Ga naar de hoofdinhoud

Integration / Analytics & Data

Synthesize Bio MCP integration

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

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
Category
Analytics & Data, Developer Tools & DevOps, AI & Machine Learning
Connection
OAuth
Type
Tool
Actions
5
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

5 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.