Mindcase

io.github.mindcase-coPublished by GitHub account mindcase-cov0.1.1Updated Oct 24, 2026

Access 30+ data collection agents from Claude with natural language.

VerifiedSTDIODesktop onlyWeb Search & Scraping

Overview

AI-generated overview

Mindcase connects an assistant to 30+ data collection agents that can be run with natural language requests.

What you can do
  • Run Mindcase's data collection agents from the assistant using natural-language requests.
  • Choose among more than 30 agents for different collection tasks.
  • Retrieve the data those agents gather for use in the conversation.
  • No individual tools are documented in the supplied material, so exact operations are not listed.
When to use it
Useful when you want an assistant to launch prebuilt data collection agents and bring the results into a chat, instead of writing scraping or collection code yourself.
Requirements
Runs as a local process installed from the PyPI package mindcase-mcp (Python). Requires a Mindcase API key supplied through the MINDCASE_API_KEY environment variable, obtained from the Mindcase app. Desktop-only; no web execution.
Before you install
The server needs a Mindcase API key, which is a secret and should be kept out of shared logs and configs. Collection requests and results are handled by Mindcase's service, so data you ask it to gather leaves your machine. No tool list is published, so review what the agents do before relying on them.

Installation

In SourceWeft

  1. Open Mindcase in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.