Execute real-time actions with ActionKit

Take real-time actions across users’ 3rd-party applications without worrying about authentication or endpoint maintenance.

Scale integration actions across every use case.

Scale integration actions across every use case.

Scale integration actions across every use case.

AI Agents

Workflow Products

Real-time CRUD

AI Agent Tool Calling

Equip your AI agent with hundreds of integration actions with one API call (or the ActionKit MCP server)

Agent-optimized tool descriptions

Implement via API or MCP server

Learn more

Your AI agent

YU

Your User

Can you send Jeff at Pied Piper an email to schedule time for a pricing call?

Your AI agent

TOOL: Search_Contacts

TOOL: Get_Calendar_Availability

Here's a draft to jeff@piedpiper.com to discuss pricing:

"Hi Jeff,
Would love to schedule time to go over pricing with you.
Are you free on Wednesday between 2-4pm PT?
Cheers,
User"

Good to send?

https://yourapp.ai

AI Agents

Workflow Products

Real-time CRUD

AI Agent Tool Calling

Equip your AI agent with hundreds of integration actions with one API call (or the ActionKit MCP server)

Agent-optimized tool descriptions

Implement via API or MCP server

Learn more

Your AI agent

YU

Your User

Can you send Jeff at Pied Piper an email to schedule time for a pricing call?

Your AI agent

TOOL: Search_Contacts

TOOL: Get_Calendar_Availability

Here's a draft to jeff@piedpiper.com to discuss pricing:

"Hi Jeff,
Would love to schedule time to go over pricing with you.
Are you free on Wednesday between 2-4pm PT?
Cheers,
User"

Good to send?

https://yourapp.ai

AI Agents

Workflow Apps

CRUD

AI Agent Tool Calling

Equip your AI agent with hundreds of integration actions with one API call (or the ActionKit MCP server)

Agent-optimized tool descriptions

Implement via API or MCP server

Learn more

Your AI agent

YU

Your User

Can you send Jeff at Pied Piper an email to schedule time for a pricing call?

Your AI agent

TOOL: Search_Contacts

TOOL: Get_Calendar_Availability

Here's a draft to jeff@piedpiper.com to discuss pricing:

"Hi Jeff,
Would love to schedule time to go over pricing with you.
Are you free on Wednesday between 2-4pm PT?
….

https://yourapp.ai

AI Agents

Workflow Products

Real-time CRUD

AI Agent Tool Calling

Equip your AI agent with hundreds of integration actions with one API call (or the ActionKit MCP server)

Agent-optimized tool descriptions

Implement via API or MCP server

Learn more

Your AI agent

YU

Your User

Can you send Jeff at Pied Piper an email to schedule time for a pricing call?

Your AI agent

TOOL: Search_Contacts

TOOL: Get_Calendar_Availability

Here's a draft to jeff@piedpiper.com to discuss pricing:

"Hi Jeff,
Would love to schedule time to go over pricing with you.
Are you free on Wednesday between 2-4pm PT?
Cheers,
User"

Good to send?

https://yourapp.ai

Appsmith needed a more scalable way to scale integrations for their AI agent, workflow automation, and dashboard component products, and made ActionKit the center of their re-architecture to achieve their goals.

Appsmith ships integrations 11x faster with ActionKit

Appsmith needed a more scalable way to scale integrations for their AI agent, workflow automation, and dashboard component products, and made ActionKit the center of their re-architecture to achieve their goals.

Appsmith ships integrations 11x faster with ActionKit

Appsmith needed a more scalable way to scale integrations for their AI agent, workflow automation, and dashboard component products, and made ActionKit the center of their re-architecture to achieve their goals.

Appsmith ships integrations 11x faster with ActionKit

Appsmith needed a more scalable way to scale integrations for their AI agent, workflow automation, and dashboard component products, and made ActionKit the center of their re-architecture to achieve their goals.

Appsmith ships integrations 11x faster with ActionKit

Placeholder

One API for 300+ integration actions

ActionKit provides a uniform interface for interacting with 3rd-party APIs.

