MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Local cost analyzer for AI coding agents: see where tokens and AI Credits go in Claude Code, GitHub Copilot Chat, pi and mitmproxy sessions. Turn-by-turn cost, prompt caching explained, cost by repository and project, replay on another model, tool-call audit, MCP server with interactive views. Also a VS Code extension: AI Credits Analyzer.
MIT ★ 1 -
agent-cost-mcpgithub.com/vanthienha199/agent-cost-mcpupdated this year
MCP server for tracking AI agent costs in real time. Per-message spending, budget alerts, visual dashboard. Works with Claude Code, Cursor, Windsurf, Codex, Gemini CLI, OpenClaw. Stop overspending on AI APIs.MCP server that tracks AI agent spending in real time. Visual dashboard, budget alerts, 15+ models. Works with Claude Code, Cursor, Windsurf.
MIT ★ 1 -
tokenscopegithub.com/wartzar-bee/tokenscopeupdated this year
See what your AI-coding session actually cost — and what is eating your context. Local, read-only CLI for Claude Code.
rubygems MIT ★ 4 -
Audit your repos and cloud providers for CI and infrastructure cost leaks. CLI + MCP server for AI coding agents (Claude Code, Codex, any MCP host).
MIT ★ 2 -
reasonix-mcp-servergithub.com/kquuen/reasonix-mcp-serverupdated this year
Cost-aware MCP server for AI coding: expensive models plan, cheaper models execute.
MIT ★ 1 -
Track what every AI coding agent costs and see the limit coming. Per-session, per-model cost for Claude Code, Codex, Cursor and 37 more tools from your provider's own token counts, plus limit gauges, a dangerous-command guard and dashboard terminals. Free, Apache-2.0, runs on your machine.
go NOASSERTION ★ 60 -
costhawkupdated this year
MCP server for CostHawk - AI API cost monitoring and optimization with Claude Code tracking
npm MIT -
Know what an AI coding task will cost before you run it. Local MCP server for Claude Code, Codex and Cursor.
npm MIT -
What your AI coding agents cost, per repo, per team and per client. Reads the session logs Claude Code and Codex CLI already write on your machine, prices them, and rolls repos up into teams to watch the spend or clients to bill it back. Includes an MCP s
npm MIT -
MCP server: predicts monthly LLM spend from local Claude Code/Cursor logs. Companion to milo-cost-auditor (diagnose past + predict future). x402/L402 payable for paid tier. Built by Milo Antaeus (autonomous AI agent). MIT.
MIT -
Claude Code plugin marketplace: 6 local-first MCP servers for safer AI coding — MCP security, Postgres migrations, OpenAPI breaking changes, npm deps, LLM costs, SEO.
MIT -
Dead man's switch, cost cap and outcome check for unattended AI agents (Claude Code, OpenClaw, n8n, cron)
npm MIT -
CLI and MCP server that verifies AI coding agent context-reduction proxies' token and cost savings claims
pypi Apache-2.0 -
Observability for AI coding assistants — cost tracking, efficiency scoring, and anti-pattern detection for Claude Code, Cursor, Copilot, and more. Local-first; New Relic optional.
npm Apache-2.0 ★ 67 -
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more. Free-first fallback chain cuts costs 35-80%.
npm MIT ★ 130 -
Cost-aware, local-first skill routing for AI agents. MCP server + CLI + Claude Code hook. Tested on 141 real skills.
npm MIT ★ 1 -
Kaldrix plugins for Claude Code, Gemini CLI and ChatGPT: connect your AI assistant to Kaldrix construction projects, schedules and cost estimates.
MIT -
Run, watch, and meter Claude Code, Codex CLI, Gemini CLI, OpenCode, and Kiro from one CLI. Normalized events, cache-aware token usage, cost accounting verified against each agent's own records, budget caps, OpenTelemetry gen_ai spans, Langfuse traces, and a live web dashboard + MCP server.
npm MIT ★ 2 -
Measure what each successful task of your AI app costs — and prove when a change makes it cheaper without hurting quality. CLI, MCP server and Claude Code skill.
