Notion MCP Server
Allows searching across a Notion workspace, retrieving/creating/updating pages, creating/querying/updating databases, and managing database entries with custom properties.
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 MCP Serversearch for my project meeting notes from last week"
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.
Notion MCP Server
A Model Context Protocol server for Notion integration, allowing Claude and other LLMs to interact with your Notion workspace.
Features
Search Notion: Search across your entire Notion workspace
Get Page: Retrieve content from a specific Notion page
Create Page: Create new pages in your Notion workspace
Update Page: Update existing pages with new content or titles
Create Database: Create new databases with custom properties
Query Database: Query databases with filters and sorting
Update Database Entry: Update properties of database entries
Create Database Row: Add new rows to existing databases with custom properties
Related MCP server: Notion MCP Server
Setup
Clone this repository
Install dependencies
npm installConfigure your Notion API key
Create an integration in the Notion Developers portal
Copy your API key
You can either:
Edit the
.envfile and replaceyour_notion_api_key_herewith your actual API key, orPass it directly in the Claude for Desktop configuration (recommended, see below)
Build the server
npm run buildRunning the server
npm start
Setting up with Claude for Desktop
Install Claude for Desktop (if not already installed)
Open your Claude for Desktop App configuration:
On macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonCreate the file if it doesn't exist
Add the Notion server to your configuration:
{ "mcpServers": { "notion": { "command": "node", "args": [ "/Users/shaheerahmad/Documents/notion-mcp-server/dist/index.js", "--notion-api-key=YOUR_ACTUAL_API_KEY_HERE" ] } } }Replace:
/Users/shaheerahmad/Documents/notion-mcp-serverwith the full path to your project directoryYOUR_ACTUAL_API_KEY_HEREwith your actual Notion API key
Restart Claude for Desktop
Using the Server
Once connected to Claude for Desktop, you can use the server by asking Claude questions like:
"Search for meeting notes in my Notion workspace"
"Get the content of my project planning page" (you'll need the page ID)
"Create a new page in Notion with a list of tasks"
"Update my Notion page with ID 1aaada269d1b8003adceda69cf7bcd97 with content 'Here is some new content to add to the page.'"
"Create a new database in my Notion page with ID 1aaada269d1b8003adceda69cf7bcd97"
"Query my Notion database with ID 1aaada269d1b8003adceda69cf7bcd97 for items with status 'Completed'"
Claude will automatically use the appropriate tools based on your request.
Tool Usage Examples
Search Notion
Search for "meeting notes" in my Notion workspaceGet Page Content
Get the content of my Notion page with ID 1aaada269d1b8003adceda69cf7bcd97Create a New Page
Create a new page in Notion with title "Weekly Report" and content "This week we accomplished the following tasks..."Update an Existing Page
Update my Notion page with ID 1aaada269d1b8003adceda69cf7bcd97 with content "Adding this new information to the page."You can also update the title:
Update my Notion page with ID 1aaada269d1b8003adceda69cf7bcd97 with title "New Title" and content "New content to add."Create a New Database
Create a new database in my Notion page with ID 1aaada269d1b8003adceda69cf7bcd97 with title "Task Tracker" and properties {
"Task Name": { "title": {} },
"Status": {
"select": {
"options": [
{ "name": "Not Started", "color": "red" },
{ "name": "In Progress", "color": "yellow" },
{ "name": "Completed", "color": "green" }
]
}
},
"Priority": {
"select": {
"options": [
{ "name": "Low", "color": "blue" },
{ "name": "Medium", "color": "yellow" },
{ "name": "High", "color": "red" }
]
}
},
"Due Date": { "date": {} }
}Query a Database
Query my Notion database with ID 1aaada269d1b8003adceda69cf7bcd97 with filter {
"property": "Status",
"select": {
"equals": "Completed"
}
}You can also add sorting:
Query my Notion database with ID 1aaada269d1b8003adceda69cf7bcd97 with sort {
"property": "Due Date",
"direction": "ascending"
}Update Database Entry
Update properties of an existing database entry (page within a database).
{
"tool_name": "update-database-entry",
"tool_params": {
"pageId": "page_id_of_database_entry",
"properties": {
"Status": {
"select": {
"name": "Completed"
}
},
"Priority": {
"select": {
"name": "High"
}
},
"Due Date": {
"date": {
"start": "2023-12-31"
}
}
}
}
}The properties parameter should match the structure expected by the Notion API for the specific property types in your database. Different property types (text, select, date, etc.) require different formats.
