Tracecat MCP

Drive Tracecat from your own agent harness over MCP: build, edit, and run workflows and cases through Claude, Cursor, ChatGPT, or any MCP client.

Tracecat works best with agentic coding tools (Claude Code, Cursor, Codex, OpenCode). Agents connected to Tracecat MCP gain the ability to build and orchestrate core Tracecat resources:

• Agents
• Workflows
• Tables (local and remote)
• Integrations (HTTP, gRPC, SQL)
• Scripts (Python, docker run)
• Cases (local and remote)

Tracecat MCP turns any coding agent into a security automation architect and engineer.

Setup

If you are self-hosted, replace https://platform.tracecat.com with your PUBLIC_APP_URL (e.g. http://localhost or https://tracecat.example.com).

Authentication uses a built-in OIDC provider—your agent is redirected to sign in through the browser on first connection. For clients or environments that cannot complete a browser sign-in, authenticate with a personal access token (PAT) instead.

Claude Code

Sign in with OAuth:

claude mcp add -t http tracecat https://platform.tracecat.com/mcp
claude
/mcp

Or authenticate with a personal access token (PAT). Set TRACECAT_MCP_PAT in your environment and reference it with single quotes so the variable (not the token) is written to the saved config:

claude mcp add --transport http tracecat https://platform.tracecat.com/mcp \
  --header 'Authorization: Bearer ${TRACECAT_MCP_PAT}'

OpenAI Codex

Sign in with OAuth:

codex mcp add tracecat --url https://platform.tracecat.com/mcp
codex mcp login tracecat

Or authenticate with a personal access token (PAT). Set TRACECAT_MCP_PAT in your environment, then reference it by name:

codex mcp add tracecat --url https://platform.tracecat.com/mcp \
  --bearer-token-env-var TRACECAT_MCP_PAT

GitHub Copilot

copilot
/mcp add
# Server Name: tracecat
# Server Type: HTTP
# URL: https://platform.tracecat.com/mcp
# Tools: *

Complete the OAuth sign-in from an interactive copilot session. A non-interactive run (copilot -p) does not wait for sign-in — it skips the tracecat tools until you have authenticated once interactively.

Follow GitHub Copilot MCP setup for the latest CLI prompts.

Or add this server to ~/.copilot/mcp-config.json:

{
  "mcpServers": {
    "tracecat": {
      "type": "http",
      "url": "https://platform.tracecat.com/mcp",
      "tools": ["*"]
    }
  }
}

To use a personal access token (PAT) instead of OAuth, add an Authorization header (${TRACECAT_MCP_PAT} is read from your environment):

"headers": {
  "Authorization": "Bearer ${TRACECAT_MCP_PAT}"
}

Cursor

On Tracecat Cloud, click Add Tracecat to Cursor to add it in one click. Otherwise configure .cursor/mcp.json manually:

{
  "mcpServers": {
    "tracecat": {
      "url": "https://platform.tracecat.com/mcp"
    }
  }
}

To use a personal access token (PAT) instead of OAuth, add an Authorization header (Cursor resolves ${env:TRACECAT_MCP_PAT} from your environment):

"headers": {
  "Authorization": "Bearer ${env:TRACECAT_MCP_PAT}"
}

Personal access tokens

OAuth is the default. For clients or environments that cannot complete a browser sign-in (CI, headless runners, shared dev containers), authenticate with a workspace-scoped personal access token (PAT) instead. PATs work the same on self-hosted and Tracecat Cloud.

1. In your workspace, go to Settings → MCP and create a token. Set a name and expiration.
2. Copy the token when it is shown. It is only displayed once and cannot be retrieved again.
3. Pass it as a bearer header from your MCP client — see the PAT option in each Setup tab above for Claude Code, Codex, Copilot, and Cursor.

Treat the PAT like a secret. It grants MCP access scoped to the workspace it was created in. Always send it in the Authorization header—never in the URL or a query string, where it leaks into server, proxy, and browser logs. Keep it out of command output and application logs, and supply it through an environment variable or secrets vault rather than hardcoding it in a config file. Revoke it from Settings → MCP if it is exposed, and prefer short expirations.

Starter prompts

Recreate automation from blog post

CopiedCopy prompt

Audit and improve existing workflows

CopiedCopy prompt

Build alert triage automation

CopiedCopy prompt

Automate phishing email response

CopiedCopy prompt

MCP tools

list_workspaces · tool

List all workspaces accessible to the authenticated user.

Returns paginated workspace summaries including workspace id/name and the owning org_id/org_slug. Multi-org users may receive workspaces from more than one organization in a single response.

create_workflow · tool

Create a new workflow in a workspace.

get_workflow · tool

Get metadata for a specific workflow.

edit_workflow · tool

Edit a draft workflow using RFC 6902 JSON Patch.

update_workflow · tool

Update workflow metadata and optional inline YAML.

list_workflows · tool

List workflows in a workspace.

list_workflow_tree · tool

List workflow folders and workflows under a path.

create_workflow_folder · tool

Create a workflow folder by absolute path.

rename_workflow_folder · tool

Rename a workflow folder by absolute path.

move_workflow_folder · tool

Move a workflow folder under a new parent path.

delete_workflow_folder · tool

Delete a workflow folder by absolute path.

move_workflows · tool

Move workflows into or out of a folder.