MIT -
Free construction MCP server for Claude, Cursor and AI assistants: cost codes, CPM critical path, pay applications, change orders, earned value, quantity calculators. Offline, no dependencies.
NOASSERTION ★ 3 -
@stackspend/mcp-serveractive
MCP server for StackSpend: query and act on cloud and AI costs from Claude Code, Claude Desktop, Cursor and other MCP clients
npm UNLICENSED -
nimbiq-mcpgithub.com/nimbiq/nimbiq-mcpupdated this year
Nimbiq AI cost intelligence for Claude Code, Cursor, Windsurf and GitHub Copilot
pypi BSL-1.1 -
Track MCP server token usage and costs for AI coding tools
MIT ★ 2 -
MCP server that lets AI agents ask CostTrace what a code or infrastructure change actually cost.
npm Apache-2.0 -
costpilot-mcpgithub.com/solemn-cap/ai-cost-pilotupdated this year
CostPilot MCP server for per-request AI cost tracking and prompt optimization for Claude Code, Cursor, Windsurf, and more
npm MIT -
getaimetergithub.com/khavel/aimeterupdated this year
Track AI coding costs across Claude, Cursor, Codex, Copilot, and Gemini. MCP server, billing blocks, optimization recommendations.
npm MIT -
watchtower-mcpgithub.com/edentan26/watchtowerupdated this year
Cost tracking + deep security scanning (live RLS cross-tenant probe, leaked-key verification) for AI builders. MCP server for Claude Code.
npm MIT -
OkOvia MCP server — query your AI cost, margin, and reliability from any MCP client (Claude Desktop, Claude Code, …) in natural language.
pypi MIT -
MCP server and costfluent command line tool that let AI assistants such as Claude Code and Cursor, and your scripts and CI jobs, read your Costfluent cloud costs, saved cost reports, budgets and anomalies, and change them where an Owner allows it. They run on your machine with the API token you give them and never delete anything.
mcpb Apache-2.0 -
agent-tts-free-mcpactive
Zero-cost, unlimited neural voice generator & MCP server for AI coding agents and autonomous content pipelines. Powered by Edge neural speech.
npm MIT -
Azure FinOps playbook as code: 10 cost optimization patterns, AI FinOps (token attribution, routing, caching, PTU, ROI, eval gate) and an approval-gated FinOps agent over MCP. Offline, synthetic data, list-price snapshot.
MIT -
sql-review-agentgithub.com/ARAVINDHRAJA123/sql-review-agentupdated this year
Agentic AI that reviews BigQuery SQL before execution — estimates cost via dry_run, flags full table scans and missing partition filters, and suggests rewrites. Works with Claude Code, OpenClaw, Cursor, Zed via MCP.
★ 1 -
Construction estimating as code. MCP server with 48 tools for materials, labor, cost, structural, permits, plumbing, electrical, HVAC, and estimate generation. Replaces SaaS estimating tools for AI agents and contractors.
pypi MIT -
See what each AI agent, client and job costs, in dollars at list price, and give any job a spend ceiling: preflight answers approved: false past it, and your code decides. An SDK and an HTTP API, not a proxy.
pypi MIT ★ 7 -
Cerver for Claude Code: an AI backend for your app, with cost and caps for each customer
MIT -
Precise Symbol-Level Code Retrieval MCP Server: Cut AI Token Costs 95% in 2026
-
judgesgithub.com/KevinRabun/judgesupdated this year
MCP server with specialized judges to evaluate AI-generated code for security, cost, scalability, cloud readiness, and best practices.
npm MIT ★ 7 -
Best Token-Efficient AI Coding Tools 2026 – Reduce Costs 90% with Local Memory & MCP
★ 1 -
Solwynno update data
Check budgets before AI spend, record what your code spends and read Solwyn costs.
pypi -
Intelligent code knowledge graph for AI coding agents. Reduces cost by up to 44%, speeds up exploration by up to 57%, and boosts smaller model quality to match Opus.
npm MIT -
memoragithub.com/VnemAIDev/memoraupdated this year
Persistent, semantic memory for AI coding agents — local-first MCP server (~85-95% lower per-session context cost)
MIT -
Zero-cost token optimization engine for AI coding assistants (Claude Code, Cursor, Antigravity, Windsurf). Saves 70-95% tokens via AST skeletons, differential cache, and line slicing.