Create Database Row
Add a new row to an existing database with custom properties.
{
"tool_name": "create-database-row",
"tool_params": {
"databaseId": "your_database_id_here",
"properties": {
"Name": {
"title": [
{
"text": {
"content": "New Task"
}
}
]
},
"Status": {
"select": {
"name": "Not Started"
}
},
"Priority": {
"select": {
"name": "Medium"
}
},
"Due Date": {
"date": {
"start": "2023-12-15"
}
},
"Notes": {
"rich_text": [
{
"text": {
"content": "This is a new task created via the API"
}
}
]
}
}
}
}The properties parameter must include all required properties for the database and follow the Notion API structure for each property type.
Troubleshooting
If tools aren't showing up, check the Claude for Desktop logs:
tail -n 20 -f ~/Library/Logs/Claude/mcp*.logMake sure your Notion API key is correctly set and that your integration has been granted access to the pages you want to interact with.
If you see "Unexpected token" errors in the logs, it's likely that console.log statements are interfering with the MCP protocol. This version of the server has been updated to avoid those issues.
Future Improvements
Add database query capabilities
Implement better content formatting
Add support for more block types
Available Tools
10 toolsadd-articleD
| Name | Required | Description | Default |
|---|---|---|---|
| databaseId | Yes | ||
| generateSummary | No | ||
| url | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create-databaseD
| Name | Required | Description | Default |
|---|---|---|---|
| parentPageId | Yes | ||
| properties | Yes | ||
| title | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create-database-rowD
| Name | Required | Description | Default |
|---|---|---|---|
| databaseId | Yes | ||
| properties | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
create-pageD
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| parentId | No | ||
| title | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
extract-url-metadataD
| Name | Required | Description | Default |
|---|---|---|---|
| authorPropertyName | No | ||
| batchSize | No | ||
| databaseId | Yes | ||
| datePropertyName | No | ||
| generateSummary | No | ||
| limit | No | ||
| publicationPropertyName | No | ||
| silentErrors | No | ||
| summaryPropertyName | No | ||
| urlPropertyName | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get-pageD
| Name | Required | Description | Default |
|---|---|---|---|
| pageId | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
query-databaseD
| Name | Required | Description | Default |
|---|---|---|---|
| databaseId | Yes | ||
| filter | No | ||
| sort | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search-notionD
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
update-database-entryD
| Name | Required | Description | Default |
|---|---|---|---|
| pageId | Yes | ||
| properties | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
update-pageD
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | ||
| pageId | Yes | ||
| title | No |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
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?
Tool has no 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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
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?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
Most tools have distinct purposes targeting different Notion resources and actions, but 'create-database-row' and 'update-database-entry' could be confused as they both modify database entries with unclear boundary between creation and updating. Other tools like 'add-article' vs 'create-page' might overlap if articles are pages, but overall ambiguity is low.
Tools follow a consistent kebab-case verb-noun pattern throughout, with clear action-object naming (e.g., 'create-database', 'query-database', 'update-page'). The only minor deviation is 'extract-url-metadata' which uses a different verb style but maintains the same casing convention.
With 10 tools, this is well-scoped for a Notion integration server. The count aligns with typical MCP servers (3-15 tools), covering core operations without being overwhelming or insufficient for the domain.
The toolset covers basic CRUD operations for pages and databases, but has notable gaps: no delete operations for pages, databases, or rows/entries, and missing tools for managing blocks, comments, or users. This could lead to dead ends in workflows requiring full lifecycle management.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP-native open-source Notion alternative: read & write pages, databases and kanban boards.
A Model Context Protocol server for Wix AI tools
Persistent memory layer for AI tools. Save and recall notes across Claude and other MCP clients.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides a standardized interface for interacting with Notion's API, enabling users to list databases, create pages, and search across their Notion workspace.111MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that connects Claude and other AI assistants to your Notion workspace, allowing AIs to interact with databases, pages, and blocks.12411MIT
- AlicenseAqualityDmaintenanceA Model Context Protocol server that connects AI assistants like Claude to Notion workspaces, enabling them to view, search, create, and update Notion databases, pages, and content blocks.129911MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides a standardized interface for AI models to access, query, and modify content in Notion workspaces.9914MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/SAhmadUmass/notion-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server