Mizito MCP
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., "@Mizito MCP Give me my daily brief with overdue tasks and unread chats"
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.
Mizito MCP
MCP server for Mizito, the Iranian project-management and team-chat tool. It covers projects, kanban boards, tasks, task comments and history, workload, team chat, and switching between workspaces.
Mizito publishes no API. Everything was reverse-engineered from the web app's own JavaScript and checked against the live API.
Setup
Needs Python 3.11+, and Google Chrome for the login helper.
git clone https://github.com/AliMilani/mizito-mcp.git && cd mizito-mcp
python3 -m venv .venv
.venv/bin/pip install -r requirements.txt websockets # websockets: login helper only
./tools/refresh-auth.sh # log in once, writes .env (0600)refresh-auth.sh opens Chrome with a separate, empty profile, waits for you to
log in to Mizito, and copies the session token from the page into .env. Your
everyday browser profile is never touched. You can also paste a token into
.env by hand (cp .env.example .env && chmod 600 .env).
Then register run-mcp.sh as a stdio server in your MCP client. Most clients
take a JSON entry like this:
{
"mcpServers": {
"mizito": { "command": "/absolute/path/to/mizito-mcp/run-mcp.sh" }
}
}The token never goes into the client's config: run-mcp.sh reads it from
.env. It also honours:
MIZITO_ENV_FILE: another env file (for example one per workspace or account). Not needed whenMIZITO_TOKENis already in the environment.MIZITO_PYTHON: the interpreter to use (default.venv/bin/python, elsepython3).
Docker works too; the token stays out of the image:
docker build -t mizito-mcp .
docker run --rm -i --env-file .env mizito-mcpIf tools start failing with "Mizito rejected the token", the session was revoked
(logout elsewhere, password change). Run ./tools/refresh-auth.sh again, then
restart your MCP client.
Options (in .env):
MIZITO_READ_ONLY=1: no write tools at all.MIZITO_LOG_LEVEL=INFO: one stderr line per API call, never with bodies or the token.MIZITO_CACHE_TTL=300: seconds that users, projects, labels and chats stay cached.
Related MCP server: ClickDown
Tools
Arguments for people, projects, boards, labels and chats accept an id or a
name. Persian names match even with Arabic ي/ك or ZWNJ differences. "me" means
you. An ambiguous name is an error that lists the candidates.
Dates come back as UTC ISO plus *_fa in Tehran time on the Jalali calendar
(1405/08/21 14:30). Date inputs accept 2026-11-20 14:30, 1405/08/30 14:30
or ISO with Z.
Read (25)
Tool | Answers |
| standup in one call: my overdue / due today, unread chats, project counts |
| who am I, which workspace, plan days, storage / is Mizito reachable |
| every workspace with unread counts / act on another one (in memory) |
| members, roles, online/last seen, what each last worked on |
| projects with boards and counts / one project: members, per-board counts |
| per-project open / done / overdue only |
| task or project labels |
| the main task query: project / mine / outbox / everything; board, assignee, owner, label, open/done/all, overdue, text; paginated |
| my tasks, overdue first |
| Mizito's own search (includes archived projects) plus exact local match |
| full task: notes, checklist with ids, attachments, comments, optional history |
| comments / change log / who opened it |
| one person's open tasks across projects, per project, overdue |
| badge counts / raw cross-workspace rollup |
| DMs, groups and project chats, unread counts, filter by kind or title |
| paged history (offset), sender names, replies, task cards |
| server search in one chat (text or sender) / across all chats |
Write (19; each one reads back and fails loudly if the change did not land)
Tool | Does |
| to a chat title, a dialog id, or a person by exact full name (opens the DM); |
| my own message / for everyone / clear the unread badge |
| in a project: board (default first), assignees, notes, reminder, deadline, labels, checklist, first comment; posts the task card to the project chat like the web app |
| title, notes, assignees (set/add/remove), labels, deadline, checklist add/remove |
| done / not done |
| schedule / clear: the date Mizito uses for today and overdue |
| percentage 0-99 (100 = |
| to another kanban column, top or bottom (same weights as the web app) |
| tick or untick by id or title, with the web app's rules; reports when every item is ticked |
| with reply and mentions |
| soft delete with undo |
| private star |
Write tools change shared data that teammates see and get notified about. All write tools were verified live on 2026-11-12 in a private sandbox project (docs/API.md).
