AgentIndex icon
AgentIndex
Genexus18MCP logo
Genexus18MCP
★ 38
vs
coder_eval logo
coder_eval
★ 154

Genexus18MCP vs coder_eval

Genexus18MCP: GeneXus MCP Server enables AI agents to interact with GeneXus 18 Knowledge Bases through the native GeneXus SDK. It provides over 30 tools for exploration, editing, analysis, and build lifecycle. The server runs on Windows and requires GeneXus 18, Node.js 18+, and an MCP-compatible client.; coder_eval: Coder Eval runs a real coding agent (Claude Code, Codex, Antigravity, OpenCode or Pi) in a sandbox against declarative YAML tasks and scores the files and commands it produced. It supports weighted 0.0-1.0 criteria, skill-trigger checks, A/B experiments and cost telemetry, and can gate CI on agent quality.

01

TL;DR

Genexus18MCP logo
Genexus18MCPDev Tooling · ★ 38

List all transactions with attribute CustomerId

Read Genexus18MCP full review →
coder_eval logo
coder_evalDev Tooling · ★ 154

Benchmark coding agents on your own domain tasks

Read coder_eval full review →
02

Side-by-Side Comparison

Field
Genexus18MCP logoGenexus18MCP
coder_eval logocoder_eval
Category
Dev Tooling
Dev Tooling
Stars
★ 38
★ 154
License
MIT
Apache-2.0
Install Command
npx genexus-mcp@latest init --kb "C:\KBs\YourKB" --gx "C:\Program Files (x86)\GeneXus\GeneXus18"
uv tool install coder-eval
Updated
1d ago
1d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
ai-agent, ai-agents, ai-tools
agent-evaluation, agent-skills, agent-testing
03

Features

Genexus18MCP logoGenexus18MCP
01Read, edit, analyze, and refactor GeneXus 18 KB objects
0230+ tools for search, editing, analysis, build, layout automation
03Auto-registration with popular AI clients like Claude Desktop, Cursor, Antigravity
04Safe editing with dry-run and idempotency keys
05Lazy worker process to minimize resource usage
coder_eval logocoder_eval
01Declarative YAML tasks with pinned dependencies and success criteria
02Sandboxed execution with resource limits
03Weighted 0.0-1.0 scoring, including LLM-graded rubrics and skill_triggered checks
04A/B experiments across agents, models, tools and prompts
05Telemetry for every tool call, token count and cost
04

Use Cases

Genexus18MCP logoGenexus18MCP
↳List all transactions with attribute CustomerId
↳Add a rule to the Order transaction that validates the total
↳Refactor a procedure to use a new SDT
coder_eval logocoder_eval
↳Benchmark coding agents on your own domain tasks
↳Verify that a skill actually triggers in the agent you ship for
↳Fail CI builds when agent or skill quality regresses
FAQ

FAQ

What is the difference between Genexus18MCP and coder_eval?
Both Genexus18MCP and coder_eval are in the Dev Tooling category. Genexus18MCP has 38 stars, while coder_eval has 154 stars.
Which is better, Genexus18MCP or coder_eval?
The best choice depends on your use case. Choose Genexus18MCP if List all transactions with attribute CustomerId, and coder_eval if Benchmark coding agents on your own domain tasks.
Is Genexus18MCP free or open source?
Yes, Genexus18MCP is open source on GitHub (MIT).
Is coder_eval free or open source?
Yes, coder_eval is open source on GitHub (Apache-2.0).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to Genexus18MCP →Alternatives to coder_eval →Genexus18MCP details →coder_eval details →