ftrack MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ftrack MCP Server List all my ftrack projects"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ftrack MCP Server
A Model Context Protocol (MCP) server that provides AI assistants (like Claude) with full access to the ftrack production tracking API. This enables natural language interactions with your ftrack workspace - query projects, manage tasks, update statuses, and more.
Prerequisites
Node.js 18 or higher
ftrack account with API access
MCP-compatible client (Claude Desktop, Cursor, VS Code with Claude extension, etc.)
Note: This project was developed and tested on Windows. It should work on macOS and Linux but hasn't been tested on those platforms yet. If you encounter issues, please open an issue on GitHub.
Related MCP server: Anytype MCP Server
Installation
1. Clone the repository
git clone https://github.com/VFX-Tools-LLC/ftrack-mcp.git
cd ftrack-mcp2. Install dependencies
npm install3. Get your ftrack API credentials
Log into your ftrack workspace
Go to Settings > API Keys (or click your avatar > Settings > API Keys)
Create a new API key or use an existing one
Note down:
Your ftrack server URL (e.g.,
https://your-workspace.ftrackapp.com)Your username
Your API key
Configuration
Step 1: Set Credentials
Option A: .env file (easiest for local development)
Copy .env.example to .env and fill in your credentials:
cp .env.example .envFTRACK_SERVER=https://your-workspace.ftrackapp.com
FTRACK_API_USER=your-username
FTRACK_API_KEY=your-api-keyThe .env file is automatically loaded at startup and is excluded from git.
Option B: System Environment Variables (recommended for production)
The most secure approach is to set your credentials as system environment variables. The MCP server reads from these automatically.
Windows (PowerShell - run as Administrator):
[System.Environment]::SetEnvironmentVariable('FTRACK_SERVER', 'https://your-workspace.ftrackapp.com', 'User')
[System.Environment]::SetEnvironmentVariable('FTRACK_API_USER', 'your-username', 'User')
[System.Environment]::SetEnvironmentVariable('FTRACK_API_KEY', 'your-api-key', 'User')Windows (GUI): Settings → System → About → Advanced system settings → Environment Variables
macOS/Linux (~/.bashrc or ~/.zshrc):
export FTRACK_SERVER="https://your-workspace.ftrackapp.com"
export FTRACK_API_USER="your-username"
export FTRACK_API_KEY="your-api-key"After setting environment variables, restart your terminal/IDE.
Step 2: Configure Your MCP Client
Claude Desktop
Edit your config file:
Windows:
%APPDATA%\Claude\claude_desktop_config.jsonmacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"ftrack": {
"command": "node",
"args": ["C:/path/to/ftrack-mcp/src/index.js"]
}
}
}Cursor / VS Code
Add to your MCP settings or .cursor/mcp.json:
{
"mcpServers": {
"ftrack": {
"command": "node",
"args": ["/absolute/path/to/ftrack-mcp/src/index.js"]
}
}
}Note: Use forward slashes (/) even on Windows.
Alternative: Credentials in Config (Less Secure)
If you can't set system environment variables, you can pass them through the MCP config:
{
"mcpServers": {
"ftrack": {
"command": "node",
"args": ["C:/path/to/ftrack-mcp/src/index.js"],
"env": {
"FTRACK_SERVER": "https://your-workspace.ftrackapp.com",
"FTRACK_API_USER": "your-username",
"FTRACK_API_KEY": "your-api-key"
}
}
}
}⚠️ Warning: This stores credentials in a config file. Make sure this file is not committed to version control.
Running Standalone (for testing)
npm startUsage Examples
Once configured, you can ask Claude to interact with ftrack using natural language:
"List all my ftrack projects"
"Show me tasks assigned to John on the Marvel project"
"Create a new task called 'Final Review' under shot SH010"
"Update the status of task XYZ to 'In Progress'"
"What's the storage usage for my workspace?"
