MCP工具
MCP工具 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分，整体质量较高。我们推荐使用将其纳入你的 AI 工具库，帮助提升工作效率。
📚 深度解析
通过安装 MCP工具，你的 AI 助手将获得额外的工具调用能力，可以用自然语言直接操控该工具的功能，无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置，永久增强"——配置完成后，每次与 AI 对话时都可以无缝调用这些工具。
在技术实现上，MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信，工具的功能以"工具列表"的形式暴露给 AI 模型，AI 可以按需调用。MCP工具 提供了结构化的工具调用接口，使 AI 模型能够精确地理解和使用每个功能点，显著降低 AI 在工具使用上的错误率。
与传统的 API 集成相比，MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON，即可让 AI 获得全新能力。AI Skill Hub 将 MCP工具 评为 AI 评分 7.5 分，属于同类工具中的优质选择。
📋 工具概览
MCP工具 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
📖 中文文档
MCP工具 是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。
- 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
- 提供结构化工具调用接口，显著降低 AI 集成复杂度
- 支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
- 可与其他 MCP 工具组合叠加，构建完整 AI 工作站
- 轻量无侵入设计，不影响现有系统架构
- 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
- 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
- 将多个 MCP 工具组合使用，构建个人专属 AI 工作站
# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/sachinshelke/codevira
# 方式二：手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp--": {
"command": "npx",
"args": ["-y", "codevira"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
- 确认已安装 Node.js（v18 或以上版本）
- 打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
- 按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
- 保存配置文件并重启 Claude 客户端
- 重启后，在对话中即可使用本工具
# 安装后在 Claude 对话中直接使用 # 示例： 用户: 请帮我用 MCP工具 执行以下任务... Claude: [自动调用 MCP工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入："列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"mcp__": {
"command": "npx",
"args": ["-y", "codevira"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Codevira
Cross-IDE decision enforcement for AI coding agents. One in-repo memory layer that every AI tool you use can read; PreToolUse hooks that physically block edits violating prior decisions. Local-first, MIT-licensed, ~83 MB pipx install.
Built for solo developers working on local projects with AI agents. Decisions live in <repo>/.codevira/decisions.jsonl — git-committed, team-shareable, visible in git diff. Every modern AI tool reads AGENTS.md, which codevira auto-generates as a slim 5 KB contract. Claude Code gets enforcement: PreToolUse hooks block Edit/Write calls that contradict decisions you marked do_not_revert.
Works with: Claude Code · Claude Desktop · Cursor · Windsurf · Google Antigravity · OpenAI Codex · GitHub Copilot · any MCP-compatible AI tool.
---
What's new in v3.1.1 — hardening + interrogable memory
3.1.1 supersedes the briefly-published 3.1.0 (which shipped without this README/CHANGELOG entry). Same code shape; this release is the documented one. Brings five memory subsystems (M1–M9 from 3.1.0) plus the v3.1.1 hardening + viewer overhaul.
| Area | What you get |
|---|---|
| **Five memory subsystems** | Origin tagging (M1), working memory (M2), skill library with FTS5 ranking (M3), spatial memory + activity heatmap (M4), skill induction wired to outcomes (M5), cross-IDE consensus check + handshake (M6/M7), reflections (M8). 22 new MCP tools. |
| **Secret scrubbing everywhere** | Decisions, sessions, working memory, skills, reflections — every store scrubs api-key / Bearer / password / AWS AKIA / long hex / long base64 at the write boundary. One shared mcp_server/storage/sanitize.py. |
| **Counter-decision discipline** | record_decision now accepts alternatives_considered: list[str] and would_re_examine_if: str — losing options + invalidation trigger surface in the viewer's rich-detail panel. Optional + back-compat. |
| **Interrogable graph viewer** | codevira graph is no longer a passive force-layout. Free-text search → top-K ranked panel with score + outcome badge. Q&A intent detection ("what did we decide about X", "what got reverted", "what's protected"). Outcome lens (kept/modified/reverted). Lineage trace mode for supersession chains. |
| **Auto outcome classification** | codevira sync now runs observe-git as a best-effort tail step — outcomes flow into the viewer's outcome lens automatically. |
| **G3 real-IDE smoke** | The last permanently-skipped gauntlet gate now ships as a real check. Verifies codevira is registered in each detected IDE config + MCP tools/list round-trips in <1s. |
| **AGENTS.md no more churn** | regenerate() is now idempotent — no rewrite when content unchanged, no perpetual uncommitted-drift loop. |
| **4 silent bugs fixed** | commit_session("../escape") rejected; triggers.tags="git" rejected; list_all(limit=0) returns []; spatial BFS catches query-time sqlite errors. |
Full v3.1.1 release notes: CHANGELOG.md.
