Vectorshift for AI agents

VectorShift builds and runs AI workflows, chatbots, and knowledge bases, used by teams assembling AI automations without writing the orchestration themselves. 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.

Developer toolsAPI keyMCP + RESTvectorshift.ai
AUDIT LOG · VECTORSHIFTPOLICY: acme-support
09:41:07 · claude · u_8f2read
vectorshift.list_chatbots
List Chatbots✓ allowed · 212ms
09:41:08 · claude · u_8f2read
vectorshift.get_chatbot
Get Chatbot✓ allowed · 164ms
09:41:09 · claude · u_8f2write
vectorshift.create_chatbot
Create Chatbot✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
vectorshift.delete_chatbot
Delete Chatbot✕ blocked · policy: deny
EVERY VECTORSHIFT CALL, ON THE RECORD
01 · USE CASES

What agents do in Vectorshift.

01

Run a pipeline

Execute a configured AI pipeline with a given input.

02

Get a knowledge base's contents

Look up what's stored in a knowledge base as a read-only check.

03

Confirm before deleting a chatbot

Check with the user before deleting a chatbot, since its configuration and history go with it.

02 · ACTIONS

11 Vectorshift actions, graded by risk.

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

read

6

Look things up. Allowed by default.

  • vectorshift.get_chatbot
    Get Chatbot
  • vectorshift.get_pipeline
    Get Pipeline
  • vectorshift.list_chatbots
    List Chatbots
  • vectorshift.list_pipelines
    List Pipelines
  • vectorshift.get_knowledge_base
    Get Knowledge Base
  • vectorshift.list_transformations
    List Transformations

write

3

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

  • vectorshift.create_chatbot
    Create Chatbot
  • vectorshift.run_pipeline
    Run Pipeline
  • vectorshift.run_pipeline_bulk
    Run Pipeline in Bulk

destructive

2

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

  • vectorshift.delete_chatbot
    Delete Chatbot
  • vectorshift.terminate_pipeline
    Terminate Pipeline Execution
03 · HOW IT WORKS

Vectorshift in three steps.

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

# 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 Vectorshift connects.

Users add their Vectorshift 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 Vectorshift 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 Vectorshift from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Vectorshift and Arc0, answered.

Q01

Can I use Vectorshift with Claude, ChatGPT or Cursor?

Yes. Connect Vectorshift 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 Vectorshift actions you allow.

Q02

How do users connect Vectorshift?

Users add their Vectorshift 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 Vectorshift actions can my agent take?

11 in total: 6 read, 3 write and 2 destructive, such as “create Chatbot”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Vectorshift?

Yes. Actions like “delete Chatbot” 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 Vectorshift too?

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

Get started

Plug Vectorshift into your agent.

Your users connect Vectorshift once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.

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