"List all versions for the compositing task"
Available Tools (55+)
Query Operations
Tool | Description |
| Execute ftrack query language expressions |
| Validate a query without executing |
| Get all available entity schemas |
| Get server version and config |
| Full-text search across entities |
CRUD Operations
Tool | Description |
| Create any entity type |
| Update entity attributes |
| Delete entities |
| Execute multiple operations atomically |
Convenience Tools
Tool | Description |
| List all projects |
| List tasks with filters |
| List all users |
| List versions for a task/asset |
| List available statuses |
| List task/object types |
| List priorities |
| Get single entity by ID |
| Add a note to any entity |
| List notes on an entity |
| Change task status |
| Assign user to task |
| List shots for a project or sequence |
| List asset builds for a project |
| Get top-level hierarchy of a project |
| List all tasks assigned to a user |
| List milestones for a project |
User & Security Management
Tool | Description |
| Add security role to user |
| Remove security role |
| Grant project access |
| Revoke project access |
| Impersonate user (admin) |
| Send invitation email |
| List all security roles |
File & Media Operations
Tool | Description |
| Get upload parameters |
| Complete chunked upload |
| Get download/upload URL |
| Trigger media transcoding |
| Get storage statistics |
Review Sessions
Tool | Description |
| List review sessions |
| Invite to review |
API Key Management
Tool | Description |
| Grant API key project access |
| Revoke API key access |
| Add role to API key |
| Remove role from API key |
2FA/Authentication
Tool | Description |
| Configure OTP |
| Configure TOTP |
| Generate TOTP secret |
| Disable 2FA |
| Reset API key |
| Reset password |
Delayed Jobs (Background Tasks)
Tool | Description |
| Import CSV data |
| Batch delete |
| Export feedback |
| Sync to iconik |
| Sync LDAP users |
ftrack Query Language Examples
The ftrack_query tool accepts ftrack's query language:
-- List all active projects
select id, name, status from Project where status is "active"
-- Get tasks assigned to a user
select id, name, status.name from Task
where assignments any (resource.username is "john")
-- Find shots in a sequence
select id, name from Shot where parent.name is "SEQ010"
-- Get latest versions for a task
select id, version, date, user.username from AssetVersion
where task_id is "abc-123" order by version descending
-- Search with wildcards
select id, name from Project where name like "%marvel%"Troubleshooting
"Failed to initialize ftrack client"
Verify your environment variables are set correctly
Check that your API key is valid and not expired
Ensure your ftrack server URL includes
https://
"Connection refused" or timeout errors
Check your network connection to ftrack
Verify the server URL is correct
Check if your workspace is accessible
"Permission denied" errors
Your API key may not have sufficient permissions
Contact your ftrack administrator to adjust your security role
Security Notes
Never commit your API credentials to version control
Use environment variables or secure secret management
API keys have the same permissions as the user - use dedicated service accounts for automation
Consider using project-scoped API keys for limited access
License
ISC
Contributing
Contributions are welcome! Please open an issue or submit a pull request.
Available Tools
59 toolsftrack_add_user_security_roleA
Add a security role to a user
Inputs: user_id (required), security_role_id (required).
ftrack_assign_user_to_taskC
Assign a user to a task
Inputs: task_id (required), user_id (required).
ftrack_assume_userA
Assume another user identity (requires admin privileges)
Inputs: user_id (required).
ftrack_batchA
Execute multiple operations in a single transaction (all succeed or all fail)
Inputs: operations (required).
ftrack_complete_multipart_uploadA
Complete a multipart upload after all parts have been uploaded
Inputs: parts (required), upload_id (required), component_id (required).
ftrack_configure_otpC
Configure OTP (One-Time Password) for a user
Inputs: user_id (required), otp_type (required).
ftrack_configure_totpC
Configure TOTP (Time-based One-Time Password) for a user
Inputs: user_id (required).
ftrack_convert_entityB
Convert an entity from one type to another
Inputs: entity_id (required), entity_type (required), target_type (required).
ftrack_createC
Create a new entity in ftrack
Inputs: entity_data (required), entity_type (required).
ftrack_create_noteC
Create a note on an entity
Inputs: content (required), entity_id (required), entity_type (required), author_id.
ftrack_csv_import_delayed_jobC
Create a CSV import delayed job
Inputs: job_data (required).
ftrack_deleteC
Delete an entity from ftrack
Inputs: entity_id (required), entity_type (required).
ftrack_delete_delayed_jobC
Create a delete delayed job for batch entity deletion
Inputs: entity_id (required), entity_type (required).
ftrack_disable_2faB
Disable two-factor authentication for a user
Inputs: user_id (required).
ftrack_encode_mediaB
Trigger media encoding/transcoding for a component
Inputs: component_id (required), options.
ftrack_export_review_session_feedback_delayed_jobB
Export review session feedback as a delayed job
Inputs: review_session_id (required), options.
ftrack_generate_signed_urlB
Generate a signed URL for accessing or uploading a component
Inputs: component_id (required), operation.
ftrack_generate_totpC
Generate a new TOTP secret for a user
Inputs: user_id (required).
ftrack_get_entityA
Get a single entity by type and ID with specified projections
Inputs: entity_id (required), entity_type (required), projections.
ftrack_get_upload_metadataC
Get metadata required for uploading a file to ftrack
Inputs: file_size (required), component_id (required), checksum, file_name.
ftrack_grant_api_key_projectB
Grant an API key access to a project
Inputs: api_key_id (required), project_id (required).
ftrack_grant_api_key_security_roleA
Grant a security role to an API key
Inputs: api_key_id (required), security_role_id (required).
ftrack_grant_user_security_role_projectB
Grant a user security role access to a specific project
Inputs: user_id (required), project_id (required), security_role_id (required).
ftrack_iconik_sync_structure_delayed_jobB
Sync structure to iconik as a delayed job
Inputs: project_id (required), options.
ftrack_list_asset_versionsB
List asset versions for a task or asset
Inputs: limit, task_id, asset_id.
ftrack_list_notesB
List notes for an entity
Inputs: entity_id (required), entity_type (required), limit.
ftrack_list_prioritiesA
List all available priorities
Inputs: no named parameters.
ftrack_list_projectsB
List all projects (convenience wrapper for query)
Inputs: limit, include_archived.
ftrack_list_review_sessionsC
List review sessions
Inputs: limit, project_id.
