mcpField
I
Indiestack

Indiestack

Local
indiestack.aiDeveloper Tools3Updated 21w ago

About Indiestack

Indiestack is an MCP server and CLI for AI coding agents that validates packages and helps select developer tools. It combines dependency checks with compatibility data across a curated catalog.

Key features

  1. 01Validate packages before installation
  2. 02Search 6,500+ developer tools
  3. 03Check tool compatibility and conflicts
  4. 04Inspect project dependencies
  5. 05Compare tools and build stacks

Use cases

  1. 01Check a package for typosquatting before installing
  2. 02Find tools for an application feature
  3. 03Review compatibility between dependencies
  4. 04Identify alternatives to project dependencies

MCP support

The MCP server provides 23 tools, 3 resources, and 5 prompts for package validation, tool search, compatibility checks, and related tasks.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"indiestack": {
"command": "uvx",
"args": [
"indiestack"
]
}
}
}
Run commanduvx indiestack

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiindiestack1.12.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

IndieStack

Dependency guardrail for AI coding agents. Validates packages before installation, catches hallucinations and typosquats, and provides compatibility intelligence across 6,500+ developer tools.

10,000+ PyPI installs | 110,000+ unique visitors | 23 MCP tools

claude mcp add indiestack -- uvx --from indiestack indiestack-mcp

Then ask your agent:

  • "Validate this package before installing"
  • "Find an auth solution for my Next.js app"
  • "Check compatibility between these two tools"

What it does

Before your AI installs a dependency or writes boilerplate — IndieStack validates it exists, checks for typosquats, and searches 6,500+ curated developer tools with real compatibility data from 4,500+ repos. You get install commands, health scores, and what tools actually work together in production.

"Indie" is the curation filter: independent developers and small teams. Focused, lean, maintained, honest pricing.


Tech stack

  • Backend: Python 3 / FastAPI / SQLite (FTS5 full-text search, WAL mode)
  • Infrastructure: Fly.io / Docker / 48-endpoint smoke testing
  • MCP server: Published on PyPI — 23 tools, 3 resources, 5 prompts
  • Auth: GitHub OAuth via sessions
  • Payments: Stripe subscriptions
  • Monitoring: Event reactor, pattern detection, Telegram alerting

Install

Claude Code (zero install — runs via uvx):

claude mcp add indiestack -- uvx --from indiestack indiestack-mcp

Claude Desktop — add to claude_desktop_config.json:

{
  "mcpServers": {
    "indiestack": {
      "command": "uvx",
      "args": ["--from", "indiestack", "indiestack-mcp"]
    }
  }
}

Cursor / Windsurf — add to your MCP config:

{"command": "uvx", "args": ["--from", "indiestack", "indiestack-mcp"]}

Persistent install:

pipx install indiestack
claude mcp add indiestack -- indiestack-mcp

CLI (terminal use):

pip install indiestack

indiestack search "analytics"
indiestack details simple-analytics
indiestack stack "auth, payments, email"

Tools (23)

ToolWhat it does
find_toolsSearch 6,500+ developer tools with 11 filters: price, health, stars, success rate, language, tags, compatibility
find_compatibleFind tools compatible with a given tool — grouped by category, with verified stacks and conflict warnings
get_tool_detailsIntegration code, pricing, API specs, and compatibility data
scan_projectAnalyze a project description + tech stack, get a complete tool recommendation
report_compatibilityReport that two tools work well together — builds the compatibility graph
report_outcomeReport success/failure with used_with and incompatible_with — feeds the compatibility graph
check_healthGitHub health audit — maintenance grade, last commit, stars, alternatives for stale tools
list_categoriesBrowse all 25 categories
compare_toolsSide-by-side comparison of any two tools
build_stackTurn a 50,000-token generation into a 2,000-token assembly
publish_toolSubmit a developer tool so other agents can recommend it
browse_new_toolsRecently added tools with pagination
list_tagsAll tags sorted by popularity
get_market_gapsTop unmet needs — what developers search for but can't find
list_stacksCurated stacks for common use cases
analyze_dependenciesScan package.json/requirements.txt for better alternatives
evaluate_build_vs_buyFinancial breakdown: build from scratch vs use what exists
get_recommendationsPersonalized suggestions based on your search history
Resources
ResourceWhat it provides
indiestack://categoriesAll 25 categories with slugs for filtering
indiestack://trendingTop 10 trending developer tools this week
indiestack://tools-indexComplete index for prompt caching — include once, reference forever
Prompts
PromptWhen to use
before-you-buildCheck IndieStack before building common functionality
find-alternativesFind indie alternatives to mainstream SaaS products
save-tokensAudit your project for token-saving opportunities
architect-featurePlan a feature using existing indie building blocks
discover-indieExplore what indie developers have built

What's new in v1.19

  • Package validation — validate_package() verifies packages exist and are safe before installation. Catches hallucinated and typosquatted packages.
  • Guardrail-first design — Built for AI agents that need to validate dependencies, not just discover them.

Recent highlights

  • Migration intelligence — Tool details include real migration data from 4,500+ GitHub repos.
  • 93,000+ verified package combinations from production repos.
  • Trust-weighted search — Tools with higher agent success rates rank higher.
  • Market gaps — get_market_gaps() exposes zero-result queries ranked by search volume.

Links


MIT License

Comments

Markdown supported

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.