This project has been archived by its maintainers, and is no longer receiving any updates.
Mindcase MCP Server
MCP server for Mindcase — access 30+ data collection agents from Claude. Scrape LinkedIn, Instagram, Google Maps, Amazon, YouTube, and more with natural language.
Features
- 30+ data agents across LinkedIn, Instagram, Amazon, Google Maps, YouTube, and more
- Natural language — just ask Claude, no code or parameters to learn
- Works everywhere — Claude Code, Claude Desktop, Cursor, Windsurf
- Auto-discovery — agents register automatically on startup
- Structured results — get tables, not raw text
- Credit tracking — check your balance anytime
Quick Start
1. Get an API key
Sign up at app.mindcase.co and create an API key in the API Console.
2. Add to Claude
Claude Code (CLI):
claude mcp add mindcase -- uvx mindcase-mcp
Then set your API key:
export MINDCASE_API_KEY=mk_live_your_api_key_here
Claude Desktop:
Add to your config (~/Library/Application Support/Claude/claude_desktop_config.json on Mac, %APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"mindcase": {
"command": "uvx",
"args": ["mindcase-mcp"],
"env": {
"MINDCASE_API_KEY": "mk_live_your_api_key_here"
}
}
}
}
3. Use it
Ask Claude things like:
- "Find coffee shops in Manhattan with ratings above 4.5"
- "Search LinkedIn for AI startups in San Francisco"
- "Get Instagram profiles for Nike, Adidas, and Puma"
- "Scrape Amazon reviews for this product"
- "Find Python developer jobs on Indeed in New York"
Available Tools
Utility Tools
| Tool | Description |
|---|---|
list_agents |
Browse all 30+ available data agents |
check_credits |
Check your remaining credit balance |
get_agent_details |
View parameters and pricing for a specific agent |
Data Collection Tools
All agents from the Mindcase API are registered as individual tools:
| Platform | Tools |
|---|---|
| Profiles, Companies, Employees, Jobs, Posts, People Search, Company Search, Domain Lookup | |
| Profiles, Posts, Comments | |
| YouTube | Videos, Channels, Comments, Shorts |
| Amazon | Products, Reviews, Bestsellers, India Products |
| Google Maps | Businesses, Reviews, Reverse Geocoding |
| Twitter / X | Posts |
| TikTok | Profiles |
| Posts | |
| Shopify | Products |
| Indeed | Jobs |
| App Store | Reviews |
| Flipkart | Products |
| Myntra | Products |
Each tool accepts the agent's specific parameters and returns structured data in a table format.
How It Works
- On startup, the server fetches all available agents from the Mindcase API
- Each agent is registered as an MCP tool with its parameter schema
- When Claude calls a tool, the server runs the agent via the API
- The server polls for results and returns structured data to Claude
Configuration
| Environment Variable | Description | Required |
|---|---|---|
MINDCASE_API_KEY |
Your Mindcase API key (mk_live_...) |
Yes |
Documentation
Also Available
- Python SDK —
pip install mindcasefor programmatic access - Node.js SDK —
npm install mindcasefor JavaScript/TypeScript
Privacy
See privacy-policy.md for details on data handling.
License
MIT
Metadata
Release files for mindcase-mcp 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| mindcase_mcp-0.1.1.tar.gz | 54.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mindcase_mcp-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 64.0 kB
Release files / mindcase_mcp-0.1.1.tar.gz
| Download URL | mindcase_mcp-0.1.1.tar.gz |
|---|---|
| Size | 54.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
eb172cd34f8829e79c028214488bc48482b20f3c88811ad6d42de1f39bafccb4
|
|
BLAKE2b-256 checksum How to use checksums |
94ac6190b1192e9e694bd9feb9e114f23676a80fb055d125b942c6779118d7d3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Apr 12, 2026.
Transparency logRelease files / mindcase_mcp-0.1.1-py3-none-any.whl
| Download URL | mindcase_mcp-0.1.1-py3-none-any.whl |
|---|---|
| Size | 9.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
bfb96570ace2d9abb89189a4a320187730dbfd183931ba21507fe3dd5b1a30a0
|
|
BLAKE2b-256 checksum How to use checksums |
2624cd1d91f11966eb1a20215067f9de89c7f97d0318358a5324d7eec5c798b1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Apr 12, 2026.
Transparency log