What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Neo — AI/ML Engineering MCP server?
AI/ML engineering MCP server for Neo — submit tasks, track execution, and retrieve outputs.
How to install Neo — AI/ML Engineering
Copy-paste configuration for popular MCP clients.
NEO_SECRET_KEYrequiredsecretYour Neo API secret key (starts with sk-v1-). Get one at https://heyneo.com.
NEO_ENVIRONMENTNeo backend environment: 'production' (default) or 'staging'.
NEO_WORKSPACE_DIRrequiredAbsolute path to your project/git root where Neo writes files. Required for Postman and recommended for all clients.
{
"mcpServers": {
"MCPServer": {
"command": "uvx",
"args": [
"neo-mcp"
],
"env": {
"NEO_SECRET_KEY": "<YOUR_NEO_SECRET_KEY>",
"NEO_ENVIRONMENT": "<YOUR_NEO_ENVIRONMENT>",
"NEO_WORKSPACE_DIR": "<YOUR_NEO_WORKSPACE_DIR>"
}
}
}
}Related MCP servers

StratEvo
Evolve trading strategies using genetic algorithms across 484+ market factors with walk-forward validation.
Cross-vendor semantic memory: recall across Claude Code / Codex / Grok sessions by meaning.
Clinical AI for lab analysis, biomarker scoring, health narratives, and risk insights.
View repository →
DispatchSEO
AI-powered SEO manager: keyword research, content PRs, and rank tracking for coding agents.

Verify trading-strategy backtests: look-ahead probes, trading costs, Deflated Sharpe, walk-forward.