ftrack_list_security_rolesB
List all security roles
Inputs: no named parameters.
ftrack_list_statusesB
List all available statuses
Inputs: no named parameters.
ftrack_list_tasksC
List tasks for a project or context
Inputs: limit, status, parent_id, project_id, +1 more.
ftrack_list_typesA
List all available task/object types
Inputs: no named parameters.
ftrack_list_usersC
List all users
Inputs: limit, include_inactive.
ftrack_parse_queryA
Parse a query expression without executing it (useful for validation)
Inputs: expression (required).
ftrack_permissionsC
Check permissions for an entity
Inputs: entity_id (required), entity_type (required), actions.
ftrack_queryB
Execute a query using ftrack query language. Example: "select id, name from Project where status is active"
Inputs: expression (required).
ftrack_query_schemasA
Query all available entity schemas in ftrack
Inputs: no named parameters.
ftrack_query_server_informationA
Get ftrack server information including version and configuration
Inputs: no named parameters.
ftrack_remove_user_security_roleB
Remove a security role from a user
Inputs: user_id (required), security_role_id (required).
ftrack_reset_remote_api_keyB
Reset a user remote API key
Inputs: user_id (required).
ftrack_reset_remote_passwordB
Reset a user remote password
Inputs: user_id (required).
ftrack_revoke_api_key_projectB
Revoke an API key access from a project
Inputs: api_key_id (required), project_id (required).
ftrack_revoke_api_key_security_roleB
Revoke a security role from an API key
Inputs: api_key_id (required), security_role_id (required).
ftrack_revoke_user_security_role_projectA
Revoke a user security role access from a specific project
Inputs: user_id (required), project_id (required), security_role_id (required).
ftrack_searchB
Full-text search across ftrack entities
Inputs: expression (required), terms, context_id, entity_type, +1 more.
ftrack_send_review_session_inviteC
Send an invitation to participate in a review session
Inputs: email (required), review_session_id (required), name, message.
ftrack_send_user_inviteB
Send an invitation email to a user
Inputs: user_id (required), email.
ftrack_storage_usageC
Get storage usage information
Inputs: project_id.
ftrack_sync_ldap_users_delayed_jobC
Sync LDAP users as a delayed job
Inputs: options.
ftrack_un_assume_userA
Stop assuming another user identity and return to original identity
Inputs: no named parameters.
ftrack_updateC
Update an existing entity in ftrack
Inputs: entity_id (required), entity_data (required), entity_type (required).
ftrack_update_task_statusC
Update the status of a task
Inputs: task_id (required), status_id (required).
ftrack_update_user_security_roleC
Update a user security role (e.g., activate/deactivate)
Inputs: user_id (required), security_role_id (required), is_active.
get_project_structureB
Get the top-level structure of a project (immediate children such as sequences, episodes, folders)
Inputs: project_id (required), limit.
list_asset_buildsB
List asset builds for a project
Inputs: limit, status, asset_type, project_id.
list_milestonesC
List milestones for a project
Inputs: limit, status, project_id.
list_shotsA
List shots for a project or parent sequence
Inputs: limit, status, parent_id, project_id.
list_user_assignmentsA
List all tasks assigned to a user, optionally filtered by project or status
Inputs: user_id (required), limit, status, project_id.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 59 tools
Most tools target distinct actions and resources, with clear separation between querying, CRUD, security roles, API keys, uploads, and delayed jobs. Some potential confusion exists between convenience list_* wrappers and ftrack_query, or between ftrack_convert_entity and ftrack_update, but descriptions help clarify.
Most tools follow a 'ftrack_verb_noun' pattern, but there are deviations: the last five tools lack the ftrack_ prefix, 'ftrack_un_assume_user' has an awkward underscore, and delayed job tools mix nomenclature. Overall, the pattern is readable but not fully consistent.
With 59 tools, the server is heavily over-scoped for an MCP interface. While the domain is complex, many niche operations (e.g., multiple delayed job tools, granular security role grants) could be consolidated or exposed via a more compact API surface. The count feels excessive and likely overwhelms agents.
The tool set covers a broad range of ftrack functionality: general query and CRUD, user/security management, uploads, media encoding, review sessions, task management, and project structure. Minor gaps exist (e.g., no note update/delete, no asset version creation) but core workflows are well-supported.
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
MCP server that lets AI assistants use all OneSchema features exposed via the public API.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseBqualityDmaintenanceA Model Context Protocol server providing AI assistants with comprehensive project, task, and subtask management capabilities with project-specific storage.2944 npm88MIT
- AlicenseNot gradedqualityBmaintenanceA Model Context Protocol (MCP) server implementation that enables AI assistants to interact with Anytype's API through natural language, allowing users to manage their knowledge base through conversation.71,433 npm544MIT

Contentfulofficial
AlicenseNot gradedqualityBmaintenanceA Model Context Protocol (MCP) server that provides AI assistants with comprehensive tools to interact with Contentful APIs.62MIT- FlicenseNot gradedqualityFmaintenanceA Model Context Protocol (MCP) server that provides AI assistants full access to the Motion task and project management API, enabling task, project, and schedule management.-