--- title: "Pylon MCP server" url: "https://martechdb.com/vendors/pylon" markdown_url: "https://martechdb.com/vendors/pylon.md" api_url: "https://martechdb.com/api/v1/vendors/usepylon.com" updated: "2026-10-12" --- # Pylon MCP server Yes. Pylon publishes an official MCP server at https://mcp.usepylon.com/. It's hosted. It offers 99 tools. We last checked it on 1 Nov 2026. MartechDB lists only servers the vendor publishes itself, never community servers. **Key facts:** As of 1 Nov 2026, Pylon's official MCP server scores 65/100 (provisional) on MartechDB's Agent Readiness Index (v1.1). It answered 20 of our 20 checks in the last 90 days and has 99 tools named in its documentation. - Website: [usepylon.com](https://usepylon.com) - Categories: [Help desk & live chat](https://martechdb.com/categories/help-desk-live-chat.md) ## Review Pylon's Pylon MCP scores 65/100 on MartechDB's Agent Readiness Index: easy to connect an AI agent to, with a few gaps. The good: - Hosted by Pylon: connect by URL, with nothing to install - Documented, with 99 tools known - Answered 100% of our checks in the last 90 days Not checked yet: how you sign in; what agent access costs. ## Agent Readiness Index: 65/100 (provisional) How friendly Pylon is to AI agents, from its best official MCP server. Anything not yet researched scores nothing, so this score may rise once it is. Methodology v1.1: https://martechdb.com/methodology. - Official MCP server: 30/30 (Published by the vendor) - Hosted by the vendor: 25/25 (Connect by URL, nothing to install) - OAuth sign-in: pending (Sign-in: see vendor docs) - Documented tools: 10/10 (A docs page, and its tools are known) - Free to start, pay as you go: 0/15 (Not stated by the vendor) ## Pylon MCP - Address: https://mcp.usepylon.com/ - Runs: Hosted - Sign-in: Sign-in: see vendor docs (`unknown`) - Official MCP Registry: not listed - Documentation: https://docs.usepylon.com/pylon-docs/integrations/pylon-mcp - How we know it's official: Documented on Pylon's own site, at docs.usepylon.com - First seen: 2026-10-12 - Last checked: 2026-11-01 - Recent checks: 7 of the last 7 reachable - Uptime: 100% (20 of 20 checks reachable since 2026-10-13) ### Tools (99) The server needs sign-in before it lists its tools, so these are as the vendor's documentation names them ([source](https://docs.usepylon.com/pylon-docs/integrations/pylon-mcp)), read on 2026-10-30. They may be out of date. - `search_issues`: Search issues by keyword (titles, messages, tags, and names) and by state, account, assignee, tags, custom fields, etc. - `get_issue`: Fetch a single issue by ID or number; set include\_messages=true to include its conversation - `get_issue_messages`: Fetch an issue's full message history in order, including the original To and Cc recipients of email messages - `get_issue_statuses`: List the default and custom issue statuses configured for your organization - `create_issue`: Create an issue in your workspace with an initial internal note - `update_issue`: Update issue fields (status, assignee, team, priority, tags, custom fields, …); tags can be replaced or added and removed individually - `snooze_issue`: Snooze an issue until a future time. It moves to On hold and returns to Waiting on you when the snooze ends - `send_issue_reply`: Send a reply to the customer on an issue. For email issues, recipients follow reply-all - `send_issue_note`: Post an internal note on an issue, visible only to your team - `get_issue_threads`: List an issue's internal threads - `create_issue_thread`: Create an internal thread on an issue, optionally synced to an internal Slack channel - `get_issue_followers`: List an issue's followers - `update_issue_followers`: Add or remove teammates as followers of an issue - `link_product_issue`: Link a Linear, Jira, GitHub, Asana, or Shortcut ticket to an issue - `search_accounts`: Search accounts by name, domain, external ID, tags, custom fields, etc. - `get_account`: Fetch a single account, including custom field values - `create_account`: Create a new account - `update_account`: Update account fields - `upload_account_files`: Upload files (e.g. PDFs) to an account's Files tab - `create_attachment`: Upload a file and get back an attachment ID and URL - `get_account_notes`: List the notes in an account's Notes block, newest first - `save_account_note`: Create a timestamped account note or edit its title or HTML body - `search_contacts`: Search contacts by name, email, phone, account, and more - `get_contact`: Fetch a contact by ID - `save_contact`: Create a contact on an account, update an