Put the Arithmetic in the Tool: an MCP Server for an AWS Waste Scanner
The article shows how to add an MCP server to a Python-based AWS cost scanner so AI agents can query computed totals, breakdowns, filters, and cleanup plans without doing arithmetic themselves. It also covers JSON-RPC over stdio, read-only tool design, end-to-end testing, rounding consistency, and integration with Claude Code.
https://dev.to/aws-builders/put-the-arithmetic-in-the-tool-an-mcp-server-for-an-aws-waste-scanner-3n79
The article shows how to add an MCP server to a Python-based AWS cost scanner so AI agents can query computed totals, breakdowns, filters, and cleanup plans without doing arithmetic themselves. It also covers JSON-RPC over stdio, read-only tool design, end-to-end testing, rounding consistency, and integration with Claude Code.
https://dev.to/aws-builders/put-the-arithmetic-in-the-tool-an-mcp-server-for-an-aws-waste-scanner-3n79
DEV Community
Put the Arithmetic in the Tool: an MCP Server for an AWS Waste Scanner
A cost report gets read twice: once by a person in a terminal, once by an agent through an MCP server. Making the server compute every total instead of handing back rows keeps the two answers the same, and measures the report's own arithmetic against the…
superdesigndev / treg
OpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn
https://github.com/superdesigndev/treg
OpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn
https://github.com/superdesigndev/treg
Discord
Join the Treg Discord Server!
Check out the Treg community on Discord - hang out with 399 other members and enjoy free voice and text chat.
Share how you use Django with Django Probe
The post introduces Django Probe, a tool that scans Django projects and anonymously aggregates how framework APIs and patterns are actually used. The goal is to give Django maintainers better data for decisions around deprecations, new features, documentation, and community priorities.
https://www.better-simple.com/django/2026/09/17/share-how-you-use-django-with-django-probe/
The post introduces Django Probe, a tool that scans Django projects and anonymously aggregates how framework APIs and patterns are actually used. The goal is to give Django maintainers better data for decisions around deprecations, new features, documentation, and community priorities.
https://www.better-simple.com/django/2026/09/17/share-how-you-use-django-with-django-probe/
Better Simple
Share how you use Django with Django Probe
Django Probe is a low effort, high impact way to support the community. By sharing how you use Django, the community can make better decisions.
jev-ultrafast
A browser agent with a dynamic, indexed action space.
https://github.com/browser-use/jev-ultrafast
A browser agent with a dynamic, indexed action space.
https://github.com/browser-use/jev-ultrafast
GitHub
GitHub - browser-use/jev-ultrafast: Fastest and cheapest web agent
Fastest and cheapest web agent. Contribute to browser-use/jev-ultrafast development by creating an account on GitHub.
TATS
TATS is an open-source Python tool for analyzing OAuth 2.0, OpenID Connect, and Microsoft Entra ID tokens, helping security researchers trace authentication flows, identify risky permissions, and visualize token lifecycles.
https://github.com/IceMoonHSV/TATS
TATS is an open-source Python tool for analyzing OAuth 2.0, OpenID Connect, and Microsoft Entra ID tokens, helping security researchers trace authentication flows, identify risky permissions, and visualize token lifecycles.
https://github.com/IceMoonHSV/TATS
GitHub
GitHub - IceMoonHSV/TATS: Token Analysis and Tracking System
Token Analysis and Tracking System. Contribute to IceMoonHSV/TATS development by creating an account on GitHub.
ouroboros
Ouroboros is an open-source AI coding framework that turns vague ideas into verified code through structured interviews, specification-driven execution, automated evaluations, and iterative improvement across multiple coding agents
https://github.com/Q00/ouroboros
Ouroboros is an open-source AI coding framework that turns vague ideas into verified code through structured interviews, specification-driven execution, automated evaluations, and iterative improvement across multiple coding agents
https://github.com/Q00/ouroboros
GitHub
GitHub - Q00/ouroboros: Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation…
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCod...