About Research MCP Server
Research MCP Server is an MCP server for survey work with Notion. It retrieves survey data and creates survey pages for use with Claude Desktop.
Key features
- 01Retrieve survey data from Notion
- 02Create survey pages in Notion
- 03Run as an MCP server
Use cases
- 01Read survey data stored in Notion
- 02Create Notion pages for survey results
MCP support
It exposes tools to MCP clients for retrieving survey data from Notion and creating survey pages.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEResearch MCP Server
This is a repository for the research project on the MCP server.
Features
- Work as an MCP server.
- Retrieve survey data from Notion.
- Create survey pages in Notion.
Prerequisites
- Python 3.12.1 or later
- uv 0.5.25 or later
- Claude Desktop Client
How to Use
- Clone the repository.
- Obtain a Notion token from Notion Integrations.
- Create a database page in Notion and retrieve the database ID. The database ID is the last part of the page URL.
- Create a
.envfile as shown below:NOTION_TOKEN=[YOUR_NOTION_TOKEN] NOTION_ROOT_DATABASE_ID=[YOUR_NOTION_DATABASE_ID] - Add an MCP server definition to
claude_desktop.json:{ ... "mcpServers": { "Research MCP Server": { "command": "uv", "args": [ "run", "--with", "mcp[cli]", "--with", "notion-client", "--with", "pydantic", "mcp", "run", "/path/to/research-mcp-server/server.py" ] } } } - Restart the Claude Desktop Client to launch the Research MCP Server.
- Ask Claude to perform a survey and review the results.
Comments
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.