What it does
The hosted server gives AI assistants and coding agents tools for Stellary projects, boards, collaboration, cockpit state and agent missions, while keeping Stellary's existing permissions. Clients can list projects, columns, cards, documents and cockpit state, create and update cards, move work, assign teammates and add comments. They can also inspect sprints, priorities, agent status and pending proposals, run agent missions under workspace rules and approval policies, and use installed workspace integrations from eligible agent sessions.
It suits teams that want an MCP-capable assistant or coding agent to read or change work in Stellary. A safe starting point is to ask the client to list projects, which confirms authentication without changing data. Write scopes can be enabled afterwards, once the client has inspected a project's columns and cards.
Setup uses an OAuth-capable MCP client: add the hosted endpoint, sign in to Stellary in the browser window the client opens, choose a workspace, and authorize Me, one or more active agents, or both. The Cursor Marketplace listing can also be used. A personal access token is documented only as a fallback when OAuth cannot complete, and should be created with read scopes first. The server runs remotely over Streamable HTTP and does not start a local stdio or npx process. The available tools are resolved at connection time and checked again on each call. Access can be revoked from Workspace settings.
Limitations and requirements
Requires a Stellary account and a workspace to authorize. An OAuth-capable MCP client is needed, or a personal access token where OAuth cannot complete. The available tools depend on OAuth scopes, project access, workspace configuration and each agent's tool and autonomy policies. All requests remain subject to Stellary permissions and rate limits. Personal access tokens should be treated like passwords, kept out of repositories, and given an expiry date when used.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Stellary Project Management MCP Server
Connect AI assistants to Stellary projects, boards, documents, and governed agent workflows.
v0.12.0As shown on registry.modelcontextprotocol.io when we last read it