Jam for AI agents

Jam captures, organizes, and shares browser bug reports and recordings for engineering teams to debug issues faster. Developers wire it into their own apps and internal tools instead of building the underlying capability from scratch. 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 Jam See the 16 actions ↓

Developer toolsAPI keyMCP + RESTjam.dev

AUDIT LOG · JAMPOLICY: acme-support

09:41:07 · claude · u_8f2read

jam.list_jams

List Jams✓ allowed · 212ms

09:41:08 · claude · u_8f2read

jam.list_folders

List Jam Folders✓ allowed · 164ms

EVERY JAM CALL, ON THE RECORD

01 · USE CASES

What agents do in Jam.

Pull a bug report's details

Pull the console logs and network requests from a reported bug to help an engineer reproduce it.

Get a recording's transcript

Get the transcript of a screen recording to understand a user's reported issue without watching the video.

List recent jams for a project

List recent jam reports for a project to see how many bugs came in this week.

02 · ACTIONS

16 Jam actions, graded by risk.

Every Jam 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.

jam.list_jams
List Jams
jam.list_folders
List Jam Folders
jam.list_members
List Jam Members
jam.get_jam_details
Get Jam Details
jam.get_screenshots
Get Jam Screenshots
jam.get_user_events
Get User Events
jam.get_console_logs
Get Console Logs
jam.get_jam_metadata
Get Jam Metadata
jam.get_video_frames
Get Jam Video Frames
jam.get_recording_link
Get Recording Link
jam.get_network_requests
Get Network Requests
jam.get_video_transcript
Get Jam Video Transcript
jam.list_recording_links
List Recording Links
jam.list_recording_domains
List Recording Domains
jam.list_recording_link_jams
List Recording Link Jams
jam.analyze_video
Analyze Jam Video

write

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

No write actions.

destructive

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

No destructive actions.

03 · HOW IT WORKS

Jam in three steps.

01Your users connect JamThey add their Jam api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
03Any agent can actYour agent calls Jam 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('jam', {
  read: 'allow',
  write: 'ask',        
  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 Jam connects.

Users add their Jam 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 Jam 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 Jam 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.

Addressfinder17 actions

Addresszen2 actions

Alchemy36 actions

ALL DEVELOPER TOOLS APPS →

07 · FAQ

Jam and Arc0, answered.

Q01

Can I use Jam with Claude, ChatGPT or Cursor?

Yes. Connect Jam 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 Jam actions you allow.

Q02

How do users connect Jam?

Users add their Jam 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 Jam actions can my agent take?

16 in total: 16 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Jam?

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

Q05

Can my own backend call Jam too?

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

Get started

Plug Jam into your agent.

Your users connect Jam once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.

Connect Jam Browse all apps →

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