AI OS MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NOTION_API_KEY | Yes | Notion API token (Internal Integration Secret) used to authenticate with the Notion API and access the AI OS workspace. |
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
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_vaultA | Search Felix's AI OS (synced in Notion) for pages matching a keyword or topic. Returns page titles and URLs, not full content — use get_page for that. |
| get_pageA | Fetch the full content of a specific named page from the AI OS, e.g. 'GetClean', 'Knowledge Core', 'Fulfillment Workflow'. |
| list_projectsA | List all active projects in the AI OS with a one-line status each, by reading the '10_Projects' index page. |
| get_project_statusA | Fetch the current status of one specific project by name, e.g. 'QuickTurnaroundGigs' or 'GetClean'. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
search_vault and get_page are clearly separated by search-results vs full-content, and list_projects vs get_project_status are also distinct in scope. The only minor ambiguity is that get_page could also be used to fetch project content that contains status, making the boundary slightly less obvious.
All tool names follow a consistent verb_noun pattern: search_vault, get_page, list_projects, get_project_status. Verbs are lowercase and the naming style is uniform.
With only 4 tools, the server is compact and well-scoped for searching and viewing pages and project statuses. Each tool serves a distinct retrieval purpose and none feels like filler.
The read/search surface is well covered: search, get page, list projects, and get specific status all work together without dead ends. The main gap is the lack of write or update operations, so if modifying pages or project statuses is expected, the toolset would be incomplete.