任何 MCP 工具
您的插件是一个小的 MCP 服务器。lean-ctx 会启动它并为您与之通信。无需分叉,无需重新编译。
Addons
一个命令即可将任何 MCP 工具连接到您的网关——然后其输出就像您自己的代码一样得到处理:清除密钥,压缩至令牌预算,并在您的代理读取之前进行搜索。这不是插件列表;这是扩展了您上下文管道的 context engineering。
这是添加插件后发生的事情。插件返回的每个结果都会经过与您自己的代码相同的管道,然后您的代理才能看到它。它会变得更小、可搜索,对于某些插件来说,甚至可以直接放入您已经使用的 ctx_ 工具中。
您的插件是一个小的 MCP 服务器。lean-ctx 会启动它并为您与之通信。无需分叉,无需重新编译。
每个结果首先会经过四个步骤:
结果会进入与您的代理已经调用的相同的 ctx_ 工具。一个查看的地方,而不是十个。
✓在一个地方搜索您自己的代码和所有插件。
✓任何内容到达您的代理之前都会剥离敏感信息。
✓结果会被缓存,因此再次读取它们基本上是免费的。
只需运行一次 lean-ctx addon add 即可安装这些中的任何一个。标记为“已列出”的插件尚未有 MCP 端点,因此它们链接到其项目本身。
Reversible context compression for tool outputs, logs, files and RAG chunks — 60–95% fewer tokens, originals retrievable on demand. Installs on add (uv tool install) and wires its MCP server (headroom mcp serve) into the lean-ctx gateway.
Deterministic context compressor for MCP agents — shrinks prompts, conversation history, code digests, file deltas and shell output with zero ML at query time. Single Rust binary; installs on add (npm) and wires its MCP server (sophon serve) into the lean-ctx gateway.
Single-binary CLI proxy that filters and compresses shell command output by 60–90%. Reaches MCP clients through the community rtk-mcp bridge (built from source), so the lean-ctx gateway can run commands through it.
Packs a whole repository into a single AI-ready file. Its MCP server (npx repomix --mcp) lets agents pack local or remote repos and grep the output on demand.
LSP-backed semantic code retrieval, editing and refactoring — the IDE for your coding agent. Connects over MCP via stdio or Streamable HTTP.
Compresses any codebase into LLM-ready semantic context with Tree-sitter WASM (TypeScript, JavaScript, Python, PHP, Dart) — symbol-level reads and AST-aware edits. Runs on add via npx; no install or native build needed.
Parses your whole repo with Tree-sitter into a semantic graph of symbols, references and dependencies — symbol search, call graphs and impact analysis. 18 tools, 8 languages, zero infrastructure or keys. Runs on add via npx.
Local code-intelligence index that gives agents surgical access to symbols — project outline, get/expand symbol, hot-path and references — backed by a SQLite index. Installs on add (.NET global tool) and wires its MCP server.
Turns code, docs, schemas and more into one queryable knowledge graph for agents. Ships an MCP server (stdio + HTTP), but serving needs a graph built by `graphify extract` (an LLM-backed step), so it is listed rather than auto-installed.
Semantic code search over an entire codebase (hybrid BM25 + dense vectors) via @zilliz/claude-context-mcp. Needs a Milvus/Zilliz vector database and an embedding API key to run, so it is listed rather than auto-installed.
Local long-term memory and context compression for coding agents — a markdown vault with hybrid BM25 + vector search and progressive disclosure, no API key required. Installs on add (npm) and wires its MCP server (context-mem serve).
Drop-in long-term memory for agents (vector + graph + key-value). Provides an official MCP server, but needs an API key/backend to run, so it is listed rather than auto-installed.
Builds a queryable knowledge graph plus vector store from your data (ECL / GraphRAG pipeline). Ships an MCP server with local default databases, but needs an LLM API key to process, so it is listed rather than auto-installed.
Stateful agent runtime that manages its own memory like an operating system (core + archival tiers). Exposes MCP-compatible tools, but needs a running server + database, so it is listed rather than auto-installed.
