AI Tools

OpenAI's Assistants API sunset on August 26, 2026, leaving 2.3M API keys stranded. This FastMCP server translates legacy Assistants API calls to the new Responses API format, automatically converting threads, runs, and function calls to MCP-compatible tool invocations.

Claude Opus 5 costs $5/$25 per million input/output tokens — the same as Opus 4.x but approaching Fable 5 capabilities at half the cost. This FastMCP server tracks real-time token spend, enforces per-session budget gates, and auto-routes to Sonnet 5 when thresholds are breached.

Z.ai's GLM-5.3-Flash went viral within 48 hours of its August 26 release — a 320B-A18B natively multimodal MoE under MIT license at $0.075/M input. This FastMCP server exposes its text, image, and video capabilities as MCP tools for Claude Desktop and Cursor.

Distributed tracing data lives in Jaeger and Grafana Tempo dashboards that agents can't query. This FastMCP server bridges the gap, exposing OpenTelemetry traces, service dependencies, and latency percentiles directly to AI agents in Claude Desktop and Cursor for real-time debugging.

Terraform state files hold the complete picture of your infrastructure, but querying them requires manual JSON parsing. This FastMCP server exposes Terraform state intelligence — resource inventory, drift detection, and cost estimation — directly to AI agents in Claude Desktop and Cursor.

Debugging Kubernetes clusters requires jumping between kubectl, Grafana dashboards, and logging tools. This FastMCP server consolidates cluster health, pod diagnostics, and resource optimization into a single MCP tool that AI agents can query directly from Claude Desktop or Cursor.

Gatik just raised $200M to scale driverless freight for PepsiCo, Walmart, and Tyson. This MCP server exposes autonomous freight tracking to AI agents with real-time ETA, route optimization, and exception management.

Google just launched Gemini Enterprise for Legal. This MCP server provides the backend tooling—clause extraction, due diligence checks, and regulatory compliance—for AI agents working in legal workflows.

AI coding agents write code in seconds but wait 8 minutes for CI feedback. This CircleCI MCP server bridges the gap—letting agents trigger pipelines, parse test failures, and auto-fix builds without leaving their IDE.

NVIDIA Jetson Orin Nano 2 powers millions of edge AI devices, but monitoring fleet health requires a native MCP server. This guide builds one with tools for device telemetry, inference status, battery management, and task assignment.

Multi-region agent deployments lose state on failover. CockroachDB's distributed SQL provides globally consistent agent state with automatic failover. This MCP server exposes CockroachDB to AI agents for transactional state management across regions.

Weaviate's vector database powers semantic search for agent RAG pipelines, but connecting it to MCP requires stateless-aware tool design. This guide builds a production Weaviate MCP server with hybrid search, reranking, and per-tenant collection isolation using the 2026-07-28 spec.