Notion MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | HTTP-transport variable; the host to bind to | |
| PORT | No | HTTP-transport variable; the port to listen on | |
| HTTP_PROXY | No | Route all outbound traffic — Notion API calls and the downloads in `get_image` and `upload_file`'s `url` source — through an HTTP(S) proxy (standard env vars, lowercase also accepted) | |
| HTTPS_PROXY | No | Route all outbound traffic — Notion API calls and the downloads in `get_image` and `upload_file`'s `url` source — through an HTTP(S) proxy (standard env vars, lowercase also accepted) | |
| NOTION_TOKEN | Yes | PAT (`ntn_…`, recommended) or Internal Integration secret (`secret_…` / `ntn_…`) | |
| MCP_TRANSPORT | No | HTTP-transport variable; selects the transport mode | |
| MCP_AUTH_TOKEN | No | HTTP-transport variable; token used to authenticate requests | |
| NOTION_PAGE_ID | No | Default parent for `create_page` / `create_database` when no `parent` is passed (page → Share → Copy link; the whole URL or the bare 32-char id both work) | |
| NOTION_FILE_URLS | No | `ref` replaces Notion's signed file URLs (~1,650 chars, valid for an hour) in slim responses with short `notion-file:` refs | full |
| NOTION_READ_ONLY | No | `true`/`1`/`yes` disables every write operation in one switch | |
| NOTION_RATE_LIMIT | No | Requests/second for the shared limiter (Notion's documented per-integration limit) | 3 |
| NOTION_UPLOAD_ROOT | No | Confine `upload_file`'s `path` source to one directory | |
| MCP_PROTOCOL_NEGOTIATION | No | Set to `auto` to probe for MCP 2026-07-28 (stateless requests, cache hints on every list) | |
| NOTION_DAILY_LOG_PAGE_ID | No | Only used by the daily-log MCP prompt | |
| NOTION_ALLOWED_OPERATIONS | No | Comma-separated allowlist of operations or group presets | |
| NOTION_BLOCKED_OPERATIONS | No | Comma-separated blocklist (same vocabulary); wins over the allowlist | |
| NOTION_CONFIRM_DESTRUCTIVE | No | `true`/`1` keeps destructive operations enabled but asks you first |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo issues