MCP.Market

Abell MCP server

by abelljs·io.github.abelljs/abell·v0.0.9·442 stars

AI tools related to Abell. Currently includes MCP of Abell

C58/100grade C
What users say
No reviews yet
Be the first
Safety scan
C58/100

full report

Adoption
Growing

442 stars

Reviews

Write one

Nobody has reviewed Abell yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Abell tools (2)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_abell_syntax

    This is to help understand the syntax of Abell and get basic understanding of abell. Call this tool everytime you're working with .abell files or need to show abell code snippets

  • scaffold_new_abell_app

    This scaffolds a new full fledge abell application. Note: Before calling tool, ensure you're in user's current working directory, ensure the directory is empty. Confirm the directory of scaffolding from user before running the tool

Public scan report

scanner v0.1.10 · 2026-10-01 · same rubric, same numbers if you re-run it

1 high
  • Code scan7 source files scanned13/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 212 days ago4/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Findings (1)

  • highShell command built from a string (injection risk)exec.shell-concat
    dist/mcp.js: … ] }; } } execSync(`npx -y create-abell@latest ${projectName} --installer ${installer} --template default`, { stdio:…
Overall 58/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Abell compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
58/100
higher than 13% of 48,255 servers
Tools
2
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
442
more than 95% of 28,688 servers

What its tools let an agent do: 2 read

Install Abell in Claude Code, Cursor or VS Code

Runs npx -y abell-ai on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add abell -- npx -y abell-ai
Add to Cursor

What the publisher says

From the Abell repository's README, as published. We do not edit it. Read it on GitHub

   

A Low-Level, Framework Agnostic, Highly Flexible Static-Site-Generator to help you build Static Sites without too much of learning curve.

Documentation: https://abelljs.org

📖   Create Abell Project

npx create-abell my-abell-site
cd my-abell-site
npm run dev

Check out https://abelljs.org for complete documentation.

🚀   Syntax Example

<!-- index.abell -->
<html>
  <body>
    I can render JavaScript! Look: {{ 10 + 10 }}
  </body>
</html>

Output:

<!-- index.html -->
<html>
  <body>
    I can render JavaScript! Look: 20
  </body>
</html>

Learn More at Syntax Guide

📄 License

This project is licensed under the MIT License

🤗 Contributing

Check out CONTRIBUTING.md

If you like my work, you can sponsor me on GitHub: https://github.com/sponsors/saurabhdaware 🌻

Nothing above is checked by us. What we check is on the safety report.

Abell: common questions

Is Abell MCP server safe?
With care: it is graded C, so read the findings first (58/100). Read the Abell safety report
How do I install Abell?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Abell need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Abell maintained?
The last commit was 245 days ago (2026-03-04). The latest release is v0.0.9.
How does Abell compare with other MCP servers?
safety score 58/100 (higher than 13% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.