Typical chains
"what's going on?":
daily_brief"Sara's open tasks?":
get_user_workload(user="سارا")"what is overdue in the shop project?":
list_tasks(project="فروشگاه", overdue_only=True)"any message from Sara?":
list_chats(only_unread=True), thenread_chat(chat="سارا")"mark the payment-bug task done":
search_tasks("باگ پرداخت"), thencomplete_task(task_id)
Tests
.venv/bin/pip install -r requirements-dev.txt
.venv/bin/python -m pytest # 65 offline tests, no network
.venv/bin/python tools/smoke.py # live: every read tool over real stdiotools/smoke.py only calls read tools, but it reads your real workspace.
MIZITO_READ_ONLY=1 .venv/bin/python tools/smoke.py also proves the write gate.
Development
Layout:
server.py entry point (run-mcp.sh and Docker exec this path)
run-mcp.sh sources .env, execs .venv/bin/python server.py
mizito_mcp/
config.py env -> Settings (MIZITO_TOKEN, MIZITO_READ_ONLY, ...)
client.py HTTP; error mapping; read retries; no write retries
util.py Persian normalisation, Jalali/Tehran dates, scrub()
directory.py TTL caches + name->id resolution + task token registry
tasks_api.py task scopes, paging (25/page via `from`), local filters, sort
shape.py raw Mizito JSON -> compact dicts for the client
tools/__init__.py @tool decorator (annotations, scrub, read-only gate)
tools/workspace.py whoami, users, workspaces, health, counts
tools/projects.py projects, project detail (+per-board counts), labels
tools/tasks.py list/search/get task, comments, history, workload, brief
tools/task_writes.py task mutations (each verified by read-back)
tools/chat.py chats, paged history, project chat, search
tools/chat_writes.py send / reply / edit / delete messages, mark read
app.py build() -> FastMCP server + instructions for the client
tests/ offline pytest suite (fake Mizito via httpx.MockTransport)
tools/smoke.py live: spawns run-mcp.sh over stdio, calls every read tool
tools/extract_endpoints.py regenerates docs/ENDPOINTS.md from the live SPA bundle
tools/refresh-auth.sh re-login flow when the token is revoked (isolated Chrome)
tools/capture.py etc. CDP capture/probe kit for finding new endpointsRules the code relies on:
Never expose a task
access_token. It is a JWT whose payload embeds the user's session token.util.scrub()runs on every tool result as a safety net. The same goes forMIZITO_TOKEN: never print, log or commit it.No guessed write endpoints. Every write body comes from the SPA call site (cited in docs/API.md) and is verified live on a throwaway object first.
Every write reads back and raises if the change is not visible. Writes are never retried automatically (
client.call(..., write=True)).Ambiguity is an error. Name -> id resolution never guesses between candidates. Where a wrong match would message the wrong person (opening a new DM), only an id or an exact full name counts.
Verify by identity, not by time. A send or comment proves itself by a NEW id. When the write surely happened but the read-back failed, the tool returns
verified: falseinstead of raising, so the caller does not retry and create a duplicate.
Adding a feature:
Find the call site in the decompressed bundle:
grep -o '.\{300\}invokeApi("ns.method".\{300\}' a_dec.js(tools/extract_endpoints.pyshows how to get it; it is gzip without a Content-Encoding header).Probe reads live. 200 = right, 400 = wrong body, 405 = wrong name.
For writes: create a throwaway private task, exercise the write on it, read it back, delete it.
Add the tool in the right
tools/*.py, shape its output inshape.py, add an offline test with the fake intests/conftest.py, run pytest and smoke.py.Update docs/API.md and the tool tables above.
MCP clients bind the tool list at session start: restart the client after changing tools.
Docs
docs/API.md: verified endpoints, bodies, gotchas
docs/ENDPOINTS.md: all SPA endpoints (generated by
tools/extract_endpoints.py)docs/SPA_CALLSITES.md: how the web app builds each request
License
Available Tools
44 toolsadd_task_commentA
Post a comment on a task (the task's people are notified). reply_to = a comment id from get_task; mention = names/ids to @.
Inputs: text (required), task_id (required), mention, reply_to. Returns: object
bookmark_taskAIdempotent
Star/unstar a task in my own task list (private to me).
Inputs: task_id (required), bookmarked. Returns: object
complete_taskBIdempotent
Mark a task done (notifies the task's people, like the web app).
