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., "@planka-mcp Create a card 'Write blog post' in the Content board"
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.
MCP server yang menghubungkan Hermes ke Planka (kanban self-hosted BTD) via REST API.
Tool | Fungsi |
| List semua project |
| Buat project (private/shared) |
| Detail project + boards |
| Buat board di project |
| Detail board + lists |
| Buat list/kolom di board |
| List card dalam list |
| Buat card |
| Detail card + members |
| List semua user |
| Buat user (admin/projectOwner/boardUser) |
| Assign user ke board (WAJIB sebelum card) |
| Assign user ke card — multi-assignee (panggil berulang utk tim) |
Related MCP server: Another Planka MCP
cd ~/planka-mcp
python3 -m venv venv
./venv/bin/pip install -r requirements.txt # mcp==1.29.0, requestsyes | hermes mcp add planka \
--command /home/dedieko/planka-mcp/venv/bin/python3 \
--env PLANKA_BASE_URL=http://127.0.0.1:13370 PLANKA_EMAIL=admin@ugm.ac.id PLANKA_PASSWORD='<pass>' \
--args /home/dedieko/planka-mcp/run_planka_mcp.py⚠️ Semua env dalam SATU --env (dipisah spasi). Restart gateway untuk aktif.
POST /api/access-tokens {emailOrUsername, password}
Jika pendingToken → GET /api/terms → signature = sha256(isi terms) → POST /api/access-tokens/accept-terms
project (type: private)
└── boards (type: trello, position)
└── lists (type: active, position)
└── cards (type: project)
└── card-memberships (multi-user)POST /api/boards/:id/board-memberships {userId, role: editor} — tanpa ini "User not found"
POST /api/cards/:id/card-memberships {userId} — panggil per anggota tim
This server cannot be deployed
MCP server for generating rough-draft project plans from natural-language prompts.
Remote MCP for Kanban AI boards—manage projects, tasks, and comments from AI tools.
Task & board management for AI agents + humans. Kanban, comments, digests via MCP.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
