Sign in Book a demo
Back to Tools
Customer Support API Key
Build Your Agent View Pylon Documentation
pylon logo

Pylon MCP Tools for AI Agents

Let an agent search Pylon issues, read ticket details, assign work, update status, and add internal notes.

Available Tools

15 tools available in this integration

Pylon.AddInternalNote

Add an internal note to a Pylon issue.

Pylon.AssignIssue

Assign a Pylon issue to a user.

Pylon.CreateInternalNote

Add an internal note to a Pylon issue.

Pylon.GetIssue

Get detailed information about a Pylon issue.

Pylon.GetTeam

Get detailed information about a Pylon team including members.

Pylon.GetTeamAndAssignment

Get detailed information about a Pylon team including members.

Pylon.ListContacts

List contacts in Pylon.

Pylon.ListIssues

List Pylon issues with optional filtering by state, assignee, team, and tags.

Pylon.ListTeams

List all teams in the Pylon workspace.

Pylon.ListUsers

List all users/team members in the Pylon workspace.

Pylon.SearchContacts

Search for contacts by name or email using fuzzy matching.

Pylon.SearchIssues

Search issues recently created by keywords in title and description.

Pylon.SearchUsers

Search for users by name using fuzzy matching.

Pylon.UpdateIssueStatus

Change the state of a Pylon issue.

Pylon.WhoAmI

Get the authenticated user's profile.

Working directly against the raw API? 82 more tools in the Pylon API server →

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find unresolved billing issues, inspect the details, and assign each to the right teammate." Arcade picks the right Pylon actions without guessing issue, user, or team identifiers.

Up to 100x fewer tokens

Pylon list and search results return the issue, contact, user, or team records needed for triage, while detailed issue and team data is fetched only when requested, so the agent avoids loading an entire support workspace.

Complete the workflow end to end

Search an issue, inspect its details, identify the right teammate, add an internal note, and update its status through one toolkit designed around the complete support issue task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Pylon

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Pylon, you can implement some of these policies:

Access when tools are listed for a user
  • Hide Pylon.AddInternalNote from agents outside the roles your IDP marks as support leads, so unapproved automation cannot add internal commentary to customer issues.
  • Restrict Pylon.AssignIssue to agents operating under your support-management role, so an agent cannot redirect ownership of a customer issue without the right authority.
  • Deny Pylon.UpdateIssueStatus to agents outside the roles your IDP marks as issue managers, so routine agents cannot close, reopen, or otherwise change the state of customer issues.
  • Hide Pylon.CreateInternalNote from agents assigned the read-only investigation role, so an investigation cannot alter the customer record.
Pre-execution before each tool call
  • Require human approval before Pylon.AddInternalNote runs when the note contains customer data, credentials, or an external case reference, so sensitive details cannot be added to the internal record without review.
  • Block Pylon.AssignIssue when the target user is outside the issue's team or your approved escalation roster, so an agent cannot send a customer issue to an unauthorized owner.
  • Require human approval before Pylon.UpdateIssueStatus changes an issue to a closed or resolved state, so an agent cannot end customer follow-up without a person confirming the outcome.
  • Require human approval before Pylon.CreateInternalNote runs on notes mentioning refunds, credits, or SLA commitments, so an agent cannot commit your support team to a customer-facing outcome without review.
Post-execution after the tool returns
  • Redact customer email addresses, phone numbers, and message bodies from Pylon.GetIssue results before they reach the model.
  • Strip personal email addresses and phone numbers from Pylon.ListContacts results, so the model receives contact records without direct contact details.
  • Redact personal email addresses and phone numbers from Pylon.ListUsers results, leaving names and workspace roles available without exposing private contact data.
  • Redact member email addresses, phone numbers, and profile identifiers from Pylon.GetTeam results before the model sees the team roster.

How to use Pylon with your agent

Connect Pylon to an MCP client through Arcade, then give your agent authenticated access to issues, teams, users, and contacts.

Your questions, answered

A Pylon MCP server exposes Pylon capabilities as structured tools that an AI agent can call through the Model Context Protocol. With a configured Pylon API key or secret, an agent can search and inspect issues, contacts, teams, and users, then update supported issue fields.

Arcade provides a managed MCP gateway and an agent-optimized set of Pylon actions instead of requiring you to wire an agent directly to Pylon's API. It also adds authentication brokering, approval workflows, redaction, and controls for which actions an agent can access.

Arcade agents can list, search, and inspect issues; filter issues by state, assignee, team, or tags; list and search contacts and users; inspect teams; assign issues; add internal notes; and update issue status. They can also identify the authenticated Pylon user, but these tools do not cover every Pylon API operation such as creating new issues.

Pylon access uses a shared API key or secret configured once for the integration. The actions can reach whatever workspace and permissions that credential grants; Arcade does not turn it into separate per-user Pylon permissions.

No. Users do not each connect their own Pylon account through OAuth. One shared API key or secret is configured for the integration, brokered by Arcade rather than passed to the model, so calls use the access granted to that credential.

Yes. Contextual Access policies can require human approval before consequential Pylon actions such as assigning an issue, adding an internal note, or changing issue status. The call proceeds only after the policy's conditions are satisfied.

Arcade proxies Pylon API calls and does not persist your Pylon content as part of normal tool execution. The shared API key or secret is brokered and stored encrypted at rest, and the model never receives the credential.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works with Arcade Pylon, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade can continue refreshing access while the configured Pylon credential remains valid. If the key or secret is revoked, rotated, expires, or can no longer be used, calls stop until you reconnect or replace the credential.

Pylon's API rate limits and any workspace or account quotas apply to calls made through Arcade. Arcade does not remove those limits; the effective allowance depends on the Pylon credential and plan you use.

Ready to actually ship your agent?

Connect your agent to Pylon with a shared API key, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Pylon Quickstart