Get started

Bigml for AI agents

BigML is a machine learning platform for building and deploying predictive models through a web interface or API, used by data teams without a full ML engineering setup. 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 BigmlSee the 45 actions ↓
AI and modelsAPI keyMCP + RESTbigml.com
AUDIT LOG · BIGMLPOLICY: acme-support
09:41:07 · claude · u_8f2read
bigml.list_pcas
List PCAs✓ allowed · 212ms
09:41:08 · claude · u_8f2read
bigml.get_source
Get Source✓ allowed · 164ms
09:41:09 · claude · u_8f2write
bigml.create_project
Create Project✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
bigml.delete_project
Delete Project✕ blocked · policy: deny
EVERY BIGML CALL, ON THE RECORD
01 · USE CASES

What agents do in Bigml.

01

Check a model's evaluation

List evaluations for a model to check its accuracy before it's used for a real prediction.

02

Pull batch predictions

List batch predictions generated from a dataset to retrieve scored results for a downstream report.

03

Delete a project carefully

Delete a project only after confirming no active models or datasets still reference it, since deletion is permanent.

02 · ACTIONS

45 Bigml actions, graded by risk.

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

read

41

Look things up. Allowed by default.

  • bigml.list_pcas
    List PCAs
  • bigml.get_source
    Get Source
  • bigml.get_project
    Get Project
  • bigml.list_models
    List Models
  • bigml.list_fusions
    List Fusions
  • bigml.list_optimls
    List OptiMLs
  • bigml.list_samples
    List Samples
  • bigml.list_scripts
    List Scripts
  • bigml.list_sources
    List Sources
  • bigml.list_clusters
    List Clusters
  • bigml.list_datasets
    List Datasets
  • bigml.list_deepnets
    List Deepnets
  • bigml.list_projects
    List Projects
  • bigml.list_anomalies
    List Anomaly Detectors
  • bigml.list_centroids
    List Centroids
  • bigml.list_ensembles
    List Ensembles
+ 25 MORE

write

3

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

  • bigml.update_source
    Update Source
  • bigml.create_project
    Create Project
  • bigml.create_external_connector
    Create External Connector

destructive

1

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

  • bigml.delete_project
    Delete Project
03 · HOW IT WORKS

Bigml in three steps.

  1. 01Your users connect BigmlThey add their Bigml api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Project” can wait for the user, and “delete Project” can be denied outright.
  3. 03Any agent can actYour agent calls Bigml 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('bigml', {
  read: 'allow',
  write: 'ask',        // create_project
  destructive: 'deny',  // delete_project
})

# 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 Bigml connects.

Users add their Bigml 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 Bigml 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 Bigml from any agent.

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

More ai and models apps.

Perplexity AI9 actionsAffinda119 actionsAgent Mail5 actionsAI/ML API30 actionsAivoov1 actionsAll Images AI7 actionsAltText.ai10 actionsAltTextLab2 actions
ALL AI AND MODELS APPS →
07 · FAQ

Bigml and Arc0, answered.

Q01

Can I use Bigml with Claude, ChatGPT or Cursor?

Yes. Connect Bigml 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 Bigml actions you allow.

Q02

How do users connect Bigml?

Users add their Bigml 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 Bigml actions can my agent take?

45 in total: 41 read, 3 write and 1 destructive, such as “create Project”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Bigml?

Yes. Actions like “delete Project” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Bigml too?

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

Get started

Plug Bigml into your agent.

Your users connect Bigml once, under your brand. Your agent gets 45 actions behind your policies, with every call on the record.

Connect BigmlBrowse all apps →

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