{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_4p7mxtagt9k6","handle":"ctx-engine-mcp","url":"https://wellknown.network/agents/ctx-engine-mcp","links":{"self":"https://wellknown.network/agents/ctx-engine-mcp/record.json","html":"https://wellknown.network/agents/ctx-engine-mcp","markdown":"https://wellknown.network/agents/ctx-engine-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ctx-engine-mcp","status":"https://wellknown.network/api/v1/agents/ctx-engine-mcp/status","claim":"https://wellknown.network/agents/ctx-engine-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ctx-engine-mcp/claim.json","badge":"https://wellknown.network/agents/ctx-engine-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/ctx-engine-mcp/history","tools":"https://wellknown.network/api/v1/agents/ctx-engine-mcp/tools"},"ard":{"identifier":"urn:air::server:ctx-engine-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ctx-engine-mcp","summary":"A Model Context Protocol (MCP) server for Context Engineering - file system as external memory for AI agents","description":"# Context Engineering MCP Server\n\n这是一个符合 **Model Context Protocol (MCP)** 标准的服务器，旨在为 Claude Desktop、Cursor 或其他 AI 助手提供\"外部记忆\"和\"上下文管理\"能力。\n\n它实现了 [Context Engineering](./ai-programming-best-practices.md) 的核心理念，允许 AI 像操作系统一样管理自己的工作区状态。\n\n## ✨ 功能\n\n这个插件为你的 AI 助手添加了以下能力（Tools）：\n\n1.  **`context_init`**: 初始化 `.ai/skills` 和 `.agent_memory` 目录结构。\n2.  **`context_state`**: 获取当前工作区的\"快照\"（包含目录树、Git状态、当前目标）。\n3.  **`context_save_observation`**: 将长输出（如日志、API响应）保存到文件，只返回摘要。\n4.  **`context_read_observation`**: 按需读取之前保存的观察结果。\n\n## 📦 安装与配置\n\n### 1. 作为 Python 包安装\n\n```bash\n# 从 PyPI 安装\npip install ctx-engine-mcp\n```\n\n### 2. 配置 Claude Desktop\n\n编辑你的 Claude Desktop 配置文件（通常位于 `~/Library/Application Support/Claude/claude_desktop_config.json`）：\n\n```json\n{\n  \"mcpServers\": {\n    \"context-engineering\": {\n      \"command\": \"uv\",\n      \"args\": [\n        \"tool\",\n        \"run\",\n        \"--from\",\n        \"ctx-engine-mcp\",\n        \"context-mcp\"\n      ]\n    }\n  }\n}\n```\n\n或者使用系统 Python：\n\n```json\n{\n  \"mcpServers\": {\n    \"context-engineering\": {\n      \"command\": \"python3\",\n      \"args\": [\"-m\", \"context_mcp.server\"]\n    }\n  }\n}\n```\n\n### 3. 配置 Cursor (即将支持)\n\nCursor 目前正在积极集成 MCP，配置方式与 Claude Desktop 类似。\n\n## 🛠️ 使用示例\n\n一旦配置完成，你可以在对话中直接告诉 Claude：\n\n> \"初始化一下上下文环境\" -> Claude 会调用 `context_init`\n\n> \"现在的项目状态是什么？\" -> Claude 会调用 `context_state`\n\n> \"运行 npm install 并帮我分析错误，输出可能很长，请注意使用外部记忆\" -> Claude 会运行命令并使用 `context_save_observation` 保存结果。","publisher":{"name":"Context Engineering Contributors","url":null},"homepage":"https://github.com/slicenferqin/ctx-mcp","repository":"https://github.com/slicenferqin/ctx-mcp","version":"0.1.1","license":"MIT","protocols":["mcp"],"tags":["agent","ai","claude","context-engineering","llm","mcp"],"pricing":null,"endpoints":[{"url":"pypi:ctx-engine-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.722,"provenance":"derived"}],"categories":["dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"ctx-engine-mcp","registry":"pypi","observedAt":"2026-11-09T02:26:07.760Z","publishedAt":"2026-01-22T01:56:44.635348Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ctx-engine-mcp","url":"https://pypi.org/project/ctx-engine-mcp/","firstSeenAt":"2026-09-09T13:21:01.792Z","fetchedAt":"2026-11-09T02:25:16.696Z","normalizedAt":"2026-11-09T02:25:16.696Z"}]},"firstSeenAt":"2026-09-09T13:21:01.792Z","updatedAt":"2026-11-09T02:26:07.760Z"}