Inputs: task_id (required). Returns: object
create_taskA
Create a task in a project. Assignees get notified: confirm with the user first unless they asked for exactly this task.
project: id or title (required: Mizito has no project-less tasks). board: kanban column title/id (default: the project's first column). assignees: names/ids/"me"; default ["me"]; [] = nobody. reminder: when the task is scheduled ("زمان یادآوری"): this is the date Mizito uses for today / overdue. "2026-11-20 14:30" | "1405/08/30 14:30". deadline: "مهلت انجام", only in projects with the deadline feature. checklist: item titles. comment: first comment text. post_card_to_project_chat: put a task card into the project chat. Default: yes when the project has a chat, like the web app. Later changes to the task show up in the chat only if it has this card.
Inputs: title (required), project (required), board, notes, +7 more. Returns: object
daily_briefARead-onlyIdempotent
One-call standup: my overdue / due-today / no-deadline task counts with the urgent tasks listed, unread chats, and per-project open and overdue counts. Good first call for "what's going on?".
Inputs: no named parameters. Returns: object
delete_messageADestructiveIdempotent
Delete one of my messages for everyone. Confirm with the user first.
Inputs: chat (required), message_id (required). Returns: object
delete_taskADestructive
Delete a task (Mizito keeps it restorable: see restore_task). Confirm with the user first.
Inputs: task_id (required). Returns: object
delete_task_commentCDestructiveIdempotent
Delete one of my task comments.
Inputs: task_id (required), comment_id (required). Returns: object
edit_messageAIdempotent
Change the text of one of my own messages. Mizito only allows this before anyone has seen it (the web app hides Edit after that).
Inputs: chat (required), text (required), message_id (required). Returns: object
edit_task_commentAIdempotent
Replace the text of one of my task comments (ids from get_task).
Inputs: text (required), task_id (required), comment_id (required). Returns: object
get_dashboard_summaryARead-onlyIdempotent
Raw cross-workspace rollup (unread + task buckets). Prefer list_workspaces, which is the same data, cleaned up.
Inputs: no named parameters. Returns: result
get_projectARead-onlyIdempotent
Full detail for one project (id or title): members, admins, boards with per-board open/done/overdue counts, settings, labels.
Inputs: project (required). Returns: object
get_project_chatBRead-onlyIdempotent
The group chat of a project (id or title). Same output as read_chat.
Inputs: project (required), limit, offset. Returns: object
get_projects_summaryBRead-onlyIdempotent
Per-project task statistics only (fast status overview): total, done, open, overdue, due today, my open/overdue, last completion.
Inputs: include_archived. Returns: result
get_taskARead-onlyIdempotent
Everything about one task: full notes, assignees, deadline, checklist items (with ids), attachments, labels, completion, and its comments (+ change history if include_history=True).
Inputs: task_id (required), include_history, include_comments. Returns: object
get_task_commentsBRead-onlyIdempotent
Comments on a task, newest first, with author names and mentions.
Inputs: task_id (required), include_deleted. Returns: result
get_task_countsARead-onlyIdempotent
My task badge counts in this workspace: due today and total open.
Inputs: no named parameters. Returns: object
get_task_historyARead-onlyIdempotent
Change log of a task: who changed what (title, notes, assignees, board, deadline, completion...) and when, oldest first.
Inputs: task_id (required). Returns: result
get_task_seenBRead-onlyIdempotent
Who has opened a task, and when (first and last view per person).
Inputs: task_id (required). Returns: object
get_user_workloadARead-onlyIdempotent
What one person (name/id/"me") has on their plate across all open projects: open task count, overdue, per project and per board, plus the task list (overdue first). Done tasks only if include_done.
Inputs: user (required), include_done. Returns: object
health_checkARead-onlyIdempotent
Check the Mizito connection: token accepted, workspace, latency.
Use when other tools fail, before telling the user Mizito is down.
Inputs: no named parameters. Returns: object
list_chatsBRead-onlyIdempotent
Chats (DMs, groups, project group chats), most recent first: id, title (DMs are titled with the other person's name), kind, unread count, last message time. Filter by kind "dm"|"group"|"project" or by a title substring. Chat arguments elsewhere accept ids or titles.
Inputs: kind, limit, query, only_unread. Returns: result
list_labelsARead-onlyIdempotent
Labels of a kind: "task" (default) or "project". Task tools accept
these titles or ids in their label arguments.
Inputs: type. Returns: result
list_my_tasksARead-onlyIdempotent
My tasks (assigned to me or personal), overdue first. Shortcut for list_tasks(scope="mine").
