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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). 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.
-
@liberliu/dysonspherain-memoryupdated this year
Quick-start wrapper for DysonSpherain MCP memory, hooks, plugins, and token economy diagnostics.
npm GPL-3.0-or-later -
thrift-mcpgithub.com/seslak/thrift-mcpupdated this year
Local context-economy MCP gateway for bounded repository inspection, file search, token estimates, and workflow telemetry.
MIT -
Token-economy stack for AI coding agents — input/output compression + MCP tools to cut agent session cost.
NOASSERTION -
This server provides high-performance GitHub interactions with a strict Token Economy First design, native zero-dependency HTTP client, and a 3-Tier Read-Only security guard.
npm MIT ★ 1 -
MCP server for Kaiten API integration with Claude - Production-ready with Token Economy (90% savings), Verbosity control, Response formats, Logging & Monitoring
npm MIT -
MCP server for Lazy Lions — read the collection, holders, rarity, listings, and the $LAZY token economy from any AI agent.
npm MIT -
@iflow-mcp/vsaranyuk-kaiten-mcp-serverupdated this year
MCP server for Kaiten API integration with Claude - Production-ready with Token Economy (90% savings), Verbosity control, Response formats, Logging & Monitoring
npm MIT -
memstratagithub.com/ConsultRuss/memstrataupdated this year
Semantic memory MCP server (FastMCP + Postgres/pgvector) with tiered recall depth for token economy. Ships a retrieval-quality eval suite — precision@5 0.69, recall@10 0.82.
MIT -
Agent-native Stata bridge for empirical research — run DiD/IV/RDD and publication-ready tables from Claude Code, Jupyter, or VS Code on one token-economy result schema, with StatsPAI cross-validation. | 面向实证研究的智能体 Stata 桥接器——在 Claude Code、Jupyter、VS Code 中用一套省 token 的结果格式跑 DiD/IV/RDD 与出版级表格,并支持 StatsPAI 跨栈交叉验证。
pypi MIT ★ 55 -
montra-mcp-servergithub.com/montrafinance/montrafinanceupdated this year
MCP server for Montra Finance — 93 tools for autonomous crypto trading, DeFi protocol analysis, multi-chain intelligence, agent swarms, risk management, order management, token discovery, copy trading, portfolio optimization, and the $MONTRA burn economy
npm MIT -
Retired: offline since October 2026 and takes no calls or payments. Reference code for a Solana token-risk API (x402 pay-per-call, MCP).
MIT -
shared-context-cache-mcp-servergithub.com/AiAgentKarl/shared-context-cache-mcp-serverupdated this year
MCP server for shared context caching — AI agents share computed results to reduce token cost and latency
pypi MIT ★ 1 -
IcyCache - universal LLM gateway with a local cache. I see cache, I burn cache.
pypi MIT