---
title: "tracecat"
description: "Operate Tracecat safely through its MCP server and platform workflows."
canonical: https://agentpluginsdirectory.com/plugins/tracecat
last-updated: 2026-10-21
---

# tracecat
Operate Tracecat safely through its MCP server and platform workflows.
- Slug: tracecat
- Publisher: Tracecat
- Repository: https://github.com/TracecatHQ/tracecat-plugins
- Manifest: plugins/tracecat/plugin.json
- Version: 0.5.0
- Category (editorial): integrations
- Skills: 5 (tracecat-automation-best-practices, tracecat-manage-skills, tracecat-mcp, tracecat-slackbot-best-practices, tracecat-workspace-chat)
- MCP servers: 1 (tracecat)
- Stars: 2
- Repository created: 2026-08-11
- Repository last pushed: 2026-10-20
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/tracecat
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What tracecat does, in the publisher's words

Tracecat's public-facing agent package for working with the Tracecat MCP server and platform.

The package at plugins/tracecat/ follows the Agent Plugins v1 layout and also carries native manifests for Codex and Claude Code. It contains one Tracecat plugin whose skills disclose domain guidance progressively:

Every skill carries an agents/openai.yaml interface stub for Codex, and pushes detail into its own references/ directory so agents load it only when the task calls for it. tracecat-mcp is the entry point: it covers connection and tool routing, and hands off to the domain skills.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/TracecatHQ/tracecat-plugins/HEAD/README.md

## Skills

- tracecat-automation-best-practices: Use when building, editing, validating, or debugging generic Tracecat automations through Tracecat MCP, including workflow DSL/YAML authoring, table design, unique indexes, run-python Tracecat imports, agent presets, ai.agent or ai.preset_agent workflows, executions, validation, and workflow best p…
- tracecat-manage-skills: Use when creating, uploading, updating, publishing, or re-binding a local Agent Skill directory through Tracecat MCP, including pushing a fix to a skill an agent preset already uses.
- tracecat-mcp: Use when an external agent needs to connect to or operate Tracecat through MCP, including workspace discovery, workflows, actions, cases, tables, integrations, agent presets, skills, executions, or safe platform navigation.
- tracecat-slackbot-best-practices: Use when building, editing, validating, or debugging Tracecat Slack bots and Slack-facing automations through Tracecat MCP, including Slack app mentions, interactive messages, event subscriptions, webhooks, thread replies, Slack tools, ai.agent or ai.preset_agent bots, Slack tone, and Slack smoke t…
- tracecat-workspace-chat: Use whenever Tracecat Workspace Chat answers platform questions or operates workflows, cases, tables, agent presets, integrations, secrets, variables, or other workspace features. Adapts generic Tracecat MCP guidance to the tools actually exposed in Workspace Chat and routes platform facts to bundl…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- tracecat: transport: streamable-http; url: https://platform.tracecat.com/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.