existing contact's name, account, or custom fields, or merge duplicate contacts - `search_users`: Search Pylon team members by name, or look one up by email - `get_user`: Fetch a Pylon team member by ID - `get_me`: Return the authenticated user and their organization - `search_teams`: Look up teams by name, or list all teams - `get_team`: Read a team's details, members, and subteams - `save_team`: Create a team, or update its name, icon, members, and subteams - `list_integration_user_mappings`: List CRM users, current mappings, and email-matched suggestions - `save_integration_user_mappings`: Map or unmap the specified CRM users - `list_knowledge_bases`: List the knowledge bases you can read - `list_collections`: List collections in a knowledge base - `get_collection`: Fetch a collection's details and visibility settings - `list_collection_contents`: List the articles and sub-collections directly inside a collection - `search_articles`: Full-text search across article titles and content - `get_article`: Fetch an article's content and visibility settings, by ID or by the identifier in its public URL; optionally include its images - `get_related_links`: List the tracked websites and external sites configured for your org - `save_draft_article`: Create a draft article, or save new draft content for an existing article without publishing - `publish_article`: Publish an article's content - `update_article_settings`: Change an article's visibility and AI agent access - `move_article_to_collection`: Move an article into a different collection - `search_feature_requests`: Search feature requests by status and other filters - `get_feature_request`: Fetch a feature request, including its evidence - `get_feature_request_statuses`: List the feature request statuses configured for your org - `save_feature_request`: Create a feature request with optional initial evidence, or update its title, description, status, or custom fields - `add_evidence_to_feature_request`: Record that a customer asked for an existing feature request, linking the issue or account - `merge_feature_requests`: Merge duplicate feature requests into one; evidence and linked tickets move over and the duplicates are archived - `search_tasks`: Search tasks across your organization, or for one account or project - `get_task`: Fetch a task, including its subtasks and 20 most recent comments - `get_task_statuses`: List the default and custom task statuses - `save_task`: Create a task or update only the fields you provide - `save_task_comment`: Add a task comment, or replace the body of a comment you authored - `delete_task`: Delete a task and its subtasks - `search_projects`: Search or list projects by name, account, owner, and status - `get_project`: Fetch a project's details and progress - `save_project`: Create a project for an account, optionally from a template, or update an existing project - `get_project_templates`: List project templates - `get_milestones`: List milestones for a project or account, or fetch one by ID - `save_milestone`: Create a milestone in a project or update an existing milestone - `search_call_recordings`: Search call recordings by title or account name, or by what was said during the call - `get_call_recording`: Fetch a recording's details, participants, summary, and full transcript, or list an account's recent recordings - `list_surveys`: List NPS, CSAT, and custom surveys - `get_survey_responses`: Fetch survey responses by survey or issue - `list_trigger_groups`: List trigger groups - `list_triggers`: List triggers with their kickoffs, actions, and firing statistics - `get_trigger`: Fetch a trigger's full configuration - `describe_trigger_kickoff`: List the available kickoff types, or describe one kickoff's supported conditions and actions - `describe_trigger_action`: List the available action types, or describe one action's variables and compatible kickoffs - `get_trigger_examples`: Example payloads for common trigger patterns - `validate_trigger`: Validate a save\_trigger payload without saving it - `save_trigger`: Create a disabled trigger, or replace an existing trigger's configuration - `list_macros`: List visible macro summaries and groups, with optional name search and group filtering - `get_macro`: Read stored HTML, text type, visibility, configured action types, and attachment summaries - `save_macro`: Create a text-only macro or edit an existing macro's name, message text, or text type - `delete_macro`: Permanently delete a macro, including its actions and attachments - `build_filter`: Build a validated filter for any object