Inputs: limit, offset, status. Returns: object
list_projectsARead-onlyIdempotent
Projects in the workspace with boards, admins, chat id and (by default) task counts: total / done / open / overdue / mine_open.
Archived projects are hidden unless include_archived=True.
project arguments elsewhere accept these ids or titles.
Inputs: with_counts, include_archived. Returns: result
list_tasksARead-onlyIdempotent
List tasks with filters. The main task query tool.
Where to look (pick one):
project="" every task of that project; project="all" = every open project
scope="mine" (default) tasks assigned to me + my personal tasks
scope="outbox" tasks I created for other people
scope="everything" inbox + outbox + every open project
Filters (combine freely, applied exactly): board (title/id, needs project), assignee (name/id/"me"), unassigned, owner (creator), label (title/id), status "open"|"done"|"all", overdue_only, query (words that must all appear in title/notes/ checklist; Persian/Arabic letter variants match).
sort: "deadline" (default; overdue first), "board" (kanban order, default for a project), "modified", "created". Paginated: returns total, has_more and next_offset.
Inputs: sort, board, label, limit, +10 more. Returns: object
list_workspacesARead-onlyIdempotent
Every workspace this account belongs to, with unread chat/inbox and
task counts per workspace. current marks the one tools act on.
Inputs: no named parameters. Returns: result
list_workspace_usersARead-onlyIdempotent
Members of the current workspace: id, name, role, online/last seen, and what each one last worked on.
include_contact=True adds phone/email (personal data: only when the
user actually needs it).
Inputs: include_contact, include_deleted. Returns: result
mark_chat_readAIdempotent
Mark every message in a chat as read (clears its unread badge).
Inputs: chat (required). Returns: object
move_taskAIdempotent
Move a task to another kanban board (column) of its project.
board: board title or id (within the task's project). position: "top" or "bottom" of the target column.
Inputs: board (required), task_id (required), position. Returns: object
read_chatARead-onlyIdempotent
Messages of one chat (id or title), newest first by default.
Page back through history with offset (skip that many newest
messages): offset=0 then offset=30, ... has_more says whether older
messages exist. Messages carry sender names, reply_to ids, mentions,
and task cards (type=task_card + task title). Deleted messages (which
Mizito keeps as "." placeholders) are skipped unless include_deleted.
Inputs: chat (required), limit, offset, oldest_first, +1 more. Returns: object
reopen_taskBIdempotent
Mark a done task as not done again.
Inputs: task_id (required). Returns: object
restore_taskA
Undo delete_task for a task id deleted earlier.
Inputs: task_id (required). Returns: object
search_chatARead-onlyIdempotent
Search inside one chat (id or title), server side, newest first.
query: text to find (Mizito's own in-chat search). from_user: only messages from this person (name/id/"me"). Give query, from_user, or both (both = server filters by text, then sender is checked locally). Paged with offset/next_offset.
Inputs: chat (required), limit, query, offset, +1 more. Returns: object
search_messagesARead-onlyIdempotent
Search all chats at once (Mizito's global message search). Returns up to 15 hits per page with the chat each came from; page with offset/next_offset.
Inputs: query (required), offset. Returns: object
search_tasksARead-onlyIdempotent
Find tasks by text, the way Mizito's own search page does (server side, includes archived projects), merged with an exact local match on title/notes/checklist of visible projects. status "open" | "done" | "all". Optional project narrows the result. Returns ids for get_task.
Inputs: query (required), limit, offset, status, +1 more. Returns: object
send_messageA
Send a chat message. Teammates see it immediately: confirm wording with the user first unless they dictated it.
to: chat title (project group / group) or a person's name (their DM is opened if it does not exist yet). Or pass dialog_id. reply_to: message id to reply to (from read_chat). mention: people to @mention (names or ids). Newlines are kept. Verified by reading the chat back.
Inputs: text (required), to, mention, reply_to, +1 more. Returns: object
set_checklist_itemAIdempotent
Tick or untick one checklist item. item = the item id from
get_task, or its exact/unique title.
Same rules as the web app: no changes on a done or deleted task; an item someone else ticked can be unticked only by a project admin. When the last item gets ticked the result says all_items_done: the web app then asks whether to mark the task done, so ask the user and call complete_task (this tool never completes the task itself).
Inputs: item (required), task_id (required), checked. Returns: object
set_task_deadlineAIdempotent
Set or clear (deadline=None) a task's deadline.