This tool is best-effort and non-atomic. If one workflow fails to move, the remaining workflow moves still proceed.

list_actions · tool

Search or browse available actions and return compact context metadata.

Supports three usage modes: -> Search: provide query to search by name/description across all namespaces. Example: list_actions(workspace_id, query=“send message”) -> Browse by namespace: provide namespace without query to list all actions in a namespace. Example: list_actions(workspace_id, namespace=“core”) -> Browse all: omit both to list all available actions.

Common namespaces: core, tools, ai.

sync_custom_registry · tool

Sync the organization’s custom action registry from its remote git repository.

Pulls the latest code from the custom registry repo registered in the caller’s organization, builds a versioned tarball, and makes the synced actions available to agents and workflows. Use this after pushing changes to the custom integrations repo, or to roll forward/back to a specific commit. Existing published workflows must be republished to pick up newly synced action versions.

get_action_context · tool

Get full schema and configuration context for a single action.

Use this after discovering an action via list_actions to get the complete parameter schema needed to write the args: block in a workflow definition.

Example action names: “core.http_request”, “core.script.run_python”, “core.transform.reshape”.

get_workflow_authoring_context · tool

Get compact workflow authoring context for selected actions.

Returns everything needed to write a workflow definition: action schemas, available secrets, and workspace variables. Use this before calling create_workflow or update_workflow.

Two input modes (provide one or neither): -> By name: pass actions with an action_names list. -> By search: pass query to search for actions by name/description

validate_workflow · tool

Validate a workflow’s draft state.

Checks that the workflow DSL is structurally sound and that arguments are valid.

prepare_template_file_upload · tool

Prepare a staged template YAML upload for remote /mcp clients.

validate_template_action · tool

Validate a template action YAML file.

Validates YAML parsing, template schema correctness, step action references, argument schemas, and expression references.

publish_workflow · tool

Publish (commit) a workflow, creating a new versioned definition.

This validates the workflow, freezes registry dependencies, and creates a new workflow definition version.

run_workflow · tool

Run a workflow from its draft state or a published definition.

By default runs the current draft (unpublished edits) so changes can be tested before publishing. Set use_draft=False to run a published version instead.

list_workflow_executions · tool

List recent executions for a workflow.

Use this to see run history, check which runs succeeded or failed, and find execution IDs for deeper inspection with get_workflow_execution.

get_workflow_execution · tool

Get status and details of a specific workflow execution.

Returns execution metadata (status, timing) and a compact event timeline showing each action’s status, timing, and any errors. Use this to debug failed runs or check the progress of running workflows.

get_webhook · tool

Get webhook configuration for a workflow.

update_webhook · tool

Update webhook configuration for a workflow.

get_case_trigger · tool

Get case trigger configuration for a workflow.

update_case_trigger · tool

Update an existing case trigger for a workflow.

list_workflow_tags · tool

List workflow tag definitions in a workspace.

Returns a JSON array of tag objects with id, name, ref, and color.

create_workflow_tag · tool

Create a workflow tag definition.

update_workflow_tag · tool

Update a workflow tag definition.

delete_workflow_tag · tool

Delete a workflow tag definition.

list_tags_for_workflow · tool

List tags attached to a workflow.

Returns a JSON array of tag objects with id, name, ref, and color.

add_workflow_tag · tool

Attach an existing workflow tag definition to a workflow.

remove_workflow_tag · tool

Remove a workflow tag association from a workflow.

list_cases · tool

List cases in a workspace with default sorting.

search_cases · tool

Search cases with filtering and sorting.

get_case · tool

Get a specific case with full details including fields, tags, and description.

create_case · tool

Create a new case.

update_case · tool

Update a case. Only provided fields are changed.

list_case_comments · tool

List all comments for a case.

list_case_comment_threads · tool

List comment threads for a case. Each thread contains the root comment and its replies.

create_case_comment · tool

Create a new comment on a case. Provide parent_id to reply to an existing comment.

update_case_comment · tool

Update an existing comment on a case.

delete_case_comment · tool

Delete a comment from a case.

list_case_tasks · tool

List all tasks for a case.

get_case_task · tool

Get a specific case task by ID.

create_case_task · tool

Create a new task on a case.

update_case_task · tool

Update a case task. Only provided fields are changed.

run_case_task · tool

Run the workflow associated with a case task.

Fetches the task’s workflow_id and default_trigger_values, merges them with case_id and task_id context (plus any caller-supplied overrides), then executes the latest published version of the workflow.

list_case_events · tool

List activity events for a case. Events are system-generated audit entries that track every change to a case — status changes, priority changes, assignee changes, comments, tasks, tags, field changes, etc.

list_case_tags · tool

List case tag definitions in a workspace.

