rafsilva85/credit-optimizer-v5
MCP server Claude CodeCodexCursor +2
AI Credit Optimizer MCP Server — Save 30-75% on AI credits with ZERO quality loss. 55% average savings across 53 adversarial scenarios. Runs locally from the mcp-credit-optimizer Python package.
MCP server Claude CodeCodexCursor +2
Compression with a quality contract — cache-aware, causally-pruned context compression for agentic runtimes, gated by a statistical non-inferiority test. Runs locally from the distil-llm Python package.
MCP server Claude CodeCodexCursor +2
Ask Claude about your AWS, Azure, GCP, and SaaS costs. MCP server with anomaly detection, rightsizing, and Jira ticketing. Runs locally from the finops-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server for KubeOpt — query Kubernetes cluster costs from Claude, Cursor, or Windsurf. Runs locally from the kubeopt-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "attune-ai" as configured in Smart-AI-Memory/attune-ai. Runs locally from the python Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Give AI agents full access to the Harness.io platform — manage pipelines, deployments, cloud costs, chaos engineering, feature flags, SEI, and 125+ resource types through 11 MCP tools. Runs locally from the harness-mcp-v2 npm package.
MCP server Claude CodeCodexCursor +2
Catch LLM cost changes in code review. Infracost for LLM spend. Runs locally from the tokentoll Python package.
NORTHTEKDevs/lossless-context-mcp
MCP server Claude CodeCodexCursor +2
Agent context flight recorder: restore after compaction, fan-out packs, signed git-bound receipts. Runs locally from the lossless-context-mcp npm package.
MCP server Claude CodeCodexCursor +2
AURA — a tiny, dependency-free token saver. Answers prompts from a local cache, saved skills, or deterministic compute, distills bloated system prompts, shapes noisy tool output, and remembers tool calls across sessions — so you call (and pay for) the LLM. Runs locally from the shaddai-aura npm package.
MCP server Claude CodeCodexCursor +2
Real-time Firestore schema context for AI coding agents. Stop hallucinating field names. Runs locally from the lintbase-mcp npm package.
MCP server Claude CodeCodexCursor +2
The open routing layer for AI tools: tool calls routed per policy, decision on every result. Runs locally from the frugal-mcp npm package.
MCP server Claude CodeCodexCursor +2
Track AI agent costs, detect waste, optimize models, and prove ROI. 23 MCP tools across 10 domains. Runs locally from the @metrxbot/mcp-server npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "ferry" as configured in PunkGo/ferry. Runs ./bin/ferry-mcp.py with python3.
MCP server Claude CodeCodexCursor +2
Trazum as an MCP server: let an agent price and budget its own prompts before it sends them. Runs locally from the @trazum/mcp npm package.
MCP server Claude CodeCodexCursor +2
Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff. Runs locally from the promptlint-mcp npm package.
rafsilva85/manus-credit-optimizer
MCP server Claude CodeCodexCursor +2
AI Credit Optimizer MCP Server — Save 30-75% on AI credits with ZERO quality loss. 55% average savings across 53 adversarial scenarios. Runs locally from the mcp-credit-optimizer Python package.
MCP server Claude CodeCodexCursor +2
MCP server "promptthrift-mcp" as configured in woling-dev/promptthrift-mcp. Runs locally from the promptthrift-mcp Python package.
MCP server Claude CodeCodexCursor +2
Offload grunt work from your subscription LLM to cheap models via MCP — auto-routing, a savings ledger, and billing isolation. Runs locally from the cheaplane Python package. Needs 5 environment variables to run.
mazhar480/Azure-FinOps-Optimizer-MCP
MCP server Claude CodeCodexCursor +2
MCP server "azure-finops-elite" as configured in mazhar480/Azure-FinOps-Optimizer-MCP. Runs locally from the azure-finops-elite Python package.
OjasKord/local-model-suitability-mcp
MCP server Claude CodeCodexCursor +2
Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference. Runs locally from the local-model-suitability-mcp npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
A second opinion for AI agents: one prompt across several live Gonka models + roles, one call. Remote server at mcp.gogonka.com.
MCP server Claude CodeCodexCursor +2
LLM API cost interceptor and budget enforcer for AI agents. Runs locally from the agentcents Python package.
MCP server Claude CodeCodexCursor +2
Offline MCP: predict LLM call cost and pick the cheapest capable model. No keys, no network. Runs locally from the @workswarm/modelcostsaver npm package.
MCP server Claude CodeCodexCursor +2
Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models. Runs locally from the llmtest-mcp npm package. Needs 1 environment variable to run.