type - `get_filter_attributes`: Fields, operators, and reference types available when filtering an object type - `get_custom_fields`: List custom field definitions for an object type - `list_tags`: List issue, account, or knowledge base article tags, or look one up by exact value - `save_tag`: Create a tag, or rename or recolor an existing tag - `delete_tag`: Permanently delete a tag and remove it from everything it's applied to - `list_audit_log_actions`: Discover exact supported action names, regardless of recorded events - `search_audit_logs`: Search recorded actions and changes in your organization by object, action, and time - `submit_support_ticket`: Send a request about Pylon to Pylon's own support team - `list_agents`: Find the AI agent ID to test. - `list_agent_variations`: Find customer-visible variation IDs for an agent. - `list_backtest_datasets`: Find datasets and their case counts. - `create_backtest_dataset`: Create an empty dataset. - `add_issues_to_backtest_dataset`: Snapshot readable issues as cases (up to 100 per dataset). - `run_backtest`: Start asynchronous runs for one or more agent configurations. - `list_backtests`: Find customer backtests, their runs, and progress. - `get_backtest_results`: Get paginated progress and results for a backtest or run. - `get_backtest_case`: Compare every agent result for one case. - `get_playground`: Inspect the full message, tool, and event timeline for a result. - `get_agent_issue`: See an AI agent's full activity on a real issue: tool calls, runbook steps, escalations, messages, and outcomes. - `update_backtest_case_feedback`: Rate one case result thumbs up or thumbs down, or clear its rating. ### Connect it Claude Code: ```sh claude mcp add --transport http pylon https://mcp.usepylon.com/ ``` - Add to Cursor: - Add to VS Code: - Claude.ai and Claude Desktop: Customize, Connectors, "+", Add custom connector, then paste https://mcp.usepylon.com/ - ChatGPT: Settings, Apps, Advanced settings, turn on Developer mode, Create, then paste https://mcp.usepylon.com/ (this usually works only with servers that use self-serve sign-in or none) JSON for Cursor, Windsurf and other clients that connect to hosted servers: ```json { "mcpServers": { "pylon": { "type": "http", "url": "https://mcp.usepylon.com/" } } } ``` ## Questions ### Does Pylon have an official MCP server? Yes. Pylon publishes its MCP server itself. Pylon's own documentation describes it. MartechDB only lists servers a vendor publishes, never community copies. ### What is the Pylon MCP server URL? The address is https://mcp.usepylon.com/. ### How do I connect Pylon MCP to Claude, ChatGPT or Cursor? In Claude, add https://mcp.usepylon.com/ as a custom connector (Customize, Connectors, Add custom connector). In Cursor, use the Add to Cursor link on MartechDB's page, or paste the JSON settings into your mcp.json. In Claude Code, run: claude mcp add --transport http pylon https://mcp.usepylon.com/ ### What can the Pylon MCP server do? It offers 99 tools, including search\_issues, get\_issue, get\_issue\_messages, get\_issue\_statuses and create\_issue (as its documentation names them, read on 30 Oct 2026). ### Is the Pylon MCP server in the official MCP Registry? No. Pylon hasn't published it to the official MCP Registry. ### Is the Pylon MCP server working? Yes. It answered our most recent check. We last checked it on 1 Nov 2026. ### What are the alternatives to Pylon's MCP server? In Help desk & live chat, the most agent-friendly alternatives with an official MCP server are SmartsUpp (97/100), Respond.io (97/100), Helpmonks (95/100), Sapling (94/100) and Productlane (92/100). Pylon scores 65/100 on the same index. ## Change history - 2026-10-12: Added to MartechDB with Pylon MCP ## Alternatives to Pylon's MCP server In Help desk & live chat, the most agent-friendly first: - [SmartsUpp](https://martechdb.com/vendors/smartsupp.md) (smartsupp.com), Agent Readiness Index 97/100 - [Respond.io](https://martechdb.com/vendors/respondio.md) (respond.io), Agent Readiness Index 97/100 - [Helpmonks](https://martechdb.com/vendors/helpmonks.md) (helpmonks.com), Agent Readiness Index 95/100 - [Sapling](https://martechdb.com/vendors/sapling.md) (sapling.ai), Agent Readiness Index 94/100 - [Productlane](https://martechdb.com/vendors/productlane.md) (productlane.com), Agent Readiness Index 92/100 ## Get this data - API: `curl https://martechdb.com/api/v1/vendors/usepylon.com` - MCP: `claude mcp add --transport http martechdb https://martechdb.com/mcp`, then ask about Pylon. - Web page: https://martechdb.com/vendors/pylon