredDescription

titlestringrequiredTitle of the OpenAPI spec. Use tool 'list-specs' or 'search-endpoints' to see available specs.

leadboxermcp_get_endpoint#Gets detailed information about a specific API endpoint, including security schemes and servers.3 params▾

Gets detailed information about a specific API endpoint, including security schemes and servers.

NameTypeRequiredDescription

pathstringrequiredThe API endpoint path (e.g. /api/v1/users).

methodstringrequiredThe HTTP method (e.g. GET, POST, PUT, DELETE).

titlestringrequiredTitle of the OpenAPI spec.

leadboxermcp_search_endpoints#Performs a deep search through paths, operations, and parameters to discover relevant API endpoints.1 param▾

Performs a deep search through paths, operations, and parameters to discover relevant API endpoints.

NameTypeRequiredDescription

patternstringrequiredSearch pattern (case-insensitive).

leadboxermcp_execute_request#Executes an API request with a given HAR request object.2 params▾

Executes an API request with a given HAR request object.

NameTypeRequiredDescription

harRequestobjectrequiredHAR request object describing the API call to execute.

titlestringrequiredTitle of the OpenAPI spec.