Skip to main content
Glama
aic0t

AI Coach MCP Server

by aic0t

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": true
}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
open_ai_coach_dashboardA

Show the current state of the AI Coach desktop mascots and open an interactive dashboard. Read-only.

refresh_ai_coach_statusA

Re-read the AI Coach mascot state for the dashboard view. Read-only.

prepare_ai_coach_careA

Show which care actions (feed, sleep, wake, walk, nurse) are currently possible for a mascot, together with the state before the change. Does not change anything; the user must confirm in the dashboard.

commit_ai_coach_careA

Apply a care action that the user confirmed in the dashboard.

show_ai_coach_messageA

Display a short text (up to 140 characters) in the AI Coach mascot's speech bubble. Text only; no images or links.

report_ai_coach_activityA

Let the AI Coach mascot show what you are currently doing, using its own animation and speech bubble. Call it with 'thinking' or 'working' when you start a task (optionally with a short label), 'waiting' when you need the user, and 'succeeded' or 'failed' when you finish. Repeating the same state does not re-announce it, so it is safe to call on every step.

show_ai_coach_fileA

Open a safe local preview beside the AI Coach mascot. Allowed files: md, markdown, txt, mmd, mermaid, html, htm, jpg, jpeg, png, heic, webp, and svg. HTML is rendered with scripts removed and no network access. The file is read only by the AI Coach app; its contents and image bytes are never returned to the model. Use this only for a file the user asked to preview or a file created in the current task.

list_ai_coach_notesA

List the user's memos in AI Coach, newest first. Returns each memo's noteId, title, last modified time, size, group and a short excerpt — not the full body. Memos can be organised into groups (one level); pass 'group' to list just one group, or an empty string for ungrouped memos only. Use read_ai_coach_note to get the body. Read-only.

read_ai_coach_noteA

Read the Markdown body of one memo in AI Coach. Large memos come back in pieces: when 'truncated' is true, call again with offsetBytes set to offsetBytes + returnedBytes. Keep the returned modifiedAt and pass it as expectedModifiedAt when you later write to the same memo. Read-only.

search_ai_coach_notesA

Search the user's AI Coach memos by title and body text (case-insensitive substring). Returns matching memos with a snippet around the hit and the group each one belongs to. Pass 'group' to search inside one group only, or an empty string to search only ungrouped memos. Read-only.

write_ai_coach_noteA

Create a memo in AI Coach, replace one, or append to one. The memo is a plain Markdown file on the user's own machine and shows up in the AI Coach memo list immediately. Pass 'group' when creating to file it under a group (a folder); the group is created if it does not exist. Use mode 'create' for a new memo, 'replace' to rewrite an existing one and 'append' to add to the end (also how you write a body larger than the per-call limit). When changing an existing memo, first read it and pass its modifiedAt as expectedModifiedAt so a memo the user edited meanwhile is not overwritten. AI Coach asks the user to confirm the change on their screen, so the call can take a few seconds; if it comes back with note_confirmation_denied, the user declined it.

delete_ai_coach_noteA

Move one memo in AI Coach to the trash. Deleting is recoverable from the trash, but ask the user before calling this unless they asked for the deletion themselves. AI Coach also asks the user to confirm the deletion on their screen; note_confirmation_denied means they declined it.

set_ai_coach_care_confirmationA

Remember whether the AI Coach dashboard asks for confirmation before its own care buttons take effect. Dashboard use only; care that the model asks for is always confirmed by the user.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
AI Coach DashboardInteractive dashboard for the AI Coach desktop mascots.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/aic0t/ai-coach-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server