What authentication does the server support?
The server uses OAuth2 authentication with a client ID and client secret. Your ShotGrid account must have API access enabled.
@chordee
Basic information
Project repository for mcp-server-shotgrid
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-shotgrid": {
"command": "uv",
"args": [
"run",
"--directory",
"{REPO_DIR}",
"main.py",
"-host",
"https://your-shotgrid-url",
"-ci",
"your_client_id",
"-cs",
"your_client_secret"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
This MCP server, built with FastMCP, enables LLM agents to programmatically query and manage Autodesk ShotGrid entities (projects, assets, tasks, users, notes, versions, bookings, etc.) via the ShotGrid REST API. It uses OAuth2 authentication and communicates over stdio transport, designed for VFX, animation, and game development pipelines that rely on ShotGrid.
Obtain your ShotGrid host URL, OAuth2 client ID, and client secret. Run the server with uv run --directory {REPO_DIR} main.py -host https://your-shotgrid-url -ci your_client_id -cs your_client_secret. All three arguments are required. The server exposes MCP tools that your LLM agent can call.
The server uses OAuth2 authentication with a client ID and client secret. Your ShotGrid account must have API access enabled.
The server uses `transport="stdio"` only, as implemented by FastMCP.
Python 3.11 is required, along with the `httpx`, `httpx-auth`, and `mcp.server.fastmcp` packages.
Yes. The tools are defined in `main.py` and can be extended or modified for your workflow. The underlying ShotGrid REST API logic is in `shotgrid_rest.py`.
The function docstrings in `main.py` document all arguments and return values for the available MCP tools.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.
Set up and manage the Eddyter AI rich text editor by talking to your AI agent — for Claude, Cursor, Codex and other MCP tools. A Model Context Protocol server that lets AI tools add Eddyter to a React, Next.js, Vite or R
Comments