Allows exporting Notion pages to markdown using Notion's unofficial API, enabling retrieval of page content as markdown text.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@notion-export-mcp-server Export my Notion page 'Project Roadmap' as markdown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A MCP(Model Context Protocol) server that accesses to Notion unofficial API to export pages.
This server provides MCP-compatible access to Notion's unofficial API, allowing AI assistants to interact with your Notion exported page data through a standardized interface.
Available tools:
notion_export_get_result - Get notion export result markdown text
Related MCP server: NotionMCP
npm install notion-export-mcp-serverNOTION_TOKEN_V2: Your Notion token
NOTION_FILE_TOKEN: Your Notion file token
Directly:
npx notion-export-mcp-serverOr, run the installed module with node.
...
"notion-export": {
"command": "npx",
"args": [
"-y",
"notion-export-mcp-server"
],
"env": {
"NOTION_TOKEN_V2": "<your token>",
"NOTION_FILE_TOKEN": "<your token>"
}
},
...To export anything from Notion, one needs to authenticate oneself with some Cookies (like a browser would). These cookies are called token_v2 and file_token. They are set on all requests of a logged in user when using the Notion web-app.
Go to notion.so.
Log in with your account.
Open the developer tools of your browser, open Application > Storage > Cookies (Chrome); Storage tab (Firefox).
Copy the value of the Cookies called token_v2 and file_token and paste them somewhere safe.
⚠️ If you don't find file_token, you need to have at least had exported a file manually once.
Those cookies have a 1 year validity, so you don't need to do this often.
This tool completely relies on the export/download feature of the official but internal Notion.so API. The advantage is, that we do not generate any markup ourselves, just download and extract some ZIPs. While the download feature seems to be pretty stable, keep in mind that it still is an internal API, so it may break anytime.
npm run dev - Start the server in development mode with hot reloading
npm run build - Build the project for production
npm run start - Start the production server
npm run lint - Run linting checks (ESLint and Prettier)
npm run fix - Automatically fix linting issues
npm run examples - Run the example scripts
Fork the repository
Create your feature branch
Run tests and linting: npm run lint
Commit your changes
Push to the branch
Create a Pull Request
Get notion export result
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Notion page id | |
| recursive | No | Export children subpages recursively |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'get,' which implies a read operation, but it does not state whether the tool is read-only, what the result contains, whether it blocks or returns immediately, or any error conditions. This is minimal and mostly inferred from the verb.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely short (4 words) and front-loaded, but it is under-specified rather than appropriately concise. It omits critical context that should accompany a tool of this complexity, making it less useful than a longer, more informative description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema, no annotations, and only 2 parameters, the description is inadequate. It does not explain what the export result looks like, how the 'recursive' parameter affects the result, or the relationship between id and the export process. The tool feels incomplete without these details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides 100% coverage with descriptions for both parameters (id and recursive). The description adds no additional parameter context, but the schema already documents their purpose. This meets the baseline of 3 where schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get notion export result' clearly indicates the action (get) and the resource (notion export result), but 'export result' is vague and could refer to a status, a file, or a report. There are no siblings to differentiate from, so it lacks specific scope. It is not a tautology, but it lacks detail.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool, prerequisites, or alternatives. It does not mention whether an export job must be initiated first, how to obtain an id, or any conditions for use. There are no sibling tools, but even basic context is absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.0.3notion_export_get_resultWith only one tool, there is no possibility of overlap or confusion. The tool's purpose is clearly stated as retrieving a Notion export result.
The single tool name follows a clear verb_noun pattern (get_result) with a domain prefix (notion_export). No inconsistencies exist in the set.
One tool is too few for a server dedicated to Notion exports. Typical export workflows require initiating an export, listing exports, and retrieving results, so the current count is insufficient for the apparent scope.
The server only supports retrieving an export result, missing essential operations like creating an export or checking export status. This severely limits the tool's usability and leaves the workflow incomplete.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Web scraping for AI agents. Converts URLs to clean, LLM-ready Markdown with anti-bot bypass.
Clean Markdown and AI-readability scoring for any URL. Built for AI agents.
Publish to self-hosted WordPress from AI agents: markdown, images, SEO, and Notion sync.
Publish Markdown or HTML to a shareable link from your AI assistant. OAuth, no API keys.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/syucream/notion-export-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server