Synthesize Bio MCP connector

1. Install the SDK

   Node.js

   npm install @scalekit-sdk/node

   Python

   pip install scalekit

   Full SDK reference: Node.js | Python

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   .env

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Authorize and make your first call

   Node.js

   quickstart.ts

   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   
   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENV_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions
   
   const connector = 'synthesizebiomcp'
   const identifier = 'user_123'
   
   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Synthesize Bio MCP:', link)
   process.stdout.write('Press Enter after authorizing...')
   await new Promise(r => process.stdin.once('data', r))
   
   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'synthesizebiomcp_get_analysis_results',
     toolInput: { job_id: 'YOUR_JOB_ID' },
   })
   console.log(result)

   Python

   quickstart.py

   import os
   from scalekit.client import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()
   
   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENV_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions
   
   connection_name = "synthesizebiomcp"
   identifier = "user_123"
   
   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Synthesize Bio MCP:", link_response.link)
   input("Press Enter after authorizing...")
   
   # Make your first call
   result = actions.execute_tool(
       tool_input={"job_id":"YOUR_JOB_ID"},
       tool_name="synthesizebiomcp_get_analysis_results",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)

What you can do

Connect this agent connector to let your agent:

• Metadata resolve sample — Resolve a natural-language experiment description into structured sample groups using Synthesize Bio’s AI metadata extraction
• Get counts data url, analysis results — Retrieve a presigned download URL for the raw gene expression counts data produced by a completed analysis job
• Expression analyze gene — Start a differential gene expression analysis using Synthesize Bio’s AI platform, returning a job ID to track progress

Tool list

Use the exact tool names from the Tool list below when you call execute_tool. If you’re not sure which name to use, list the tools available for the current user first.

synthesizebiomcp_analyze_gene_expression # Start a differential gene expression analysis using Synthesize Bio's AI platform, returning a job ID to track progress. 1 param ▾

Start a differential gene expression analysis using Synthesize Bio's AI platform, returning a job ID to track progress.

Name Type Required Description

resolution_id string required The completed resolution_id returned by resolve_sample_metadata.

synthesizebiomcp_get_analysis_results # Poll the status and results of a running gene expression analysis job. 1 param ▾

Poll the status and results of a running gene expression analysis job.

Name Type Required Description

job_id string required The job_id returned by analyze_gene_expression.

synthesizebiomcp_get_counts_data_url # Retrieve a presigned download URL for the raw gene expression counts data produced by a completed analysis job. 1 param ▾

Retrieve a presigned download URL for the raw gene expression counts data produced by a completed analysis job.

Name Type Required Description

job_id string required The job_id returned by analyze_gene_expression.

synthesizebiomcp_resolve_sample_metadata # Resolve a natural-language experiment description into structured sample groups using Synthesize Bio's AI metadata extraction. 3 params ▾

Resolve a natural-language experiment description into structured sample groups using Synthesize Bio's AI metadata extraction.

Name Type Required Description

modality string optional Sequencing modality. Defaults to "bulk".

prompt string optional Natural language description of the experiment, e.g. "heart vs liver cells" or "KRAS knockout vs control in lung adenocarcinoma". Required unless `resolution_id` is provided to poll a previously-started resolution.

resolution_id string optional Resolution identifier from a previous response with status 'resolving'. When provided, polls that in-flight resolution and `prompt` may be omitted.