Returns a JSON array of tag objects with id, name, ref, and color.

create_case_tag · tool

Create a case tag definition.

update_case_tag · tool

Update a case tag definition.

delete_case_tag · tool

Delete a case tag definition.

list_tags_for_case · tool

List tags attached to a case.

Returns a JSON array of tag objects with id, name, ref, and color.

add_case_tag · tool

Attach a case tag to a case.

remove_case_tag · tool

Remove a case tag association from a case.

list_case_fields · tool

List case field definitions in a workspace.

Returns a JSON array of field objects with id, type, description, nullable, default, reserved, options, and optional kind.

create_case_field · tool

Create a case field definition.

Supports optional create-only kind: LONG_TEXT requires type="TEXT" and URL requires type="JSONB".

update_case_field · tool

Update a case field definition.

list_case_dropdowns · tool

List case dropdown definitions in a workspace. Requires the case add-ons entitlement.

Returns a paginated JSON array of dropdown objects with id, name, ref, icon_name, is_ordered, required_on_closure, position, and embedded options.

create_case_dropdown · tool

Create a case dropdown definition with optional initial options. Requires the case add-ons entitlement.

update_case_dropdown · tool

Update a case dropdown definition. Only provided fields are changed. Requires the case add-ons entitlement.

delete_case_dropdown · tool

Delete a case dropdown definition along with all its options and per-case values. Requires the case add-ons entitlement.

add_case_dropdown_option · tool

Add an option to a case dropdown definition. Requires the case add-ons entitlement.

update_case_dropdown_option · tool

Update an option within a case dropdown definition. Only provided fields are changed. Requires the case add-ons entitlement.

delete_case_dropdown_option · tool

Delete an option from a case dropdown definition. Requires the case add-ons entitlement.

set_case_dropdown_value · tool

Set or clear a dropdown value on a case. Provide exactly one of definition_id or definition_ref, and at most one of option_id or option_ref; omit both option arguments to clear the value. Requires the case add-ons entitlement.

list_tables · tool

List workspace tables.

create_table · tool

Create a table with optional columns.

get_table · tool

Get table definition and index metadata.

update_table · tool

Update table metadata.

insert_table_row · tool

Insert a table row.

insert_rows · tool

Insert multiple table rows.

update_table_row · tool

Update a table row.

update_rows · tool

Update multiple table rows with the same values.

search_table_rows · tool

Search rows in a table.

export_csv · tool

Export table data as a staged download URL.

create_column_index · tool

Create a unique index on a table column. Only one unique index per table is allowed.

drop_column_index · tool

Drop the unique index on a table column.

list_variables · tool

List workspace variables.

get_variable · tool

Get a workspace variable.

list_secrets_metadata · tool

List secret metadata without secret values.

get_secret_metadata · tool

Get secret metadata by name without secret values.

list_integrations · tool

List workspace integrations useful for workflow and preset authoring.

get_agent_preset_authoring_context · tool

Get models, integrations, output_type guidance, and other preset authoring context.

create_agent_preset · tool

Create an agent preset in the selected workspace.

Use skills to attach published skills. Each binding contains skill_id.

update_agent_preset · tool

Update an existing agent preset in the selected workspace.

Use skills to replace attached published skills. Each binding contains skill_id. Omit skills to leave bindings unchanged, or pass an empty list to detach all skills.

list_agent_tree · tool

List agent folders and presets under a path.

create_agent_folder · tool

Create an agent folder by absolute path.

rename_agent_folder · tool

Rename an agent folder by absolute path.

move_agent_folder · tool

Move an agent folder under a new parent path.

delete_agent_folder · tool

Delete an agent folder by absolute path.

move_agent_presets · tool

Move agent presets into or out of a folder by preset slug.

list_skills · tool

List workspace skills with IDs, names, and current published versions.

Use this before updating, publishing, or attaching skills to agent presets.

upload_skill · tool

Upload a local skill directory into Tracecat as a workspace skill.

This creates a new logical skill. Use update_skill when replacing an existing skill draft to avoid duplicate skill rows with the same name.

Agents should read the local directory themselves, preserve relative paths, include the root SKILL.md file, and pass every file in files using content_base64.

update_skill · tool

Replace an existing skill draft with a local skill directory.

This does not publish the draft. Call publish_skill after the update if the skill should be attachable to agent presets.

publish_skill · tool

Publish a skill draft into an immutable skill version.

Only published skill versions can be attached to agent presets.

list_agent_presets · tool

List saved agent preset slugs and names.

Use get_agent_preset for the full preset definition.

get_agent_preset · tool

Get the full configuration for a saved agent preset by slug.

run_agent_preset · tool

Run an agent preset with a prompt and return text or approval status.

Creates an ephemeral session, triggers the agent workflow, and waits for the response. The agent has access to all tools configured on the preset.