---
What's new in v3.0.0 — audited, lean, opinionated
Major version. v3.0.0 is the biggest API contraction since v2.0 shipped: 21 MCP tools deleted, 8 CLI subcommands deleted, per-IDE nudge file matrix collapsed to AGENTS.md only, IDE detection hardened from "directory exists" to "binary on PATH + valid config file." Full plan + rationale indocs/audit-2026-05-22.md; per-item kill list indocs/surface-cuts-2026-05-22.md.
| Area | What changed |
|---|---|
| **Decision storage** | Moved into <repo>/.codevira/decisions.jsonl (git-tracked, one decision per line). v2.x stored decisions in ~/.codevira/projects/<key>/graph/graph.db (a SQLite blob nobody could read). |
| **AGENTS.md is the nudge file** | Per-IDE nudges (CLAUDE.md / GEMINI.md / .windsurfrules / .cursor/rules/codevira.mdc / .github/copilot-instructions.md) all deleted. Every modern AI tool reads AGENTS.md natively. Slim 5 KB cap; auto-regenerated from decisions; user content outside the ... markers preserved byte-for-byte. |
| **MCP tool surface** | 46 → 24 tools (-48%; 23 surfaced to AI clients, 1 admin-only). The audit found 22 tools that nobody called in real usage (preferences, learned_rules, changesets, project_maturity, list_nodes / add_node / update_node / export_graph, etc.). All deleted. |
| **CLI surface** | 23 → 15 commands (-35%). Deleted: heal (use reset), budget, agents, hooks, register, configure, report (folded into doctor), calibrate, insights. |
| **IDE detection hardened** | No more false-positives from stale ~/.cursor/ dirs. Each IDE needs a STRONG signal (binary on PATH, or verified config file). Pass --ide X --force to override when the detector misses an install. |
**codevira uninstall** | New command. Reverses every system write made by init/setup: drops the MCP entry from ~/.claude.json, deletes ~/.claude/hooks/codevira-*.sh, strips codevira-tagged registrations from ~/.claude/settings.json, removes per-project .codevira/ + .codevira-cache/, strips the codevira block from AGENTS.md. Optional --keep-data. |
| **Install size** | ~83 MB pipx venv (was ~450 MB in v2.1.2 with ChromaDB + sentence-transformers + torch). MCP server starts in <100 ms (was 1-3 s). |
Full v3.0.0 release notes: CHANGELOG.md.
Upgrading from v2.x? See the Migration notes section.
---
1. Install
pipx install codevira
What `codevira setup` actually does
The one command above replaces what used to take 5+ steps in v1.x:
Detects installed AI tools via STRONG signals: - Claude Code: claude on PATH - Claude Desktop: ~/Library/Application Support/Claude/config.json exists + parses - Cursor: ~/.cursor/ + (cursor on PATH OR mcp.json exists) - Windsurf: mcp_config.json in ~/.windsurf/ or ~/.codeium/windsurf/ - Antigravity: ~/.gemini/antigravity/mcp_config.json Injects MCP server config into each detected tool's config file (per-IDE schema handled automatically; no JSON to hand-edit). Installs Claude Code lifecycle hooks (SessionStart, PreToolUse, PostToolUse, UserPromptSubmit, Stop) — these are what turn codevira from passive memory into the active guardian that blocks edits violating do_not_revert decisions. Writes AGENTS.md with the slim codevira-managed block (5 KB cap; preserves user content outside the marker boundaries).
