Skip to content
MCP server

Archestack

Search and compare open-source AI projects by score, license and hardware needs

Pricing
Open source
Platforms
API, CLI
Runs
Locally or Remotely
Version
0.3.1
Listing updated
3 days ago

About Archestack

Archestack is an open-source MCP server for ai models and llm tooling. It can run locally on your machine or as a hosted remote server.

Answers come from a published dataset rather than live scraping. Archestack's rankings cover two lists: Best of AI (self-hosted apps and infrastructure such as chat UIs, model servers, RAG and vector databases) and Best of Vibe Coding (starters, coding agents, MCP servers, skills and plugins). The server reads the site's static, CC BY 4.0 JSON API, refreshed twice a day.

Tools let an assistant search with filters such as list, category, license family and whether a project runs without a GPU, open a category's top entries, pull one project in full with score parts and review, see what it takes to run, compare projects side by side, and find open-source picks for a paid product.

The hosted copy at mcp.archestack.com/mcp is read-only and allows 120 requests a minute per address on Cloudflare's free plan; heavy users are pointed to the npm package, which needs Node.js 22 or newer. Archestack also publishes safety allowlists of MCP servers that passed its checks, with the caveat that a pass is not a guarantee about the code.

Install

Run in a terminal

claude mcp add --transport http mcp https://mcp.archestack.com/mcp

Add to Settings → Connectors → Add custom connector

https://mcp.archestack.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp": {
      "url": "https://mcp.archestack.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.archestack.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "mcp": {
      "serverUrl": "https://mcp.archestack.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.archestack.com/mcp"
    }
  }
}

Tools this server provides (7)

Read directly from the server.

search_projects
Find open-source AI projects across both Archestack lists by words and filters. Words match names, repos, taglines, categories and the products a project replaces; results rank by how many words match, then exact names, then projects whose name or category holds the words, then by score. Put hard needs in the filters, not the words (no_gpu instead of "without a GPU"). Use it when the user describe
get_project
Everything Archestack has on one project: score and the parts it is made of, place in its category, GitHub facts (stars, license, last commit and release, language, Docker, arm64, GPU, RAM, external services, port), project health, demo and docs links, and the review (summary, audience, strengths, weaknesses). Use it when the user names one project and wants the full picture; for only what it take
deploy_facts
The facts an agent needs before installing or deploying one project: Docker files, arm64 build, GPU need, minimum RAM, outside services it needs, web port, what its README says it needs, docs and demo links, and upkeep (latest release, releases in 12 months, security advisories, its package). null means Archestack does not know. Archestack does not track hosting cost or deploy templates. Use it ri
top_in_category
The ranking of one category, best first, with score and tagline. An unknown category returns the list of categories, so calling it with a guess is a cheap way to learn the category ids. Use it for "what is the best X"; to filter by GPU, arm64 or license, or to search across categories, use search_projects.
compare
Put 2 to 4 projects side by side: score and its parts, place, stars, license, last commit, Docker, arm64, GPU, RAM, external services, strengths and weaknesses. Use it when the user is choosing between named projects ("X or Y"); with only one name, find candidates first with top_in_category or alternatives_to.
check_repo
Check a GitHub repo before installing it, most useful for an MCP server, skill or plugin: whether Archestack lists it, its license in plain words, upkeep, the safety checks it passed (with the failed ones and their evidence) and up to 3 higher-ranked projects in its category. "Checks passed" means those checks passed, not that the code is safe. A repo Archestack does not list returns listed: false
alternatives_to
Open-source projects that replace a paid or closed product (e.g. Cursor, ChatGPT, Notion), highest score first. own_claim is true when the project says so in its own README. Use it when the user names a product and asks what can replace it or how to self-host it instead; to weigh the picks against each other, pass them to compare.

What it does

Filtered project search
Filter by list, category, license family, GPU need and other facts.
Side-by-side compare
Compare scored projects on the same facts.
Open-source alternatives
Find open-source picks for a paid product.
Run requirements
See what a project takes to run, including GPU needs.
Safety allowlists
Admin allowlists of MCP servers that passed Archestack's safety checks.
Hosted or npm
Use the hosted URL or run @archestack/mcp locally.

Good for

  • Find a self-hosted RAG stack that runs without a GPU
  • Compare two vector databases by score and license
  • Look for an open-source replacement for a paid tool
  • Build an approved MCP server list for a Copilot or Claude Code policy

Pricing

Open source

Free, no key

Prices change. Check archestack.com before you buy.

Archestack FAQ

Does it need a key or account?

No. It is read-only with no sign-in.

How fresh is the data?

The open data API refreshes twice a day with the site.

What are the hosted limits?

120 requests a minute per address; it keeps no logs of your questions, per its privacy note.

What is the license of the data?

CC BY 4.0, per the API page.

Is Archestack free?

Yes. Archestack is open source, so you can use and self-host it for free.

How do I add Archestack to Claude Code?

Run this command in your terminal: claude mcp add --transport http mcp https://mcp.archestack.com/mcp

What are the best alternatives to Archestack?

The closest alternatives to Archestack are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to Archestack

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools