Enables AI clients to perform private, local semantic and keyword searches over user-selected files with automatic secret redaction.
Also known as ankitb073/lanternkb
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- 167
- Latest version
- 0.1.3
- Last commit
- Oct 13, 2026
- License
- Apache-2.0
What is lanternkb MCP?
lanternkb enables AI clients to perform private, local semantic and keyword searches over user-selected files with automatic secret redaction.
Summary generated from the project's README
About lanternkb MCP server
lanternkb provides a way for developers to perform private, local semantic and keyword searches across specific folders on their machines. It functions as a local MCP server that works with Claude Code, Cursor, VS Code, and other compatible clients. Users install it via uv on macOS 14 or later or Linux, and must run a setup process to select folders and define which data is accessible to cloud-based assistants.
The system prioritizes privacy by redacting detected secrets before indexing and using sandboxed worker processes like sandbox-exec or Landlock. It supports various file formats including code, PDFs, Word documents, and web pages. While it offers an open tier for cloud assistants, it also allows for local-only folders that never leave the machine. The server runs without a daemon or open ports, ensuring that no telemetry is sent and nothing travels over the network except for chosen model downloads.
What you can do with it
- 1Semantic file retrievalAsk an AI assistant to find specific information within your documents using natural language queries.
- 2Filtered content searchingSearch for specific document types or files modified within a certain timeframe.
- 3Secure local indexingMaintain a searchable knowledge base that automatically redacts sensitive credentials to prevent them from reaching the cloud.
- 4Recent file trackingQuickly identify which files in your indexed folders have been updated recently.
Written from the project's README. Every use case is checked against a quote from it.
How to install lanternkb MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall lanternkb MCP in Claude Code
$ claude mcp add lanternkb -- uvx lanternkbInstall lanternkb MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"lanternkb": {
"command": "uvx",
"args": [
"lanternkb"
]
}
}
}Install lanternkb MCP in VS Code
.vscode/mcp.json
{
"servers": {
"lanternkb": {
"type": "stdio",
"command": "uvx",
"args": [
"lanternkb"
]
}
}
}Install lanternkb MCP in VS Code CLI
$ code --add-mcp '{"name":"lanternkb","type":"stdio","command":"uvx","args":["lanternkb"]}'Install lanternkb MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"lanternkb": {
"command": "uvx",
"args": [
"lanternkb"
]
}
}
}Install lanternkb MCP in Codex
$ codex mcp add lanternkb -- uvx lanternkbInstall lanternkb MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.lanternkb] command = "uvx" args = ["lanternkb"]
Install lanternkb MCP in Gemini CLI
$ gemini mcp add -s user lanternkb uvx -- lanternkbInstall lanternkb MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"lanternkb": {
"command": "uvx",
"args": [
"lanternkb"
]
}
}
}Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableankitb073/lanternkb is public and reachablegithub.com/ankitb073/lanternkb ↗Pass
- Package names this repository as its sourcelanternkb names ankitb073/lanternkb as sourcepypi.org/project/lanternkb/ ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for lanternkbpypi.org/project/lanternkb/ ↗Pass
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-13github.com/ankitb073/lanternkb ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from lanternkbPass
- No critical advisory in the package or its dependencies4 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHublanternkb
Private, local search over your own files, for you and the AI tools you choose.
lanternkb indexes the folders you pick and searches them by meaning and by exact words. It runs as a local MCP server for Claude Code and other assistants, with no daemon, no open port and no telemetry. Secrets it detects are redacted before anything is stored, and you decide which folders an assistant that sends results to the cloud may see.
Install
macOS 14 or later on Apple silicon, or Linux, with uv:
uv tool install --managed-python --python 3.12 "lanternkb[embed,ui]"
lanternkb setup # asks for folders and whether an assistant may see them, offers the models, indexes
--python 3.12 matters: without it uv may pick an older Python already on the machine, and the install fails.
The install takes about 0.9 GB on macOS, plus about 1.2 GB for the embedding model. uv tool upgrade lanternkb
updates it.
Search
lanternkb search "what did the plumber say about the boiler"
lanternkb search "boiler quote" --type pdf,docx --since 30d
lanternkb recent # files changed lately
lanternkb ui # the settings page, with a search box
lanternkb doctor # checks the setup and says what to fix
Run lanternkb setup before connecting an assistant: the server searches the folders you chose there.
Use it from your AI tools
Claude Code:
lanternkb mcp-setupprints aclaude mcp addcommand. Run it.- The server it registers returns files from folders you marked open, and nothing else.
- Claude Code can also read files with its own tools, so
mcp-setupprints deny rules too. Add them to~/.claude/settings.jsonto keep its tools away from your local-only folders and the index.
Codex, Cursor, VS Code, Gemini CLI and any other MCP client: run lanternkb serve --tier open as a stdio
server. For Codex, in ~/.codex/config.toml:
[mcp_servers.lanternkb]
command = "lanternkb"
args = ["serve", "--tier", "open"]
The user guide has the JSON form the other clients take, and what to watch for.
What it reads
Notes, code, PDFs, Word and OpenDocument files, rich text, saved web pages and subtitles; scanned pages and audio optionally. Plugins can add file types, embedding models and rules for which folder is open (plugins).
Privacy and safety
- Every folder is
openorlocal-only, and new folders are local-only. - Credential folders and secret-shaped files are skipped, and a secret scanner redacts what it finds before anything is split up or embedded. A file in which it finds a secret becomes local-only, even in an open folder.
- Files are read in sandboxed worker processes that deny by default:
sandbox-execon macOS, Landlock and seccomp on Linux. - Nothing goes over the network except the model downloads you agree to.
The threat model says what is protected and what is not.
How well it works
Tested on a synthetic set of files (three open-source code bases and 654 generated notes) with 330 held-out questions: nDCG@10 0.831, against 0.777 for grooveseek with its reranker and 0.760 for QMD, at about 30 ms a search (about 120 ms with reranking, on an M5 Max). On the hardest held-out test of planted fake secrets, the scanner kept 71.9% out of the index, so treat it as a second line of defence: keep credential folders out of indexed folders, or local-only.
Limits
- The secret scanner misses some secrets, and values that read as examples (
example,changeme, a<placeholder>, a${VARIABLE}) are left alone. - On Linux, reranking runs on the CPU at 0.4 to 1 s a search, so it is off until you enable it.
- Email, browser history, calendars and contact cards are not indexed.
- Scanned PDFs and images need OCR, which is off by default.
More
Licence
Apache-2.0: see LICENSE, NOTICE and THIRD_PARTY_NOTICES.md.
lanternkb MCP questions
How do I add lanternkb MCP to Claude Code?
Run claude mcp add lanternkb -- uvx lanternkb in your terminal. Add --scope user to make it available in every project.
How do I add lanternkb MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How does lanternkb handle privacy and secrets?
It redacts detected secrets before storage and allows you to designate folders as either 'open' for cloud-connected assistants or 'local-only'.
What types of files can be indexed?
The server can index notes, code, PDFs, Word documents, OpenDocument files, rich text, saved web pages, and subtitles.
Does it require a running daemon or open ports?
No, it runs as a local MCP server with no daemon, no open ports, and no telemetry.
Can I use it with Claude Code?
Yes, you can use the lanternkb mcp-setup command to generate a command for adding it to Claude Code.