Cherry Notes
Server Details
Tasks that outlive the chat. Capture features and tasks on your phone; your AI agent picks them up.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool maps to a distinct action in the pick-work-complete lifecycle, and descriptions proactively clarify the riskiest pairs (list_projects vs get_items vs select_project). Minor residual overlap between 'releasing' (cherry_unpick) and 'finishing' (complete_items) for an item, but the guidance is explicit enough to separate them.
Mostly a consistent snake_case verb_noun pattern (get_items, complete_items, list_projects, select_project). The cherry_pick/cherry_unpick pair uses a domain-prefix style instead of verb-first, which is a minor deviation but still clear and thematic.
Six tools is tightly scoped to the claim-and-complete workflow, with no filler. Every tool corresponds to a necessary step (browse projects, select, read items, pick, unpick, complete).
The core loop of listing projects, selecting one, viewing items, claiming, releasing, and completing is fully covered with pagination support. Gaps are minor but real: no way to create or edit items, and no single-item detail fetch beyond the paginated get_items.
Publisher details
- Operator
- Closing CRM LLC · Publisher source
- Operator website
- https://cherrynotes.app/ · Publisher source
- Vendor relationship
- First-party
- Documentation
- https://cherrynotes.app/#connect · Publisher source
- Privacy policy
- Not provided
- Trust center
- Not applicable
- Restrictions
- Requires the Cherry Notes iOS app to approve the connection (6-digit code). iOS only for now - Android in review. Free tier: 1 project / 10 items; Pro ($4.99/mo) removes limits.
Available Tools
6 toolscherry_pickAIdempotentInspect
Claims items for work. This is STEP 1 — ALWAYS pick before doing any work. NEVER do work without calling this first. Requires idempotency_key. Pass item_numbers from the display (e.g. [3] for item 3), or set pick_all=true to pick all todo items. Show the display field to the user verbatim in a code block.
Inputs: idempotency_key (required), item_ids, pick_all, item_texts, +1 more. Returns: picked, display
cherry_unpickAIdempotentInspect
Releases picked items back to todo. Use if you picked the wrong item or need to release work. Requires idempotency_key. Pass item_numbers of the picked items. Show the display field to the user verbatim in a code block.
Inputs: item_numbers (required), idempotency_key (required), item_ids, item_texts. Returns: display, unpicked
complete_itemsAIdempotentInspect
Marks picked items as done. Ask the user for confirmation BEFORE calling this. Only call after the user confirms the work is done. Requires idempotency_key. Pass item_numbers of the picked items. Show the display field to the user verbatim in a code block.
Inputs: item_numbers (required), idempotency_key (required), context, item_ids, +1 more. Returns: display, completed
get_itemsARead-onlyInspect
Returns the current items in the selected project. Items are tasks for you to work on. ALWAYS call cherry_pick before doing any work on items — NEVER do work without picking first. Ask the user to confirm before calling complete_items. Show the display field to the user verbatim in a code block. If has_more is true, call again with cursor to get more. Do NOT show has_more or next_cursor to the user — ask "More items?" instead.
Inputs: cursor. Returns: items, notes, status, display, +12 more
list_projectsARead-onlyInspect
Returns all of the user's projects. ONLY call this when the user explicitly asks to see all projects or wants to switch projects — NOT when they say "show me the list" (that means get_items). Show the display field to the user verbatim in a code block. If has_more is true, call again with cursor to get more.
Inputs: cursor. Returns: display, message, has_more, projects, +1 more
select_projectARead-onlyInspect
Selects a project to work on. After calling this, get_items and cherry_pick will operate on the selected project. Pass project_number (the 1-based index from the list_projects display, e.g. 3 for the 3rd project) — preferred over project_id. Only the first page of list_projects is selectable by number; for later pages pass project_id. Show the display field to the user verbatim in a code block.
Inputs: project_id, project_title, project_number. Returns: items, notes, status, display, +12 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Turn user requests and support messages into tasks and tell users what shipped, from any AI agent.
Agent-native task management: your AI agent is the interface. Delegate to anyone by email.
A task list shared by you and your coding agents (Claude Code, Cursor, Codex and any MCP client). Agents plan each task into steps, report live progress to a board, and block on questions you answer from your phone.
Shared task layer for AI agents: tasks, handoffs and decisions that persist across tools.
Related MCP Servers
- FlicenseAqualityBmaintenanceOne shared project for your team's Claude Code, Codex, Cursor and OpenCode agents: a task board, decisions and handoffs. Everyone keeps their own plan.1353-
- AlicenseNot gradedqualityBmaintenanceLets coding agents like Codex, Cursor, and Claude Code share and resume each other's chats, and attach to a common task with saved notes that can be searched later. This keeps task state and decisions in sync no matter which agent you switch to.61 npm2MIT
- AlicenseAqualityBmaintenanceSelf-hosted task tracker and MCP server for AI coding agents. Append-only case files preserve decisions, failed attempts, questions, and check results across sessions. A live web board lets people track progress and answer agents. Runs locally in Docker and connects to Claude Code, Codex, Cursor, and other Streamable HTTP MCP clients. MIT licensed.306MIT
- AlicenseAqualityBmaintenanceFeedback ingestion for AI agents. Record your screen and talk; your agent does the rest — files the bugs, writes the spec, builds the backlog.997 PyPI35MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.