---
title: "Synthesize Bio MCP integration | Growf"
description: "Synthesize Bio MCP lets agents start and monitor bulk or single-cell gene-expression analyses from natural-language… Connect Synthesize Bio MCP to Growf."
url: "https://www.growf.io/integrations/synthesize_bio_mcp/"
language: "en"
---

Integration / Analytics & Data

![Synthesize Bio MCP logo](https://logos.composio.dev/api/synthesize_bio_mcp)

# Synthesize Bio MCP integration

Synthesize Bio MCP lets agents start and monitor bulk or single-cell gene-expression analyses from natural-language experiment requests.

[Get a demo](https://www.growf.io/demo/)

About Synthesize Bio MCP

## Synthesize Bio MCP is a toolkit that runs bulk and single-cell gene-expression analyses from natural-language experiment requests. Use it to translate experiment intents into reproducible pipelines and monitor results without bespoke integration.

[All integrations](https://www.growf.io/integrations/)

Category

Analytics & Data, Developer Tools & DevOps, AI & Machine Learning

Connection

OAuth

Type

Tool

Actions

1368

Tags

library

Example prompts

## What you can ask Growf to do with Synthesize Bio MCP

- “Run differential expression on latest samples”

- “Start single-cell pipeline for patient sample”

- “Fetch results and generate QC summary report”

Available actions

## 1368 actions your agents can run in Synthesize Bio MCP

- Analyze gene expression  
Starts a differential gene expression analysis using Synthesize Bio's AI platform. Requires the resolution\_id returned by resolve\_sample\_metadata; raw natural-language prompts are not accepted. Requires \`user\_confirmed\_metadata: true\`. When the flag is missing or false, the call is rejected with fa…
- Get analysis results  
Polls the status of a gene expression analysis. Each call waits server-side for a short bounded window and may return earlier if progress is detected. Responses always include a \`structuredContent\` object (declared by the tool's \`outputSchema\`); MCP clients read from \`structuredContent\` directly ra…
- Get counts data url  
Returns a presigned S3 URL to download the raw gene expression counts data (JSON) produced by a completed or in-progress analysis job. The data is typically large (20,000+ genes by N samples) and requires an environment with direct network access. The JSON has the following structure: { gene\_order:…
- Get metadata schema  
Returns the structured-metadata schema used to turn a natural-language experiment description into sample groups. Response fields include \`group\_schema\` (the JSON shape of one sample group), the \`fields\` and \`perturbation\_fields\` inventory for the active metadata version, and \`instructions\` for bui…
- Resolve sample metadata  
Deterministically harmonizes already-structured sample \`groups\` to Synthesize Bio's controlled ontology vocabulary. Does not accept a natural-language prompt and makes no AI calls. Input: \`groups\` — a JSON array of sample-group objects matching get\_metadata\_schema's \`group\_schema\`. Returns a resolu…

## Put Synthesize Bio MCP to work inside Growf.

Connect it once and every workspace, agent and workflow can use it — securely, with your team in the loop.

[Get a demo](https://www.growf.io/demo/)