Conveyor for AI agents

Conveyor automates security reviews and vendor questionnaires, using a Trust Center and AI to speed up compliance work between companies. 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 Conveyor See the 25 actions ↓

Security and identityAPI keyMCP + RESTconveyor.com

AUDIT LOG · CONVEYORPOLICY: acme-support

09:41:07 · claude · u_8f2read

conveyor.get_folders

List all Exchange folders✓ allowed · 212ms

09:41:08 · claude · u_8f2read

conveyor.get_documents

Get all Conveyor documents✓ allowed · 164ms

09:41:09 · claude · u_8f2write

conveyor.post_folder

Create new folder✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

conveyor.delete_folder

Delete folder✕ blocked · policy: deny

EVERY CONVEYOR CALL, ON THE RECORD

01 · USE CASES

What agents do in Conveyor.

Check a questionnaire's status

Check a security questionnaire's status to see how much of it is already answered.

Submit an answer to a question

Submit a single question's answer instead of waiting to complete the entire questionnaire.

Confirm before deleting a document

Confirm before deleting a Trust Center document, since it may be referenced by open requests.

02 · ACTIONS

25 Conveyor actions, graded by risk.

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

read

Look things up. Allowed by default.

conveyor.get_folders
List all Exchange folders
conveyor.get_documents
Get all Conveyor documents
conveyor.get_connections
Get all Conveyor connections
conveyor.get_interactions
Get all interactions
conveyor.get_access_groups
Get all access groups
conveyor.get_product_lines
Get product lines
conveyor.get_authorizations
Get authorizations
conveyor.get_questionnaires
Get questionnaires
conveyor.get_authorization_request
Get Authorization Request
conveyor.get_authorization_requests
Get Authorization Requests
conveyor.get_knowledge_base_questions
Get Knowledge Base Questions
conveyor.get_interactions_by_document_id
Get interactions by document ID
conveyor.get_interactions_by_connection_id
Get interactions by connection ID

write

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

conveyor.post_folder
Create new folder
conveyor.post_review
Create new review
conveyor.post_document
Upload new document
conveyor.post_authorization
Create new authorization
conveyor.post_questionnaire
Submit new questionnaire
conveyor.post_single_question
Submit single question
conveyor.post_questionnaire_request
Create questionnaire request
conveyor.patch_document
Update Conveyor document
conveyor.patch_authorization
Patch authorization
conveyor.patch_questionnaire_request
Update questionnaire request

destructive

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

conveyor.delete_folder
Delete folder
conveyor.delete_document
Delete a Conveyor document

03 · HOW IT WORKS

Conveyor in three steps.

01Your users connect ConveyorThey add their Conveyor api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “create new folder” can wait for the user, and “delete folder” can be denied outright.
03Any agent can actYour agent calls Conveyor 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('conveyor', {
  read: 'allow',
  write: 'ask',        // post_folder
  destructive: 'deny',  // delete_folder
})

# 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 Conveyor connects.

Users add their Conveyor 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 Conveyor 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 Conveyor from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More security and identity apps.

1Password6 actions

AbuseIPDB6 actions

Anonyflow5 actions

Dnsfilter170 actions Borneo153 actions

Digicert101 actions

Paradym69 actions

Persona69 actions

ALL SECURITY AND IDENTITY APPS →

07 · FAQ

Conveyor and Arc0, answered.

Q01

Can I use Conveyor with Claude, ChatGPT or Cursor?

Yes. Connect Conveyor 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 Conveyor actions you allow.

Q02

How do users connect Conveyor?

Users add their Conveyor 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 Conveyor actions can my agent take?

25 in total: 13 read, 10 write and 2 destructive, such as “create new folder”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Conveyor?

Yes. Actions like “delete folder” 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 Conveyor too?

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

Get started

Plug Conveyor into your agent.

Your users connect Conveyor once, under your brand. Your agent gets 25 actions behind your policies, with every call on the record.

Connect Conveyor Browse all apps →

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