Managed authentication for every integration and action

Paragon handles any 3rd-party breaking changes

All actions support user-level custom objects & fields

Placeholder

{
  "actions": {
    "hubspot": [{
      "type": "function",
      "function": {
        "name": "HUBSPOT_CREATE_RECORD_CONTACTS",
        "description": "Create a contact in HubSpot CRM",
        "parameters": {
          "type": "object",
          "properties": {
            "field-email": {
              "type": "string",
              "description": "Email"
            },
            "field-firstname": {
              "type": "string",
              "description": "First Name"
            },
            "field-lastname": {
              "type": "string",
              "description": "Last Name"
            },
            "field-jobtitle": {
              "type": "string",
              "description": "Job Title"
            },
            "field-company": {
              "type": "string",
              "description": "Company Name"
            },
            "field-hubspot_owner_id": {
              "type": "string",
              "description": "Contact Owner: The HubSpot user who is assigned to this contact. Use Connect Portal Workflow Settings to allow users to select an Owner. (example value: \\"{{settings.owner}}\\")"
            },
            "field-lifecyclestage": {
              "type": "string",
              "description": "Lifecycle Stage: Defaults to the user’s first Lifecycle Stage if not provided. Use Connect Portal Workflow Settings to allow users to select a Lifecycle Stage. (example value: \\"{{settings.lifecycleStage}}\\")"
            },
            "field-hs_lead_status": {
              "type": "string",
              "description": "Lead Status: Defaults to the user’s first Lead Status if not provided. Use Connect Portal Workflow Settings to allow users to select a Lead Status. (example value: \\"{{settings.leadStatus}}\\")"
            },
            "additionalFieldsJSON": {
              "type": "string",
              "description": "Additional Fields: Specify any other fields that should be updated in JSON below. Use Connect Portal Workflow Settings to allow users to select which Contact fields to update. (example value: \\"{\\n  \\"property_number\\": \\"17\\",\\n  \\"property_dropdown\\": \\"choice_b\\",\\n  \\"property_radio\\": \\"option_1\\",\\n  \\"property_string\\": \\"value\\",\\n  \\"property_date\\": \\"1572480000000\\"\\n}\\")"
            }
          },
          "required": [
            "recordType",
            "field-email"
          ],
          "additionalProperties": false,
          "$schema": ""
        }
      }
    }]
  },
  "errors": []
}

Placeholder

Interface via the API or MCP server

Whether you need deterministic or agentic integration functionality, ActionKit can be implemented with just a few lines of code.

API

MCP

// OpenAI SDK

import requests

from openai import OpenAI

client = OpenAI()


actions_url = f"https://actions.useparagon.com/projects/{project_id}/actions"

get_actions_params = {

"categories": "crm,project_management"

}

response = requests.get(actions_url, params=params, headers=actions_auth_header)

paragon_tools = response.json()

messages = [{"role": "user", "content": "Help me create a Jira ticket"}]

completion = client.chat.completions.create(

model="gpt-4o",

messages=messages,

tools=paragon_tools,

tool_choice="auto"

)

API

MCP

// OpenAI SDK

import requests

from openai import OpenAI

client = OpenAI()


actions_url = f"https://actions.useparagon.com/projects/{project_id}/actions"

get_actions_params = {

"categories": "crm,project_management"

}

response = requests.get(actions_url, params=params, headers=actions_auth_header)

paragon_tools = response.json()

messages = [{"role": "user", "content": "Help me create a Jira ticket"}]

completion = client.chat.completions.create(

model="gpt-4o",

messages=messages,

tools=paragon_tools,

tool_choice="auto"

)

API

MCP

// OpenAI SDK

import requests

from openai import OpenAI

client = OpenAI()


actions_url = f"https://actions.useparagon.com/projects/{project_id}/actions"

get_actions_params = {

"categories": "crm,project_management"

}

response = requests.get(actions_url, params=params, headers=actions_auth_header)

paragon_tools = response.json()

messages = [{"role": "user", "content": "Help me create a Jira ticket"}]

completion = client.chat.completions.create(

model="gpt-4o",

messages=messages,

tools=paragon_tools,

tool_choice="auto"

)

API

MCP

// OpenAI SDK

import requests

from openai import OpenAI

client = OpenAI()


actions_url = f"https://actions.useparagon.com/projects/{project_id}/actions"

get_actions_params = {

"categories": "crm,project_management"

}

response = requests.get(actions_url, params=params, headers=actions_auth_header)

paragon_tools = response.json()

messages = [{"role": "user", "content": "Help me create a Jira ticket"}]

completion = client.chat.completions.create(

model="gpt-4o",

messages=messages,

tools=paragon_tools,

tool_choice="auto"

)

Scale your integration roadmap

Join hundreds of SaaS companies that are scaling their integration roadmaps with Paragon

Scale your integration roadmap

Join hundreds of SaaS companies that are scaling their integration roadmaps with Paragon

Scale your integration roadmap

Join hundreds of SaaS companies that are scaling their integration roadmaps with Paragon

Scale your integration roadmap

Join hundreds of SaaS companies that are scaling their integration roadmaps with Paragon