mcpField
M
Mila

Mila

Remote
github.com/mila-ggProductivity0Updated 30w ago
Repository

About Mila

Mila is an OpenClaw skill that documents how AI agents can use Mila's REST API and MCP tools to manage documents, spreadsheets, and slide presentations. It includes setup guidance and detailed references for content operations and workspaces.

Key features

  1. 01Create and manage documents
  2. 02Edit spreadsheet workbooks, tabs, and cells
  3. 03Create and manage slide presentations
  4. 04Use formulas and cell formatting
  5. 05Filter by workspace and paginate results

Use cases

  1. 01Create or update documents through an agent
  2. 02Manage spreadsheet cells and formatting
  3. 03Build or append slide presentation content

MCP support

The skill explains how to connect to Mila's MCP server and use its tools for document, spreadsheet, and presentation operations.

#productivity#documents#spreadsheets#presentations#office-suite#ai#mcp#api#collaboration

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.mila.gg
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://mcp.mila.ggAuth required

Tools

23

This tool takes no parameters.

Details

From the project README

Mila Skill for OpenClaw

An OpenClaw skill that teaches AI agents how to use the Mila REST API and MCP tools to manage documents, spreadsheets, and slide presentations.

What is OpenClaw?

OpenClaw is a package manager for AI agent skills. Skills are structured reference files that give agents domain knowledge — like API docs, best practices, and usage patterns — so they can perform tasks without needing everything hardcoded into their system prompt.

When a user installs a skill, the agent downloads the skill files into its local workspace (typically ~/.openclaw/workspace/skills/<name>/) and loads them as context when relevant tasks come up.

How it works

This repo contains a SKILL.md file (the skill manifest) and a references/ directory with detailed API documentation:

mila-skill/
  SKILL.md                    # Manifest: metadata, auth, MCP setup, quick start, tool list
  references/
    DOCUMENTS.md              # 6 endpoints for document CRUD + append
    SHEETS.md                 # 10 endpoints for workbook/tab/cell operations
    SLIDES.md                 # 6 endpoints for presentation CRUD + append
    SERVERS.md                # 1 endpoint for listing workspaces

When an agent has this skill installed, it knows how to:

  • Authenticate with Mila API keys (mila_sk_*)
  • Create, read, update, and delete documents with HTML content
  • Manage spreadsheets with A1 cell notation, formulas, and cell formatting
  • Build slide presentations with free-form HTML on a 960x540 canvas
  • Connect to the MCP server for tool-based interaction
  • Filter content by server (workspace) and paginate results

Install

Ask any OpenClaw-compatible agent:

Can you install this skill please? https://clawhub.ai/freddyjd/mila

The agent downloads and installs it automatically. Then give it your API key:

Here is the API key: mila_sk_your_key_here

Create an API key at mila.gg/api-keys (individual) or mila.gg/team-api (teams).

Publishing

This repo auto-publishes to ClawHub via GitHub Actions whenever SKILL.md or anything in references/ changes on main.

The workflow (.github/workflows/publish-clawhub.yml):

  1. Extracts the version from SKILL.md frontmatter
  2. Checks if that version already exists on ClawHub
  3. If not, publishes using bunx clawhub@latest publish

To release a new version: bump the version field in SKILL.md and push to main.

Links

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.