cocoindex-claude MCP — 使用场景, 安装 & 实时演示

为什么要用

核心特性

Drop-in knowledge of CocoIndex flow definitions, sources, and sinks
Guidance on writing custom transformation functions correctly
Claude picks the right CLI vs programmatic API based on task
Understands incremental processing semantics so it doesn't suggest full rebuilds
Official — authored by the CocoIndex team

实时演示

实际使用效果

cocoindex-claude-skill.replay ▶ 就绪

0/0

安装

选择你的客户端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "cocoindex-claude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ],
      "_inferred": true
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "cocoindex-claude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "cocoindex-claude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ],
      "_inferred": true
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "cocoindex-claude-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ],
      "_inferred": true
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "cocoindex-claude-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/cocoindex-io/cocoindex-claude",
        "~/.claude/skills/cocoindex-claude"
      ]
    }
  ]
}

Continue 使用服务器对象数组，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "cocoindex-claude-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/cocoindex-io/cocoindex-claude",
          "~/.claude/skills/cocoindex-claude"
        ]
      }
    }
  }
}

加入 context_servers。Zed 保存后热重载。

claude mcp add cocoindex-claude-skill -- git clone https://github.com/cocoindex-io/cocoindex-claude ~/.claude/skills/cocoindex-claude

一行命令搞定。用 claude mcp list 验证，claude mcp remove 卸载。

使用场景

实战用法： cocoindex-claude

Build your first CocoIndex pipeline from a local folder into a vector DB

👤 Developers evaluating CocoIndex for a RAG use case ⏱ ~30 min intermediate

何时使用： You've read the CocoIndex homepage and want Claude to scaffold a working flow instead of copy-pasting tutorials.

前置条件

Skill cloned to ~/.claude/skills/cocoindex-claude — git clone https://github.com/cocoindex-io/cocoindex-claude ~/.claude/skills/cocoindex-claude
cocoindex Python package installed — pip install cocoindex

步骤

Describe the pipeline

Use the cocoindex skill — scaffold a flow that watches ./docs, chunks markdown, embeds with OpenAI, writes to Qdrant.✓ 已复制

→ Claude generates a flow.py with @cocoindex.flow_def and the right source/transform/export calls
Run and verify

Now show me the exact CLI commands to build, run, and incrementally update this flow.✓ 已复制

→ cocoindex setup / update / eval commands in the correct order

结果： A working flow.py plus the commands to run it — no more guessing at the CocoIndex decorator surface.

注意事项

Claude invents APIs that don't exist in CocoIndex — Explicitly prompt 'use only APIs documented in the cocoindex skill' — hallucination drops when the skill is in scope

搭配使用： filesystem

Write a custom CocoIndex transform function

👤 Engineers extending an existing CocoIndex flow ⏱ ~25 min intermediate

何时使用： Built-in transforms don't cover your parsing / enrichment step.

步骤

Describe the transform

With the cocoindex skill — write a @cocoindex.op.function that takes a PDF path, extracts tables, returns structured rows.✓ 已复制

→ Idiomatic function signature with correct typed inputs/outputs
Wire it into the flow

Now plug this into my existing flow at the chunking stage.✓ 已复制

→ Diff against current flow.py with the new op in place

结果： A custom transform that obeys CocoIndex's incremental semantics.

注意事项

Function returns non-deterministic output, breaking incremental processing — Skill reminds Claude that transforms must be pure — if you hit this, re-read the incremental section

组合

与其他 MCP 搭配，撬动十倍杠杆

cocoindex-claude-skill + filesystem

Let Claude actually write the flow.py file to disk, not just print it in chat

Scaffold the CocoIndex flow and save it to ./pipelines/docs_to_qdrant.py.✓ 已复制

cocoindex-claude-skill + postgres

Pipe CocoIndex output into a Postgres vector store and query it from the same session

Build the flow targeting pgvector, then run a retrieval query against it.✓ 已复制

工具

此 MCP 暴露的能力

工具	输入参数	何时调用
scaffold_flow	source type + sink type + transform steps	Starting a new pipeline
write_custom_op	function intent + input/output types	Built-in transforms aren't enough
cli_guidance	task (setup / update / eval / drop)	You're unsure whether to rebuild or incrementally update

成本与限制

运行它的成本

API 配额: None
每次调用 Token 数: Modest — skill loads reference material only when relevant
费用: Free — skills are local files
提示: CocoIndex itself is free; costs come from your embedding model and vector DB, not this skill.

安全

权限、密钥、影响范围

凭据存储： No credentials — pure prompts

数据出站： None from the skill itself. Your pipeline calls whichever embedding / DB services you configure.

故障排查

常见错误与修复

Skill not invoked when you ask about CocoIndex

Say 'use the cocoindex skill' explicitly, or check it's installed at ~/.claude/skills/cocoindex-claude.

验证： ls ~/.claude/skills/cocoindex-claude/SKILL.md

SKILL.md frontmatter wrong

Open the file and verify name / description are populated. Re-clone if partial.

验证： head ~/.claude/skills/cocoindex-claude/SKILL.md

Wrong trigger keywords — Claude writes generic Python instead of CocoIndex

Mention CocoIndex explicitly, or say 'scaffold a cocoindex flow_def'.

替代方案

cocoindex-claude 对比其他方案

替代方案	何时用它替代	权衡
LlamaIndex skills	You want LlamaIndex's retrieval abstractions instead of CocoIndex's transform-centric model	Different mental model — LlamaIndex is retrieval-first, CocoIndex is pipeline-first
Hand-written Python	You need one-off processing and don't want incremental state	No incremental rebuilds, no framework conventions

cocoindex-claude

为什么要用

核心特性

实时演示

实际使用效果

安装

选择你的客户端

使用场景

实战用法： cocoindex-claude

Build your first CocoIndex pipeline from a local folder into a vector DB

前置条件

步骤

注意事项

Write a custom CocoIndex transform function

步骤

注意事项

组合

与其他 MCP 搭配，撬动十倍杠杆

工具

此 MCP 暴露的能力

成本与限制

运行它的成本

安全

权限、密钥、影响范围

故障排查

常见错误与修复

替代方案

cocoindex-claude 对比其他方案

更多

资源