Temporal knowledge-graph memory for agents — a bi-temporal entity/edge graph with hybrid semantic, keyword and graph search. Ships an MCP server, but needs a Neo4j/FalkorDB backend and an LLM API key, so it is listed rather than auto-installed.
Memory platform for AI agents — persistent threads, a knowledge graph and semantic recall via a managed cloud or self-hosted Community Edition. Reaches agents over MCP, but needs an account/API key, so it is listed rather than auto-installed.
Structured step-by-step reasoning tool — the official MCP reference server for breaking a hard problem into revisable thoughts.
Directive-driven Markdown for agent plans. Reusable macros, phase-isolation and single-sourcing keep plans token-lean and cache-safe — written hard against lean-ctx, inspired by MarkdownAI.
Official MCP reference server that exercises every protocol feature — install it to verify your lean-ctx gateway can discover and call downstream tools.
No addons match your filters.
+部署一个 MCP 服务器 + 一个清单文件,并在注册表中占位。
这是让您的工具出现在全天都在终端工作的人面前的最简单方法。
用户只需运行一次 lean-ctx addon add,您的工具就会在其网关中上线。没有派生,没有重新编译,没有设置指南。
被列入内置二进制文件和本页面注册表中的列表。每个 lean-ctx 用户都只需一个命令就能使用您的工作成果。
lean-ctx 可以将您的输出折叠到它用于您自己代码的 ctx_ 工具中。人们随后可以将您的插件像处理其他所有内容一样进行搜索和图表化,而不是让它处于侧通道。
一个插件会在您的机器上运行真实代码。因此 lean-ctx 会在它安装之前向您展示它确切会做什么,并且团队可以设置规则,而单个仓库无法覆盖这些规则。
在任何东西运行之前,您会看到它将启动的确切服务器以及一个简短的安全检查:远程端点、shell 访问、未固定版本。直到您说“是”,任何内容都不会连接进来。
将您的机器或整个集群锁定为仅限已验证(allowlist)、允许列表,或完全关闭。沙箱服务器,阻止高风险的连接,要求签名注册表。所有这些都在一个 [addons] 配置中。
任何插件返回的内容都会被扫描以查找秘密信息,并在模型看到之前标记为不可信。这为数据泄露和提示注入设置了坚固的屏障。
每个注册表条目都在合并时进行审查。固定您的上游,保持连接干净,两个维护者的审计会将您提升到用户可以一目了然信任的已验证级别。
使用 addons.policy、addons.sandbox 和 addons.require_signature 进行锁定——查看 安全模型。
任何人都可以发布。一个插件就是一个 MCP 服务器和一个小的清单文件。
发布一个通过 stdin/stdout 或 HTTP 端点通信 MCP 的小型程序。这就是 lean-ctx 运行或连接的内容。它保持自己的进程,因此没有派生和重新编译。
在 [addon] 中声明元数据以及 lean-ctx 如何在 [mcp] 中启动您的服务器。如果没有 [mcp] 区块,您的条目将被列出;如果包含,则可安装。
运行 lean-ctx addon add ./lean-ctx-addon.toml。这就是完整的安装流程,直接集成到您自己的网关中,无需触碰注册表。
打开一个合并请求,将您的条目添加到精选注册表中。一旦合并,每个人都可以通过一个命令安装它,并且它会出现在这里。
[addon]
name = "my-addon" # slug: [a-z0-9-]
display_name = "My Addon"
description = "What it does, in one line."
author = "you"
homepage = "https://github.com/you/my-addon"
license = "Apache-2.0"
categories = ["workflow"]
[mcp]
transport = "stdio" # or "http"
command = "my-addon-mcp" # stdio: executable to spawn
args = ["serve"] 在注册表中占位并为每个 lean-ctx 用户提供一键安装。
Cookie preferences
We use analytics to understand how our site is used. You choose what's allowed — no tracking runs until you decide.
Essential
Site functionality, security, preferences
Analytics
Pageviews & usage patterns · PostHog EU (Frankfurt) · No cross-site tracking
Read our Privacy Policy for full details. You can change your preferences anytime.