Skip to main content

canpoint-knowledge-mcp

面向业务项目的知识库 MCP。安装后,AI 助手可以直接检索和阅读你项目的知识库 文档:查大纲、混合检索、读全文与章节、沿文档引用关系跳转;项目发布后, 还能一键把最新的 docs/ 同步进知识库。

能做什么

查询 MCP(只读,绑定一个项目):

工具 能力
get_outline 查看项目知识库的文档大纲(可按版本/分组过滤)
search 在项目范围内混合检索,命中结果带标题路径、父章节与行号
get_document 按文档路径读取全文
get_section 读取章节块及其父块、子块
hop 沿文档之间的引用边跳转相邻内容

同步 MCP(发布后更新知识库):

工具 能力
sync_now(project_root) 把业务项目 docs/ 下的最新文档提交到知识库,返回受理任务号;project_root 传业务项目的绝对根目录
sync_status(job_id) 查询同步任务进度,done / failed 为终态

怎么用

前提:

  • 一个可访问的 KB2 知识库服务(通常由团队统一部署,向管理员要地址)
  • 通过 npm 使用时需要先安装 uv

启动前设置两个环境变量,把 MCP 绑定到服务和项目:

KB_SERVER_URL=http://your-kb-service:8001
KB_PROJECT_KEY=your-project

Claude Code 配置示例(.mcp.json):

{
  "mcpServers": {
    "kb2-query": {
      "command": "npx",
      "args": ["-y", "canpoint-knowledge-mcp"],
      "env": {
        "KB_SERVER_URL": "http://your-kb-service:8001",
        "KB_PROJECT_KEY": "your-project"
      }
    },
    "kb2-sync": {
      "command": "npx",
      "args": ["-y", "--package", "canpoint-knowledge-mcp", "kb2-sync-mcp"],
      "env": {
        "KB_SERVER_URL": "http://your-kb-service:8001",
        "KB_PROJECT_KEY": "your-project"
      }
    }
  }
}

也可以用 Python 方式安装运行:

pip install canpoint-knowledge-mcp   # 提供 kb2-query-mcp / kb2-sync-mcp 命令
uvx canpoint-knowledge-mcp            # 免安装直接运行查询 MCP

Codex 配置示例(~/.codex/config.toml):

[mcp_servers.kb2-query]
type = "stdio"
command = "npx"
args = ["-y", "canpoint-knowledge-mcp"]

[mcp_servers.kb2-query.env]
KB_SERVER_URL = "http://your-kb-service:8001"
KB_PROJECT_KEY = "your-project"

[mcp_servers.kb2-sync]
type = "stdio"
command = "npx"
args = ["-y", "--package", "canpoint-knowledge-mcp", "kb2-sync-mcp"]

[mcp_servers.kb2-sync.env]
KB_SERVER_URL = "http://your-kb-service:8001"
KB_PROJECT_KEY = "your-project"

Windows 下若 npx 启动失败,可把 command 改为 cmd、args 改为 ["/c", "npx", "-y", "canpoint-knowledge-mcp"](env 表不变)。

推荐的发布规则(写入业务项目的 AGENTS.md):

发布成功后调用同步 MCP 的 sync_now(project_root="<当前项目绝对根目录>");
取得并汇报已受理的 job_id 后继续发布流程;除非知识库索引完成是发布门禁,
否则不要等待或轮询 sync_status。

项目

Metadata

Release files for canpoint-knowledge-mcp 0.1.9

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for canpoint-knowledge-mcp 0.1.9
File Size Uploaded Provenance Actions
canpoint_knowledge_mcp-0.1.9.tar.gz 81.6 kB Without provenance Details for canpoint_knowledge_mcp-0.1.9.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for canpoint-knowledge-mcp 0.1.9
File Interpreter ABI Platform Actions
canpoint_knowledge_mcp-0.1.9-py3-none-any.whl Python 3 none any Details for canpoint_knowledge_mcp-0.1.9-py3-none-any.whl

Total release size: 117.3 kB

Release files / canpoint_knowledge_mcp-0.1.9.tar.gz

Download URL canpoint_knowledge_mcp-0.1.9.tar.gz
Size 81.6 kB
Tags Source
SHA-256 checksum
How to use checksums
07346c442768d4a5ec249cac6c964e8184ff0eaa3a60ab33615fad4d08a9ab64
BLAKE2b-256 checksum
How to use checksums
5549f3d22c9a3fa41fe3514ff731c7d4dc625e823072f769bb25cfc9de0bc3b1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.32 {"installer":{"name":"uv","version":"0.11.32","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / canpoint_knowledge_mcp-0.1.9-py3-none-any.whl

Download URL canpoint_knowledge_mcp-0.1.9-py3-none-any.whl
Size 35.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9c36b3c534c800708a383e6746d01bc96c73586f0ca9da48e71afef6ea88b650
BLAKE2b-256 checksum
How to use checksums
025a4e1c9fb2d0239230c84f21a7cdc9fe7919b509bf41b0ac4237f7588f5d42
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.32 {"installer":{"name":"uv","version":"0.11.32","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":null,"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Security for canpoint-knowledge-mcp 0.1.9

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page