Connpass

Provides access to Connpass events and groups via MCP, including user events, group events, and location/keyword searching.
  • python

0

GitHub Stars

python

Language

3 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "tyukei-commpass_mcp_server": {
      "command": "python",
      "args": [
        "/path/to/commpass_mcp_server/src/main.py"
      ],
      "env": {
        "CONNPASS_API": "YOUR_API_KEY"
      }
    }
  }
}

Connpass MCP Server lets you fetch IT study group and event information from the Connpass API through a Model Context Protocol (MCP) server. It exposes a set of actions you can call from an MCP client to query user events, group events, available groups, and location or keyword based searches, all while handling API access securely.

How to use

You use this MCP server by running it locally and connecting an MCP client to it. The server provides a set of actions such as getting a user’s attended events, listing events for a group, searching by location or keyword, and listing prefectures that can be searched. From your MCP client, call these actions as registered endpoints and pass the required parameters. Ensure your client supplies your Connpass API key so every request is authenticated.

How to install

# 1) Clone the project
git clone https://github.com/tyukei/commpass_mcp_server.git

# 2) Create a Python virtual environment using Python 3.12
uv venv  --python python3.12

# 3) Activate the virtual environment
source .venv/bin/activate

# 4) Synchronize dependencies and setup
uv sync
# 5) Create your environment file with your Connpass API key
cp .env.example .env
CONNPASS_API=your_connpass_api_key_here
# 6) Start the MCP server
python src/main.py

Configuration and usage notes

Configure your MCP client with the server entry and your API key. The example below shows how to register the local server in a client configuration, using Python to start the MCP server and pointing the client to the local runtime.

Example MCP client configuration

{
  "mcpServers": {
    "connpass": {
      "command": "python",
      "args": ["/path/to/commpass_mcp_server/src/main.py"],
      "env": {
        "CONNPASS_API": "your_api_key_here"
      }
    }
  }
}

Available actions you can call

From an MCP client, you can perform the following actions exposed by this server. Each action corresponds to a Connpass API query and returns relevant event data.

Tools and endpoints overview

The server implements a set of endpoints that map to common Connpass operations. You can invoke actions to fetch a user’s attended events, group events, and perform location or keyword based searches. The server also provides a utility to list available groups and prefectures.

Testing and diagnostics

Run the test suites to verify functionality and rate limit handling. Tests exercise user-related queries, location-based searches, and rate limit behavior. Be mindful that rate limits may cause HTTP 429 responses if you exceed the API’s request threshold.

Security considerations

Treat your Connpass API key as sensitive credentials. Do not commit the key to public repositories. Ensure the key is provided through a secure environment variable in your MCP client configuration.

Available tools

get_user_attended_events

Fetches the list of events a specific user has attended, with paging support via start and count parameters.

get_group_events

Retrieves the list of events for a specific Connpass group, with paging support.

list_available_groups

Returns a list of groups that are available for querying.

search_events_by_location

Search events by prefecture or location keywords, with paging support.

search_events_by_keyword_or

Search events by keywords using OR logic, with paging support.

list_available_prefectures

Lists prefectures that can be used as search locations.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational