Get started

Seqera for AI agents

Seqera Platform centralizes the launch, management, and monitoring of Nextflow data pipelines across on-premises and cloud compute environments. Bioinformatics and data engineering teams use it to run pipelines at scale. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect SeqeraSee the 14 actions ↓
Developer toolsAPI keyMCP + RESTseqera.io
AUDIT LOG · SEQERAPOLICY: acme-support
09:41:07 · claude · u_8f2read
seqera.list_pipelines
List Pipelines✓ allowed · 212ms
09:41:08 · claude · u_8f2read
seqera.get_user_info
Get User Info✓ allowed · 164ms
09:41:09 · claude · u_8f2write
seqera.create_wave_container
Create Wave Container✓ approved · approved by user
EVERY SEQERA CALL, ON THE RECORD
01 · USE CASES

What agents do in Seqera.

01

List running pipelines

Pull the pipelines and workflows in an organization to see what's active before starting a new run.

02

Validate a pipeline name first

Check that a proposed pipeline name is valid before launching it, catching naming conflicts early.

03

Check a container build's status

Look up a Wave container build's status and logs to confirm it finished before using it in a run.

02 · ACTIONS

14 Seqera actions, graded by risk.

Every Seqera action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

12

Look things up. Allowed by default.

  • seqera.get_user_info
    Get User Info
  • seqera.list_pipelines
    List Pipelines
  • seqera.list_workflows
    List Workflows
  • seqera.get_service_info
    Get Service Info
  • seqera.list_organizations
    List Organizations
  • seqera.get_wave_build_logs
    Get Wave Build Logs
  • seqera.get_wave_build_status
    Get Wave Build Status
  • seqera.list_action_event_types
    List Action Event Types
  • seqera.get_organization_details
    Get Organization Details
  • seqera.list_compute_environments
    List Compute Environments
  • seqera.validate_action_name
    Validate Action Name
  • seqera.validate_pipeline_name
    Validate Pipeline Name

write

2

Create and change things. Allow, or ask the user first.

  • seqera.create_wave_container
    Create Wave Container
  • seqera.inspect_wave_container
    Inspect Wave Container

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

Seqera in three steps.

  1. 01Your users connect SeqeraThey add their Seqera api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “create Wave Container” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Seqera through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('seqera', {
  read: 'allow',
  write: 'ask',        // create_wave_container
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Seqera connects.

Users add their Seqera api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Seqera connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Seqera from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More developer tools apps.

GitHub896 actionsSupabase129 actions0CodeKit8 actionsAbly25 actionsAbstract3 actionsAddressfinder17 actionsAddresszen2 actionsAlchemy36 actions
ALL DEVELOPER TOOLS APPS →
07 · FAQ

Seqera and Arc0, answered.

Q01

Can I use Seqera with Claude, ChatGPT or Cursor?

Yes. Connect Seqera to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Seqera actions you allow.

Q02

How do users connect Seqera?

Users add their Seqera api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Seqera actions can my agent take?

14 in total: 12 read, 2 write and 0 destructive, such as “create Wave Container”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Seqera?

Yes. Allow read actions and deny writes in the Seqera policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Seqera too?

Yes. The same Seqera connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Seqera into your agent.

Your users connect Seqera once, under your brand. Your agent gets 14 actions behind your policies, with every call on the record.

Connect SeqeraBrowse all apps →

Free to build · MCP + REST · Audit log on every plan