Accepts "2026-11-20 14:30" (Gregorian, Tehran time), "1405/08/30 14:30" (Jalali) or ISO with Z. A date without time means 23:59 Tehran.
Inputs: task_id (required), deadline (required). Returns: object
set_task_progressAIdempotent
Set a task's progress percentage (0-99). For 100 use complete_task: in the web app 100% means done, and it asks before completing.
Inputs: percent (required), task_id (required). Returns: object
set_task_reminderAIdempotent
Schedule a task ("زمان یادآوری"), or clear it with when=None. This is the date Mizito uses to put a task under today / overdue / upcoming, and when it reminds the assignees. Same date formats as create_task. (The web app calls this "snooze".)
Inputs: when (required), task_id (required). Returns: object
switch_workspaceARead-onlyIdempotent
Point every tool at another workspace (id or title from list_workspaces) for the rest of this MCP session.
Mizito binds a workspace to the token: workspace/switch mints a new
token, and the previous one stays valid (verified 2026-11-12), so
switching back is free. Kept in memory only: a restart returns to the
workspace of the token in .env.
Inputs: workspace (required). Returns: object
update_taskA
Edit a task. Only the arguments you pass change; everything else is sent back exactly as it is (Mizito's save replaces the whole task).
assignees / labels replace the whole list; add_* / remove_* edit it. People and labels accept names or ids. remove_checklist takes item ids or exact titles (see get_task). add_checklist skips titles that already exist. To move columns use move_task; to complete use complete_task.
Mizito has no partial update or version check: a change someone makes in the web app between this tool's read and its save is overwritten.
Inputs: task_id (required), notes, title, labels, +9 more. Returns: object
whoamiARead-onlyIdempotent
Current user and workspace: ids, name, role, plan days left, storage.
Call first when you need your own user id (it appears as owner / assignee / message sender elsewhere).
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 44 tools
Most tools target a distinct resource+action, but there are several self-acknowledged near-duplicates: get_dashboard_summary is explicitly 'the same data' as list_workspaces, get_project_chat returns 'same output as read_chat', get_task_comments duplicates the comments already in get_task, and list_my_tasks is a shortcut for list_tasks(scope="mine"). The descriptions do actively steer the agent ("prefer X", "shortcut for Y"), which keeps this usable, but an agent still has multiple plausible entry points for the same question.
Names are consistently snake_case verb_noun (get_task, list_tasks, set_task_deadline, delete_task_comment, search_messages), and the task/chat/project prefixes make families readable. A few exceptions break the pattern (whoami, daily_brief, health_check, bookmark_task) but they are memorable and unambiguous.
44 tools is well past the heavy threshold for a project/chat workspace server, and the surface includes redundant entries (dashboard summary, project summary, list_my_tasks shortcut, get_project_chat) that could be folded into existing tools. Many fine-grained setters (set_task_progress, set_task_deadline, set_task_reminder, set_checklist_item) add granularity that could plausibly be consolidated under update_task.
Task lifecycle is very thorough (create/update/delete/restore/complete/reopen/progress/deadline/reminder/move/checklist/comments/bookmark) and chat has send/edit/delete/read/search coverage. However there is no project or board creation/administration, no label management, and attachments are surfaced in get_task but cannot be uploaded or fetched — notable gaps for a workspace-management server.
Maintenance
Related MCP Connectors
Task manager your agent can fully operate: boards, tasks, sprints, roles, worklogs, day planner.
Manage projects, tasks, time tracking, and team collaboration through natural language.
Task & board management for AI agents + humans. Kanban, comments, digests via MCP.
Kanban boards your AI agent can use: add, complete, move and recall tasks with your team.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA comprehensive project management system that provides a full-featured Kanban board and dashboard accessible to AI agents. It enables agents to programmatically manage projects, tasks, and workflows through a suite of 13 specialized tools and 4 resource types.4-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to manage Kanban tasks, boards, teams, and checklists via natural language, with full CRUD operations and live updates.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to work a self-hosted kanban board as first-class users, exposing eleven kanban_* tools over a stateless Streamable HTTP endpoint for listing projects, stages, members and custom fields, and for creating, updating, moving and deleting tasks. Authenticates with bearer-token scopes so read-only or write access can be granted per agent, with every mutation audited.6MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to track time, manage the project board with epics, milestones, schedules and dependencies, and generate shareable reports through a single authenticated connection.MIT