Liana-MCP

Created By
scmcphuba year ago
MCP server for cell–cell communication using liana
Overview

What is Liana-MCP?

Liana-MCP is a natural language interface designed for single-cell RNA sequencing (scRNA-Seq) analysis, enabling users to perform cell-cell communication analysis using Liana through the MCP framework.

How to use Liana-MCP?

To use Liana-MCP, install it via PyPI with the command pip install Liana-mcp, and run it locally or remotely as per the provided configuration instructions in your MCP client.

Key features of Liana-MCP?

  • Input/output module for reading and writing scRNA-Seq data.
  • Methods for analyzing cell-cell communication.
  • Plotting capabilities including circle plots and dot plots.

Use cases of Liana-MCP?

  1. Performing scRNA-Seq analysis using natural language queries.
  2. Integrating Liana's functions into AI clients and agent frameworks.
  3. Visualizing cell cluster analysis results in various formats.

FAQ from Liana-MCP?

  • Who can use Liana-MCP?

Anyone interested in scRNA-Seq analysis, including researchers and developers looking to integrate its functionalities into their applications.

  • How do I run Liana-MCP?

You can run it locally or remotely by following the installation and configuration instructions provided in the documentation.

  • Is Liana-MCP open for contributions?

Yes! Contributions to the code are welcome, and users can submit issues or contact the author for questions.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
scmcphub
Star
0
Language
Python
License
-

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago