Weline MCP
Provides project intelligence and learning capabilities for OpenAI's Codex CLI, enabling batch editing, persistent indexing, and evidence-based skill generation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Weline MCPbatch edit the authentication flow and auto-learn skills"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Weline Project Intelligence MCP 0.13.0
这是 Weline_Ai 内置、依赖无关的本地项目智能 MCP。它以 PHP 8.2+ 和 SQLite 运行,通过 STDIO 同时服务 Codex、Cursor 及其他遵守 readiness 协议的 AI 客户端;不依赖 WLS、Weline DI、业务数据库或网络服务。
唯一知识模型
长期知识只来自
app/code/Weline/Ai/doc/、app/code/Weline/Framework/doc/与app/code/*/*/doc/。每个知识单元必须包含
doc/README.md、doc/需求.md、doc/开发日志.md;专题文档按需增加。派生文件清单、全文内容、符号、关系和 Hash 只存于项目隔离的 SQLite。
仓库技能投影已退役。
resolve_skill、get_skill只是resolve_task_context的动态兼容别名。
Related MCP server: Portable MCP Toolkit
强制调用顺序
客户端启动
bin/learning-mcp。以仓库根目录和唯一
client_session_id调用prepare_project。只有
project-readiness.v1.status=ready才能继续。needs_repair只返回确定性、create-only 的修复 Bundle;用户明确授权后调用repair_project_docs。开发前调用
resolve_task_context,后续受保护工具都携带同一会话的readiness_id。临时用户决定写入
set_session_directives,仅在当前 MCP 进程内存中生效。
readiness 绑定项目身份、Git revision、模块清单、必需文档 Hash 和客户端会话。外部编辑会在下一次受保护调用前触发 freshness 检查;失效 readiness 必须重新准备。
入口与工具
php bin/learningctl doctor
php bin/learning-mcp
php tests/run.php --quick
php tests/project-readiness.php核心公共工具:
prepare_project/repair_project_docsset_session_directivesresolve_task_contextresolve_deploy_plan(只读调用Weline_Deploy公开 CLI)search_project_knowledge/get_indexed_documentget_edit_bundle/apply_compact_editget_edit_status/rollback_editresolve_skill/get_skill(动态兼容别名)
详细契约见 PROJECT-INTELLIGENCE.md,部署与维护见 OPERATIONS.md,安全边界见 SECURITY.md。
维护关系
app/code/Weline/Ai/Mcp 是 0.13.0 起的唯一代码源。独立发行仓只由本目录生成一致快照,并在 0.13.0 后冻结维护。子目录继续使用 Apache-2.0 许可。
This server cannot be deployed
Maintenance
Related MCP Connectors
Project memory, semantic code search, and grounded agent context.
AI-powered spec-to-task decomposition and execution orchestration for coding agents.
Context engineering for AI coding agents: product context, project missions, and 360 memory.
Codebase intelligence for agents: 152 structured artifacts across 21 programs, one call.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceImplements Agentic Context Engineering to create self-improving AI coding assistants that learn from execution feedback and build persistent knowledge playbooks. Reduces token usage by 86.9% while improving code accuracy by 10.6% through incremental context updates.4MIT
- AlicenseNot gradedqualityCmaintenanceProvides AI-powered code intelligence for any codebase using local LLMs and vector search, enabling semantic code search, pattern analysis, and context-optimized code generation with 90% token savings.2MIT
- FlicenseBqualityDmaintenanceConnects AI assistants to a local Codex engine for performing deep, project-level code reviews and automated refactoring. It enables context-aware bug fixes and multi-file analysis through a standardized bridge between modern AI clients and local development environments.42-
- AlicenseNot gradedqualityBmaintenanceReduces token consumption for AI coding agents by 50-70% through intelligent code context filtering, Git delta tracking, and local SQLite/Tree-sitter indexing.167 npmMIT