Flags:
- --dry-run — preview without writing - --ide <name> — narrow to one IDE (claude, claude_desktop, cursor, windsurf, antigravity, agents_md) - --force — configure an --ide value even if codevira didn't auto-detect it (escape hatch for portable binaries / unusual config locations) - -y / --yes — skip the confirmation prompt - --no-hooks / --no-mcp / --no-nudge-files — scope-narrow the steps
Uninstall
```bash
Reverse every system write made by init/setup. Preserves user content
Quick Start — three commands
```bash
MCP Workflow Prompts
| Prompt | Description |
|---|---|
onboard_session | Full project context catch-up for new sessions. Wraps get_session_context(). |
v3.0.0 removed 4 v2.x prompts (review_changes,debug_issue,pre_commit_check,architecture_overview) because they referenced deleted MCP tools. The slim surface means the AI can synthesize these workflows from the 25 kept tools directly.
---
Production-stable vs known-limited
| Production-stable | Known-limited |
|---|---|
| Cross-IDE decision memory via in-repo JSONL | The PreToolUse hook enforcement is Claude Code only today. Other IDEs read AGENTS.md (soft signal), but don't have hard blocks |
do_not_revert enforcement at Claude Code PreToolUse | Multi-language code graph for languages outside Python / TS / JS / Go / Rust — use the [all-languages] extra |
| FTS5 decision search with BM25 ranking | Real-time multi-machine sync — by design, codevira is local-first; for team sharing, commit .codevira/ to git |
Per-project + cross-machine project inventory (global.db) | Web UI for browsing decisions — use the codevira://decisions MCP resource in Claude Desktop, or codevira replay --format html for a static file |
| All 24 MCP tools (23 AI-facing + 1 admin) + 15 CLI commands + 6 engine policies | The HTTP server (codevira serve) is single-project per launch — for daily use, stick with stdio via codevira setup |
Concurrent-safe storage layer (Posix fcntl.flock + Windows sentinel fallback). Proven against 50-thread + 20-subprocess stress + 29-attack chaos harness | The cross-process file-lock contract has been exercised on macOS + Linux CI; the Windows sentinel-file fallback is verified via unit-test simulation but hasn't been load-tested on real Windows yet |
Code graph data store is functional but the v3.0.0 spec target (<project>/.codevira-cache/graph.sqlite) and the actual location (<data_dir>/graph/graph.db) drifted during the surface-cut audit. Tracked for v3.1 reconciliation | n/a (functional today; spec-truthfulness gap only) |
---
FAQ
Common questions about setup, usage, architecture, and troubleshooting — see FAQ.md.
高质量的MCP工具，实现AI代理会话记忆
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- Python 依赖冲突：建议用 venv / uv 隔离环境
- CLI：直接 npm install -g / pip install，命令行调用
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
- 提供结构化工具调用接口，显著降低 AI 集成复杂度
- 支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
- 可与其他 MCP 工具组合叠加，构建完整 AI 工作站
- 轻量无侵入设计，不影响现有系统架构
- 需要让 Claude / Cursor 操作本地工具的 AI 工程师
- 构建多智能体协作系统的 Agent 开发者
- 配置 MCP 服务器时建议使用 stdio 传输 + JSON-RPC，避免暴露公网
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- MCP 配置路径拼错或权限不足，重启 Claude Desktop 才生效
- Python 依赖冲突：建议用 venv / uv 隔离环境
👥 适合人群
🎯 使用场景
- 在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
- 通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
- 将多个 MCP 工具组合使用，构建个人专属 AI 工作站
⚖️ 优点与不足
- +MIT 协议，可免费商用
- +标准化 MCP 协议，生态互联性强
- +与 Claude 官方生态无缝对接
- +即插即用，配置简单快捷
- −依赖 Claude 客户端，非 Claude 用户无法使用
- −MCP 协议仍在持续演进，接口可能变更
- −需要一定的配置步骤
AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一，可自由商用、修改、分发，仅需保留版权声明。
❓ 常见问题 FAQ
经综合评估，MCP工具 在MCP工具赛道中表现稳健，质量良好。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | codevira |
| 原始描述 | 开源MCP工具：Stop re-explaining your project to AI agents every session. One memory layer for。⭐10 · Python |
| Topics | ai-agentsmcppython |
| GitHub | https://github.com/sachinshelke/codevira |
| License | MIT |
| 语言 | Python |
收录时间：2026-06-01 · 更新时间：2026-06-01 · License：MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。