Piaso MCP
Docs for the PIASO single-cell omics toolkit and its companion packages, plus marker DB
- Pricing
- Open source
- Platforms
- CLI, self-hosted
- Runs
- Locally
- Version
- 0.1.1
- Listing updated
- 1 day ago
About Piaso MCP
Piaso MCP is an open-source MCP server for health and science. It runs locally on your machine and is started by your AI client.
This server serves documentation for the PIASO ecosystem, built from a single agent-neutral knowledge pack kept by the Fishell Laboratory at Harvard Medical School and the Broad Institute. It also reaches the live PIASOmarkerDB. The registry entry names PIASO, COSG, cytome, LARIS and cytorete as covered components.
The README explains how the pieces fit: piaso-tools for analysis, cytome for single-file SQLite storage, COSG for marker genes, LARIS for spatial ligand-receptor analysis, and cytorete for gene regulatory networks. It also covers choices such as SCALAR versus LARIS, and AnnData versus .cytome. The docs are tested against pinned component versions on every push.
It is for bioinformaticians who want a coding agent to write correct single-cell analysis code. It runs over stdio from a PyPI package.
Install
Run in a terminal
claude mcp add piaso-mcp -- uvx piaso-mcpAdd to claude_desktop_config.json
{
"mcpServers": {
"piaso-mcp": {
"command": "uvx",
"args": [
"piaso-mcp"
]
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"piaso-mcp": {
"command": "uvx",
"args": [
"piaso-mcp"
]
}
}
}Add to .vscode/mcp.json
{
"servers": {
"piaso-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"piaso-mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"piaso-mcp": {
"command": "uvx",
"args": [
"piaso-mcp"
]
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"piaso-mcp": {
"command": "uvx",
"args": [
"piaso-mcp"
]
}
}
}What it does
- Ecosystem documentation
- Guides for PIASO, COSG, cytome, LARIS and cytorete.
- Live marker database
- Connects to PIASOmarkerDB for annotation.
- Tested guidance
- Code blocks run against pinned versions in CI.
- Agent-neutral pack
- Same knowledge generated for Claude, Cursor, Codex and others.
- Composition advice
- Explains choosing between tools such as SCALAR and LARIS.
Good for
- Ask an agent to write a PIASO analysis pipeline
- Choose between COSG and cytorete for a question
- Look up marker genes for annotating cell types
- Set up spatial ligand-receptor analysis
Pricing
Open source
Prices change. Check piaso.org before you buy.
Piaso MCP FAQ
How is it installed?
As the piaso-mcp package from PyPI, over stdio.
Who maintains it?
The Fishell Laboratory at Harvard Medical School and the Broad Institute.
Which versions is it tested against?
The README lists piaso-tools 1.2.6, cosg 1.2.0, cytome 0.3.6, laris 0.14.0 and others.
Is Piaso MCP free?
Yes. Piaso MCP is open source, so you can use and self-host it for free.
How do I add Piaso MCP to Claude Code?
Run this command in your terminal: claude mcp add piaso-mcp -- uvx piaso-mcp
What are the best alternatives to Piaso MCP?
The closest alternatives to Piaso MCP are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Piaso MCP

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools