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.
-
project-brain-mcp-servergithub.com/nihalcastelino/project-brain-mcpupdated this year
Project management MCP server for AI-assisted development. Track tasks, conversations, decisions, token usage, and costs.
npm MIT -
@rulecatch/ai-poolergithub.com/thedecipherist/rulecatch-sdkupdated this year
Monitor and track AI coding activity in Claude Code — real-time analytics, token usage, cost tracking, rule enforcement. Zero overhead.
npm MIT -
codeledgergithub.com/bhvbhushan/codeledgerupdated this year
Token-level cost intelligence for Claude Code — per-project, per-agent, per-skill usage tracking with conversational MCP querying and local dashboard
npm MIT -
token-lens-mcpgithub.com/mdfifty50-boop/token-lens-mcpupdated this year
MCP server for analyzing and optimizing context window token usage — audit tool definitions, compress schemas, track usage, and reduce bloat
npm MIT -
docxenginegithub.com/ruwadgroup/docxengineupdated this year
AI-optimized DOCX manipulation engine: deterministic OOXML editing with tracked changes, hash-anchored addressing, and a token-efficient agent view.
pypi Apache-2.0 -
promptthrift-mcpgithub.com/woling-dev/promptthrift-mcpupdated this year
Smart token compression MCP server for LLM apps. Gemma 4 local compression, multi-model cost tracking, intelligent model routing. Save 70-90% on API costs.
MIT ★ 1 -
contextpulse-mcpgithub.com/DIYA73/contextpulse-mcpupdated this year
Real-time MCP server that tracks context budget, detects agent loops, and alerts before token overflow — for Claude Code, Cursor, and any MCP-compatible AI tool.
★ 1 -
slush-meme-mcp-servergithub.com/slush-meme/mcp-serverupdated this year
MCP Server for slush.meme — AI-native meme coin launchpad on Avalanche. Real on-chain trading, token deployment, portfolio tracking, and risk scoring.
npm MIT -
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.
NOASSERTION ★ 60 -
MCP server for Cabal-Hunter — Solana token rug & cabal detection for AI agents. Wallet clusters, same-block bundles, deployer track record with peak market caps, honeypot and authority traps. 5 free scans/month, or 250 with a free key. Card, USDC or x402.
npm MIT -
agent-cost-tracker-mcpgithub.com/rumblingb/agent-cost-tracker-mcpupdated this year
MCP server: Track AI agent token usage and API costs — npm wrapper
npm MIT -
Claude Code plugins: work tracking, statusline lab, token-usage panes, GLM quota, readability + local-LLM MCP servers
npm MIT -
@nexusforgetools/crypto-intelgithub.com/nexusforge-toolsupdated this year
Crypto intelligence — on-chain analytics, whale tracking, DeFi yields, token metrics. MCP server for AI agents.
npm MIT -
Etherscan Toolsno update data
Access Ethereum blockchain data effortlessly. Check balances, view transaction history, track token transfers, and fetch contract ABIs with ease. Enhance your Ethereum interactions with real-time gas prices and ENS name resolution.
smithery -
cache-manager-mcpgithub.com/datawithdanny/cache-manager-mcpupdated this year
Save tokens across AI agent chats with prompt TTL tracking, handoff memories, and cost insights — over MCP.
MIT -
Read-only MCP server for a tracked KOL wallet's portfolio P&L and its trades on a token mint.
Apache-2.0 ★ 9 -
Power MCP servers for persistent memory, project tracking, and token-efficient AI workflows with a plugin-based MCP architecture
-
freshrss-mcp-gogithub.com/XimilalaXiang/freshrss-mcp-goupdated this year
Go MCP server for FreshRSS — 15 tools to manage feeds, search articles, and track subscriptions. Token-efficient, ~32MB Docker image
★ 1 -
Production-grade Model Context Protocol (MCP) server for Google Docs with native comment anchors, suggestion tracking, styled redlines, tables, and low-token Markdown reading.
MIT ★ 1 -
An MCP server and CLI to track model prices, detect volatility, and optimize token costs on OpenRouter.io for AI Agents such as Hermes or OpenClaw.
