@friday-ai-codes/mcp
Click on "Install 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., "@@friday-ai-codes/mcpsearch for code related to error handling and create a coding plan"
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.
@friday-ai-codes/mcp
Friday AI 的 MCP(Model Context Protocol)server。把 Friday 的代码索引、Graph RAG、编码计划与 PR / MR 工具暴露给 Cursor / Claude Code / Codex 等 AI 编码助手。
配置(一条命令)
在 Friday Web 控制台「个人资料 → 访问令牌」创建 PAT(明文只显示一次),然后:
npx -y @friday-ai-codes/mcp setup交互式中文向导一条龙:凭证问答 → 自动注册进本机 agent → 连通性测速(延迟 ms 高亮)→ 能力演示(随机介绍一个已索引仓库)。
脚本 / CI 场景用命令式 init:
npx -y @friday-ai-codes/mcp init --base-url https://friday.example.com --token <你的访问令牌>配置写入 ~/.friday/config.json(权限 0600)。也可以用环境变量 FRIDAY_BASE_URL / FRIDAY_ACCESS_TOKEN 覆盖。
Related MCP server: codesight
注册到 IDE
一条命令,自动探测已安装的 agent 并幂等注册:
npx -y @friday-ai-codes/mcp registerCursor:写入
~/.cursor/mcp.json(--project时写./.cursor/mcp.json)Claude Code:执行
claude mcp add friday -- npx -y @friday-ai-codes/mcpCodex:追加
[mcp_servers.friday]到~/.codex/config.toml
只新增 friday 条目,不覆盖既有配置;已注册则跳过。用 --agent cursor|claude-code|codex(可重复)指定目标,--all 注册全部。
命令
命令 | 作用 |
| 启动 stdio MCP server |
| 交互式中文向导:凭证 → 注册 → 测速 → 能力演示 |
| 写入配置(带 |
| 把 friday MCP server 注册进 agent 配置(幂等) |
| 检查配置、注册状态与连通性测速(不回显令牌) |
工具集
23 个工具,对应 Friday /api/mcp/tools/* 端点:仓库发现(route_repositories)、Graph RAG 检索(search_rag_chunks、find_related_chunks)、精确文本检索(grep_repository)、仓库浏览(get_repository / list_repository_files / get_repository_file)、分析与计划(analyze_repository / create_coding_plan / improve_coding_plan)、执行与 MR(execute_coding_plan / get_coding_execution / summarize_branch / create_merge_request)、飞书工作项(get_feishu_work_item_context / create_feishu_technical_plan / create_work_item_repo_tasks / execute_work_item_repo_tasks)、学习案例(create_learning_case / search_learning_cases)、交付知识图谱(search_delivery_knowledge / get_entity_timeline / get_related_entities)。
每个工具都带 MCP 标准 annotations(中文 title 按「阶段 · 动作」分组 + readOnlyHint / idempotentHint / openWorldHint 行为提示)。
配合 Friday AI skills(4 个技能:friday / friday-code / friday-feishu / friday-memory)使用效果最佳,一键全装:
npx @friday-ai-codes/skillsLicense
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceEnables AI agents to search code by meaning, explore codebase structure, store and query knowledge with temporal facts, and read source code through a set of MCP tools.4536MIT
- Alicense-qualityAmaintenanceProvides 13 MCP tools for codebase analysis, wiki generation, and knowledge mapping, enabling AI assistants to understand project structure and context efficiently.9421,343MIT
- Alicense-qualityCmaintenanceEnables AI coding agents to retrieve and manage code context with hybrid search, project memory, and observability via MCP tools.29MIT
- Alicense-qualityAmaintenanceProvides code intelligence for AI coding agents by indexing repositories into a hybrid knowledge graph, enabling agents to query dependencies, impact, and context through 28 MCP tools.2Apache 2.0
Related MCP Connectors
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
AI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/friday-ai-codes/mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server