Get started

Svix for AI agents

Svix is webhook infrastructure that lets developers send webhooks reliably, managing applications, endpoints, event types, and delivery retries through an API. 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 SvixSee the 37 actions ↓
Developer toolsAPI keyMCP + RESTsvix.com
AUDIT LOG · SVIXPOLICY: acme-support
09:41:09 · claude · u_8f2write
svix.app_get
Get Application✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
svix.app_delete
Delete Svix Application✕ blocked · policy: deny
EVERY SVIX CALL, ON THE RECORD
01 · USE CASES

What agents do in Svix.

01

List endpoints for an application

Pull the list of webhook endpoints configured for an application as a read-only check before editing one.

02

Replay missed webhook deliveries

Replay webhooks that failed to deliver to an endpoint after the user confirms the endpoint is fixed.

03

Rotate an endpoint secret

Rotate a webhook endpoint's signing secret only after the user confirms the old one should be retired.

02 · ACTIONS

37 Svix actions, graded by risk.

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

read

0

Look things up. Allowed by default.

  • No read actions.

write

33

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

  • svix.app_get
    Get Application
  • svix.app_list
    List Applications
  • svix.app_create
    Create Application
  • svix.app_update
    Update Svix Application
  • svix.attempt_get
    Get Attempt Details
  • svix.message_get
    Get Message
  • svix.attempt_list
    List Message Attempts
  • svix.endpoint_get
    Get Endpoint
  • svix.message_list
    List Messages
  • svix.endpoint_list
    List Endpoints
  • svix.source_create
    Create Source
  • svix.endpoint_patch
    Patch Endpoint
  • svix.event_type_get
    Get Event Type
  • svix.message_create
    Create Message
  • svix.endpoint_create
    Create Endpoint
  • svix.endpoint_update
    Update Endpoint
+ 17 MORE

destructive

4

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

  • svix.app_delete
    Delete Svix Application
  • svix.endpoint_delete
    Delete Endpoint
  • svix.event_type_delete
    Delete Event Type
  • svix.integration_delete
    Delete Integration
03 · HOW IT WORKS

Svix in three steps.

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

# 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 Svix connects.

Users add their Svix 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 Svix 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 Svix 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

Svix and Arc0, answered.

Q01

Can I use Svix with Claude, ChatGPT or Cursor?

Yes. Connect Svix 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 Svix actions you allow.

Q02

How do users connect Svix?

Users add their Svix 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 Svix actions can my agent take?

37 in total: 0 read, 33 write and 4 destructive, such as “get Application”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Svix?

Yes. Actions like “delete Svix Application” 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 Svix too?

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

Get started

Plug Svix into your agent.

Your users connect Svix once, under your brand. Your agent gets 37 actions behind your policies, with every call on the record.

Connect SvixBrowse all apps →

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