MIT ★ 2 -
baselings-mcpgithub.com/jimbo530/baselings-mcpupdated this year
49 MCP tools for AI agents on Base chain — DeFi swaps ($0.10 max, guardrailed), token launches with permanently locked liquidity, reactor timing, portfolio tracking, liquidity depth, pet game. Every action burns MfT supply.
npm MIT -
Candidate Hub MCPno update data
**CandidateHub** gives AI agents a complete job-search toolkit backed by [aicandidatehub.com](https://www.aicandidatehub.com) — 18 tools covering the whole application lifecycle. ## What your agent can do - **Jobs** — import postings from any URL, search saved jobs, track applications end-to-end - **CVs & cover letters** — generate job-tailored CVs and cover letters from your profile - **Fit & pay** — analyze job fit against your profile; benchmark compensation for any role - **Profile** — import your résumé once; every tool builds on it ## Setup (2 minutes) 1. [Create a free account](https://www.aicandidatehub.com/login?utm_source=mcp&utm_medium=ai-agent&utm_campaign=smithery) 2. Mint a Personal Access Token at **Account → MCP Tokens** 3. Paste it as `candidatehub_token` when installing _Runs locally over stdio. Starts and lists tools without a token; API-backed tools need one._
smithery -
token-auditgithub.com/littlebearapps/token-auditupdated this year
Token usage auditor for AI coding tools. Investigate context bloat across Claude Code, Codex CLI & Gemini CLI.
pypi MIT -
agent-costcenter-mcpgithub.com/mdfifty50-boop/agent-costcenter-mcpupdated this year
MCP server for AI agent cost tracking — per-agent attribution, budget alerts, model cost comparison
-
MCP server providing AI agent observability — tracing, cost tracking, performance monitoring, and audit trails
npm MIT -
MCP server providing AI agent observability — tracing, cost tracking, performance monitoring, and audit trails
-
Daily snapshots of your AI coding usage, kept forever: local dashboard, optional Cloudflare Worker backup, MCP servers over both.
MIT -
@aipper/zentao-mcp-servergithub.com/aipper/zentao-mcpupdated this year
A minimal MCP server for ZenTao (token + focused bug workflow tools).
npm MIT -
@enterpret/jira-mcpgithub.com/aavaz-ai/jira-mcp-serverupdated this year
Enterpret fork of @aashari/mcp-server-atlassian-jira adding an ATLASSIAN_OAUTH_BEARER mode (3LO bearer + cloudId discovery) so a Nango-supplied access token plugs straight into Jira Cloud REST. Used by the Orbit/wisdom-v2 jira_mcp bring_token connector.
npm ISC -
What your coding-agent seats and tokens buy, from your own machine: Claude Code and Codex tokens and API-equivalent cost by day, project and model, burn toward your own limits, and a flag when the rate changes. Local, no account.
MIT -
tracksiyactive
Agent-first CLI and MCP server for Tracksiy: errors, uptime, alerts, releases and source maps, from one token.
npm MIT -
MCP server for Jira with scoped API tokens — the only server that supports Atlassian's modern authentication
Apache-2.0 ★ 4 -
LLM cost calculator, token counter, latency benchmark, CI guardrail, MCP server, and VS Code/Cursor extension.
MIT ★ 1 -
MCP Server that solves context window overload — smart tool pruning, relevance scoring, budget tracking for AI agents
MIT ★ 1 -
MCP server for @mukundakatta/agentbudget — token + dollar budget caps for AI agents over stdio. Drop into Claude Desktop, Cursor, Cline, Windsurf, Zed.
MIT -
A local-first MCP server that answers, from real data on your machine: How many tokens have I used, from which client, model and session — and what did it cost?
MIT ★ 1 -
Claude Code quota planner: a status line for your 5h/7d windows — or your USD budget on pay-per-token auth — plus an MCP server that says whether a task fits before you start it.
MIT -
Read-only Model Context Protocol server for WHOOP, over stdio. Browser OAuth login with automatic token refresh, and scope-gated tools across WHOOP's v2 API: cycles, sleep, recovery, workouts, profile and body measurements, plus summaries that digest the last N days into one answer.
MIT -
See where your OpenAI Codex tokens, dollars and plan limits go: every response counted once, live 5-hour and weekly limits from your own logs, quota forensics, a web dashboard, menu bar and tray, an MCP server and a share card. Python, no dependencies, no login.
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