Connector Setup Guides

Copy

• Copy for LLM

  Copy page as Markdown for LLMs
• View as Markdown

  Open this page as Markdown
• Open in ChatGPT

  Get insights from ChatGPT
• Open in Claude

  Get insights from Claude

GitHub

Prerequisites

• GitHub account
• Repository access

Step 1: Generate Personal Access Token

1. Go to GitHub Settings → Developer Settings → Personal Access Tokens
2. Click "Generate new token (classic)"
3. Name: Freddy AI Integration
4. Select scopes:
   • ✅ repo - Full control of private repositories
   • ✅ read:org - Read organization data
   • ✅ workflow - Update GitHub Actions workflows
5. Click "Generate token"
6. Copy the token (starts with ghp_)

Step 2: Configure in Freddy

curl https://api.freddy.aitronos.com/v1/personal-connectors/configurations \
  -H "api-key: $FREDDY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "connectorId": "github",
    "name": "My GitHub",
    "configuration": {
      "defaultRepo": "username/repository"
    },
    "credentials": {
      "token": "ghp_your_token_here"
    }
  }'

Step 3: Test Connection

curl -X POST https://api.freddy.aitronos.com/v1/personal-connectors/configurations/{config_id}/test \
  -H "api-key: $FREDDY_API_KEY"

Expected response:

{
  "configurationId": "pconf_abc123",
  "status": "healthy",
  "message": "Connection successful"
}

Available Tools

Once configured, your assistant can:

• Create issues
• List issues and pull requests
• Create pull requests
• Add comments
• Manage labels
• Search repositories

ClickUp

Prerequisites

• ClickUp account
• Workspace access

Step 1: Generate API Token

1. Go to ClickUp Settings → Apps
2. Scroll to "API Token"
3. Click "Generate" or "Regenerate"
4. Copy your API token (starts with pk_)

Step 2: Get Workspace and List IDs

1. Open ClickUp and navigate to your workspace
2. Click on a list
3. Copy the list ID from the URL: https://app.clickup.com/{workspace_id}/v/li/{list_id}

Step 3: Configure in Freddy

curl https://api.freddy.aitronos.com/v1/personal-connectors/configurations \
  -H "api-key: $FREDDY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "connectorId": "clickup",
    "name": "My ClickUp",
    "configuration": {
      "workspaceId": "12345678",
      "defaultListId": "987654321"
    },
    "credentials": {
      "apiKey": "pk_your_clickup_api_key"
    }
  }'

Available Tools

• Create tasks
• List tasks
• Update tasks
• Delete tasks
• Add comments
• Manage priorities

Jira

Prerequisites

• Atlassian account
• Jira project access

Step 1: Generate API Token

1. Go to Atlassian Account Settings
2. Click "Create API token"
3. Label: Freddy AI
4. Click "Create"
5. Copy the token

Step 2: Get Your Jira Details

• Domain: Your Jira site URL (e.g., yourcompany.atlassian.net)
• Email: Your Atlassian account email
• Project Key: Found in your project settings

Step 3: Configure in Freddy

curl https://api.freddy.aitronos.com/v1/personal-connectors/configurations \
  -H "api-key: $FREDDY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "connectorId": "jira",
    "name": "My Jira",
    "configuration": {
      "domain": "yourcompany.atlassian.net",
      "defaultProject": "PROJ"
    },
    "credentials": {
      "email": "your.email@company.com",
      "apiToken": "your_jira_api_token"
    }
  }'

Available Tools

• Create issues
• List issues (with JQL support)
• Update issues
• Transition issues (change status)
• Add comments
• Manage assignees

Microsoft Teams (Coming Soon)

OAuth integration for Microsoft Teams is coming soon.

Custom MCP Server

Prerequisites

• Running MCP server
• Server URL and credentials

Step 1: Prepare Your MCP Server

Your server must implement the MCP protocol:

# Example MCP server endpoints
GET  /mcp/tools      # List available tools
POST /mcp/execute    # Execute a tool
GET  /health         # Health check

Step 2: Configure in Freddy

curl https://api.freddy.aitronos.com/v1/personal-connectors/configurations \
  -H "api-key: $FREDDY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "connectorId": "custom",
    "name": "My Custom Server",
    "configuration": {
      "serverUrl": "https://my-mcp-server.com",
      "serverType": "http"
    },
    "credentials": {
      "apiKey": "your_custom_api_key"
    }
  }'

MCP Protocol Requirements

Your server must respond to:

GET /mcp/tools

{
  "tools": [
    {
      "name": "my_tool",
      "description": "Tool description",
      "inputSchema": {
        "type": "object",
        "properties": {
          "param1": { "type": "string" }
        },
        "required": ["param1"]
      }
    }
  ]
}

POST /mcp/execute

{
  "tool": "my_tool",
  "arguments": { "param1": "value" },
  "_credentials": { "apiKey": "..." }
}

GET /health

{
  "status": "healthy"
}

Troubleshooting

Configuration Fails Validation

Error: Failed to validate credentials

Solutions:

1. Verify token/API key is correct
2. Check token hasn't expired
3. Ensure token has required permissions
4. Test token directly with service API

Configuration Shows "Unhealthy"

Error: Configuration created but marked unhealthy

Solutions:

1. Check lastError field for details
2. Test connection manually
3. Verify service is accessible
4. Update credentials if expired

Tools Not Discovered

Error: No tools available

Solutions:

1. Refresh tool cache: POST /configurations/{id}/refresh
2. Check MCP server is responding
3. Verify server implements /mcp/tools endpoint
4. Check server logs for errors

Next Steps

• Use connectors with AI assistants
• Monitor usage and costs
• API Reference