Give agents tools for secure, real-time access to fetch, search, write, and sync across every system, with replication, entity mapping, and auth built-in.
About this Connector
Pylon is a customer support platform that helps B2B companies manage customer interactions across Slack, email, chat widgets, and other channels. This connector provides access to issues, accounts, contacts, teams, tags, users, custom fields, ticket forms, and user roles for customer support analytics and account intelligence insights.
CRM
Sales Analytics
Customer Data
Version Information
Package version
0.1.9
Connector version
0.1.9
SDK commit
unknown
Support Open Source
Check us out on Github and join the Airbyte community
Installation & Usage
1
Install Package
Using uv or pip
bash
uv pip install airbyte-agent-sdk
2
Import
Initialize and use
python
from airbyte_agent_sdk.connectors.pylon import PylonConnector
from airbyte_agent_sdk.connectors.pylon.models import PylonAuthConfig
connector = PylonConnector(
auth_config=PylonAuthConfig(
api_token="<Your Pylon API token. Only admin users can create API tokens.>"
)
)3
Tool
Add tools to your agent
python
@agent.tool_plain # assumes you're using Pydantic AI
@PylonConnector.tool_utils
async def pylon_execute(entity: str, action: str, params: dict | None = None):
return await connector.execute(entity, action, params or {})Supported Entities & Actions
Lorem ipsum
Lorem ipsum
| Entity | Actions |\n|--------|---------|\n| Issues | [List](./REFERENCE.md#issues-list), [Create](./REFERENCE.md#issues-create), [Get](./REFERENCE.md#issues-get), [Update](./REFERENCE.md#issues-update), [Delete](./REFERENCE.md#issues-delete), [Context Store Search](./REFERENCE.md#issues-context-store-search) |\n| Issue Replies | [Create](./REFERENCE.md#issue-replies-create) |\n| Issue Assignments | [Update](./REFERENCE.md#issue-assignments-update) |\n| Issue Statuses | [Update](./REFERENCE.md#issue-statuses-update) |\n| Messages | [List](./REFERENCE.md#messages-list), [Context Store Search](./REFERENCE.md#messages-context-store-search) |\n| Issue Notes | [Create](./REFERENCE.md#issue-notes-create) |\n| Issue Threads | [Create](./REFERENCE.md#issue-threads-create) |\n| Accounts | [List](./REFERENCE.md#accounts-list), [Create](./REFERENCE.md#accounts-create), [Get](./REFERENCE.md#accounts-get), [Update](./REFERENCE.md#accounts-update), [Context Store Search](./REFERENCE.md#accounts-context-store-search) |\n| Contacts | [List](./REFERENCE.md#contacts-list), [Create](./REFERENCE.md#contacts-create), [Get](./REFERENCE.md#contacts-get), [Update](./REFERENCE.md#contacts-update), [Context Store Search](./REFERENCE.md#contacts-context-store-search) |\n| Teams | [List](./REFERENCE.md#teams-list), [Create](./REFERENCE.md#teams-create), [Get](./REFERENCE.md#teams-get), [Update](./REFERENCE.md#teams-update), [Context Store Search](./REFERENCE.md#teams-context-store-search) |\n| Tags | [List](./REFERENCE.md#tags-list), [Create](./REFERENCE.md#tags-create), [Get](./REFERENCE.md#tags-get), [Update](./REFERENCE.md#tags-update), [Context Store Search](./REFERENCE.md#tags-context-store-search) |\n| Users | [List](./REFERENCE.md#users-list), [Get](./REFERENCE.md#users-get), [Context Store Search](./REFERENCE.md#users-context-store-search) |\n| Custom Fields | [List](./REFERENCE.md#custom-fields-list), [Get](./REFERENCE.md#custom-fields-get), [Context Store Search](./REFERENCE.md#custom-fields-context-store-search) |\n| Ticket Forms | [List](./REFERENCE.md#ticket-forms-list), [Context Store Search](./REFERENCE.md#ticket-forms-context-store-search) |\n| User Roles | [List](./REFERENCE.md#user-roles-list), [Context Store Search](./REFERENCE.md#user-roles-context-store-search) |\n| Tasks | [Create](./REFERENCE.md#tasks-create), [Update](./REFERENCE.md#tasks-update) |\n| Projects | [Create](./REFERENCE.md#projects-create), [Update](./REFERENCE.md#projects-update) |\n| Milestones | [Create](./REFERENCE.md#milestones-create), [Update](./REFERENCE.md#milestones-update) |\n| Articles | [Create](./REFERENCE.md#articles-create), [Update](./REFERENCE.md#articles-update) |\n| Collections | [Create](./REFERENCE.md#collections-create) |\n| Me | [Get](./REFERENCE.md#me-get) |
Example Prompts
Lorem ipsum
List all open issues in Pylon - Show me all accounts in Pylon - List all contacts in Pylon - What teams are configured in my Pylon workspace? - Show me all tags used in Pylon - List all users in my Pylon account - Show me the custom fields configured for issues - List all ticket forms in Pylon - What user roles are available in Pylon? - Show me details for a specific issue - Get details for a specific account - Show me details for a specific contact - Reply to the customer on an issue saying we are looking into it - Send a message to the customer on the billing issue - Assign an issue to a specific team member - Change the status of an issue to waiting_on_customer - Close an issue as resolved - Delete a test issue - What are the most common issue sources this month? - Show me issues assigned to a specific team - Which accounts have the most open issues? - Analyze issue resolution times over the last 30 days - List contacts associated with a specific account
Why Airbyte for AI Agents?
Built for production AI workloads with enterprise-grade reliability
Agent-Native Design
Structured, LLM-friendly schemas optimized for AI agent consumption with natural language query support.
Secure Authentication
Built-in OAuth 2.0 handling with automatic token refresh. No hard-coded credentials.
Production Ready
Battle-tested connectors with comprehensive error handling, logging, and retry logic.
Open Source
Fully open source under the MIT license. Contribute, customize, and extend freely.
Works with your favorite frameworks
🦜
LangChain
🦙
LlamaIndex
🤖
CrewAI
⚡
AutoGen
🧠
OpenAI Agents SDK
🔮
Claude Agents SDK
Frequently Asked Questions
Didn't find your answer? Please don't hesitate to reach out.
The Pylon connector supports API token authentication in open source mode. You provide your Pylon API token directly (note: only admin users can create API tokens). In hosted mode, credentials are stored securely in Airbyte Cloud and you authenticate using your Airbyte client ID and client secret.
Can I use this connector with any AI agent framework?
The connector is compatible with any Python-based AI agent framework including LangChain, LlamaIndex, CrewAI, Pydantic AI, and custom implementations.
Does this connector support write operations?
Yes, the Pylon connector supports several write operations. These include creating and updating issues, replying to issues, updating issue assignments and statuses, deleting issues, creating and updating accounts, contacts, teams, tags, tasks, projects, milestones, articles, collections, and more. Notable unsupported write operations include deleting accounts and scheduling meetings with contacts.
How is this different from the Airbyte data connector?
Agent connectors are specifically designed for AI agents and LLM applications. They provide natural language interfaces, optimized response formats, and seamless integration with agent frameworks, unlike traditional ETL-focused connectors.
Will there be a platform for agent connectors?
The hosted version with secure credential storage through Airbyte Cloud is already available. See the hosted usage section in the documentation for setup instructions.