Local Knowledge MCP
A security-first, read-only MCP server that lets clients browse and read text, PDF, and XLSX files from an explicit allowlist of local folders, with strict path and secret protections.
README
Local Knowledge MCP
A security-first, read-only Model Context Protocol (MCP) server for local folders.
Local Knowledge MCP lets an MCP client browse an explicit root allowlist, inspect metadata, read bounded text, and receive supported images and documents as MCP content. It is intentionally not a general-purpose filesystem write server.
Features
- Read-only by design and default-deny.
- Client paths use
root_alias + relative path; clients never send local absolute paths. - Blocks unknown roots, parent traversal, symlink escape, hidden paths, and common secret-bearing files.
- Atomically updates the persistent root configuration.
- Reloads the security policy on every tool call, so
lk-add,lk-remove, andlk-cleartake effect without a project-specific runtime manager. - Ships as a normal Python package with portable console commands.
- Provides guided ChatGPT setup through OpenAI Secure MCP Tunnel without bundling shared tunnel identities or credentials.
Requirements
- Python 3.11 or newer.
uvis recommended;pipxalso works.- For local stdio usage: an MCP client that can launch a local process.
- For ChatGPT usage: OpenAI tunnel permissions and ChatGPT developer-mode access.
lk-chatgpt-setupguides this optional flow.
Install
Directly from GitHub
With uv:
uv tool install "git+https://github.com/TuanLe-bk18/local-knowledge-mcp.git"
Or with pipx:
pipx install "git+https://github.com/TuanLe-bk18/local-knowledge-mcp.git"
From a clone
git clone https://github.com/TuanLe-bk18/local-knowledge-mcp.git
cd local-knowledge-mcp
uv tool install .
The installation provides:
local-knowledge-mcp
lk-init
lk-set
lk-add
lk-list
lk-remove
lk-clear
lk-chatgpt-setup
Update
If installed directly from GitHub with uv, refresh and reinstall the tool from the latest commit:
uv tool upgrade local-knowledge-mcp --reinstall
If installed with pipx:
pipx install --force "git+https://github.com/TuanLe-bk18/local-knowledge-mcp.git@main"
For an installation made from a local clone:
git pull --ff-only origin main
uv tool install --force --reinstall .
Restart or reconnect local MCP clients after upgrading. For a managed ChatGPT tunnel runtime, recreate it with the updated executable:
lk-chatgpt-setup --no-browser
The existing root configuration, tunnel ID, and runtime key file are reused.
Quick start
Initialize a secure empty configuration:
lk-init
Add one or more allowed folders:
lk-add project "~/Code/my-project"
lk-add notes "~/Documents/notes"
lk-list
Connect a local stdio MCP client
lk-init prints an MCP client configuration using the installed executable. A typical configuration is:
{
"mcpServers": {
"local-knowledge": {
"command": "local-knowledge-mcp"
}
}
}
Some desktop applications do not inherit your shell PATH. In that case, use the absolute command path printed by lk-init.
Restart or reconnect the MCP client after first adding the server. Root allowlist changes made while the server is running are loaded automatically on the next tool call.
See docs/client-setup.md for local stdio setup details and troubleshooting.
Connect ChatGPT with Secure MCP Tunnel
After configuring at least one root, run:
lk-chatgpt-setup
The command:
- discovers
tunnel-client, or offers to download the latest officialopenai/tunnel-clientrelease; - verifies the downloaded archive against the official
SHA256SUMS.txtasset; - opens OpenAI Platform tunnel and runtime-key setup pages;
- asks for the user's own
tunnel_idand hidden runtime API key; - stores the runtime key outside the repository in a user-private
0600file; - starts a managed tunnel runtime and waits until it reports
ready; - opens ChatGPT connector settings and prints the tunnel ID to select or paste.
The runtime key must have Tunnels Read + Use. An admin key is not accepted, stored, or passed to the long-lived runtime. Tunnel creation remains in the authenticated OpenAI Platform UI, so every installation uses the user's own tunnel identity and permissions.
See docs/chatgpt-setup.md for prerequisites, non-interactive options, credential storage, and troubleshooting.
Root commands
Replace every configured root with one workspace root:
lk-set "/path/to/folder"
Add or update an alias while preserving other roots:
lk-add project "/path/to/project"
List roots without touching the MCP process:
lk-list
Remove one alias:
lk-remove project
Remove all roots while keeping read-only/default-deny policy enabled:
lk-clear
Folder inputs are expanded, required to exist, required to be directories, and saved as canonical absolute paths. Aliases must begin with a lowercase letter and may contain lowercase letters, numbers, hyphens, and underscores.
The persistent configuration is stored outside the repository at:
~/.config/local-knowledge-mcp/security.yaml
No personal root configuration is bundled in the package.
MCP tools
browse(root_alias, path="")
get_info(root_alias, path)
read_text(root_alias, path, max_chars=None)
read_document_resource(root_alias, path)
read_file_resource(root_alias, path)
Example tool arguments:
{
"root_alias": "project",
"path": "docs/architecture.md"
}
read_file_resource returns PNG, JPEG, and GIF files as concise text metadata plus MCP ImageContent, with structured output disabled so clients can pass them to a model's image input without duplicating base64 as text. It returns allowed PDF, DOCX, PPTX, XLSX, and XLS files as EmbeddedResource values. It does not parse, OCR, index, or modify files. The existing read_document_resource tool remains available for PDF/XLSX compatibility.
Security model
Every filesystem access reaches SecurityPolicy.resolve() before touching a client-selected path. The default generated policy enforces:
mode:
read_only: true
default_deny: true
path_policy:
allow_absolute_paths_from_client: false
allow_parent_traversal: false
allow_symlinks: false
allow_hidden_files: false
Additional deny patterns block common credential, token, key, environment, build, and VCS paths. Direct text reads are UTF-8 only, extension-limited, binary-checked, file-size limited, and character-limited.
An empty root mapping is valid and denies every root alias. See SECURITY.md before changing policy defaults.
Scope
Included:
- directory browsing;
- file/directory metadata;
- bounded text/source reading;
- PNG/JPEG/GIF image content and PDF/DOCX/PPTX/XLSX/XLS embedded resources;
- local root allowlist management.
Not included:
- write, edit, delete, move, or create operations;
- arbitrary absolute-path access;
- OCR or document parsing;
- embeddings, vector databases, or RAG;
- a shared hosted tunnel, shared runtime credential, or shared cloud runtime.
For ChatGPT, lk-chatgpt-setup configures the official outbound Secure MCP Tunnel client on the user's machine. This repository never bundles tunnel credentials, identifiers, API keys, or machine-specific runtime state.
Development
git clone https://github.com/TuanLe-bk18/local-knowledge-mcp.git
cd local-knowledge-mcp
uv sync --all-groups
uv run pytest -q
uv build
See CONTRIBUTING.md for contribution guidelines.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。