NOASSERTION ★ 6 -
Structured code retrieval for AI agents — index once with tree-sitter, query symbols precisely via MCP. Cut code-reading token costs by up to 99%.
NOASSERTION ★ 4 -
Local MCP server for Tilden’s aibill CLI: inspect coding-agent usage, cost evidence and Context Health from a compatible AI client.
npm MIT -
Agent Boostergithub.com/sseshachala/agent-boosterno update data
Cut AI agent token costs 5-15x — routes only relevant code symbols instead of full files.
pypi -
Local-first Build Truth & verification layer for AI coding agents. Stops hallucinations, cuts token costs by 90%, and fixes monorepo test failures for Claude, Cursor, Aider, & Copilot.
npm Apache-2.0 ★ 3 -
reponoesisgithub.com/MathewAddala/reponoesisupdated this year
Local, zero-cost semantic change propagation and logic contradiction check for AI coding agents. Cryptographic Merkle linking + stdio Model Context Protocol (MCP) server.
MIT ★ 1 -
Hard budget enforcement for Claude Code tool calls — PreToolUse gating, AI-agent cost control, Cycles usage metering, and MCP budget tools.
Apache-2.0 -
agent-mux-mcpgithub.com/wowoyong/agent-muxupdated this year
MCP server for agent-mux — routes tasks between Claude Code and Codex CLI based on complexity, optimizing AI coding subscription costs
npm MIT -
让你电脑里那块闲置的 NPU,第一次替你的 AI 编程助手干活:按语义找代码、不占 CPU、不出网。 | Put your idle Intel NPU to work for AI coding agents - semantic code search, fully offline, zero CPU cost.
MIT ★ 1 -
Live AI compute pricing oracle MCP server — real-time LLM model prices across providers. Includes Claude Code skills for session cost analysis.
npm MIT -
Local multi-agent AI code reviewer powered by Ollama — 15 specialist agents review your git diff with zero API calls or cost. Outputs markdown, JSON, SARIF, or GitHub PR annotations; also ships an MCP server and a VS Code/Cursor extension.
MIT ★ 2 -
Local, private browser for AI coding CLI sessions (Claude Code + Copilot + Codex) — unified search, usage/cost dashboard, resume-from-anywhere, cross-CLI bridge, reasoning trails, MCP server
MIT ★ 3 -
reporaggithub.com/davidnbr/reporagupdated this year
Fully local, zero-cost RAG knowledge layer for AI coding tools. Achieve near perfect codebase awareness with any AI tool. Supports Claude Code, Cursor, Codex, Antigravity
MIT ★ 1 -
vigilogithub.com/Idan3011/vigiloupdated this year
Audit trail and cost tracker for AI coding agents. See exactly what Claude Code and Cursor read, wrote, and executed - locally, in real time.
MIT ★ 4 -
ollama-bridge-mcpgithub.com/ElnurIbrahimov/ollama-bridge-mcpupdated this year
MCP server that gives Claude Code 27 AI brains via Ollama — 15 cloud + 12 local models. Auto-routing, batch comparison, smart delegation. Reduce API costs, get specialized models for code, math, vision, reasoning.
MIT -
Context compression for AI agents — cut token usage costs with retrievable CCR compression. Rust core + Python API, Claude Code & Codex plugin, MCP server. PyPI: furl-ctx
Apache-2.0 ★ 5 -
GraphRAG code search over MCP. Parses code with tree-sitter, weaves a Neo4j code graph, and serves hybrid semantic search to AI agents at lower cost than grep.
MIT ★ 1 -
Pre-Execution Token Budget Firewall & Cost Telemetry Sentinel for AI Coding Agents
npm MIT -
Bi-temporal, 4-tier hybrid cognitive memory engine for AI coding agents (Claude Code, Cursor, Windsurf) via FastMCP. Eliminates amnesia and reduces token costs using local PostgreSQL & Neo4j.