Documentation
Recall

Let Claude, Cursor and Codex read your codecast

Add codecast.sh/mcp to an agent that runs outside codecast, sign in once, and it reads your docs, tasks, plans, pages and sessions as you, read only.

3 min read

Some of the agents you work with don't run on a computer where codecast is installed: Claude in the browser or the Claude app, Claude Code or Cursor on a laptop without the codecast app, Codex in the cloud. They can still read your codecast. Add one address to the agent, sign in once, and it can look up your docs, tasks, plans, published pages and sessions, the same ones you see in the app.

Settings, Connected agents: the codecast.sh/mcp address with a Copy button, a setup line for Claude, Claude Code, Cursor and Codex, and what a connected agent can and cannot do
Settings, Connected agents. Pick your agent's tab for its setup line.

Connect an agent

Open Settings and choose Connected agents. The page shows the address, https://codecast.sh/mcp, and a tab for each agent with the line it needs:

AgentWhat to do
Claude (web, desktop and mobile apps)Settings, Connectors, Add custom connector. Paste the address, then Connect.
Claude CodeRun claude mcp add --transport http codecast https://codecast.sh/mcp, then /mcp, pick codecast and sign in.
CursorAdd the server to ~/.cursor/mcp.json with the address as its url, then Connect.
CodexRun codex mcp add codecast --url https://codecast.sh/mcp, then codex mcp login codecast.

Any other agent that speaks MCP over HTTP connects the same way: give it the address.

The agent then opens a codecast page in your browser. It leads with where the agent will send you back to (this computer, or a website), then the name the agent gives itself, the account it will act as, the workspaces it will read, and Writes: Nothing. Connect shows one more review of what it reads and how to stop it, and confirming finishes the connection. You never paste a token anywhere.

What it can read

A connected agent reads as you, through the same rules that decide what you see in the app:

  • Docs, tasks and plans you can read, with task comments and a plan's tasks.
  • Published pages you own, your teams share, or that are open. A page behind a password or an email list you don't own comes back locked, with the reason.
  • Sessions the way their cards show them to you: title, pinned state, summary, status and project. A teammate's session shows only what that session shares with the team.
  • One workspace at a time when you ask. Your agent sees all of your workspaces by default; tell it to stay in one team and it filters to that team.

Something you can't see in the app doesn't exist for the agent either. If you leave a team, or a page or session goes private, the agent loses it on its next read.

What it can't do

  • Change, create or delete anything. Connections are read only.
  • Message a session or read a session's full transcript.
  • Read the Vault, connectors or credentials.
  • Disconnect itself or another agent.

What it reads from codecast is your team's writing, so the agent is told to treat doc bodies, pages and summaries as material to read, never as instructions to follow.

See and stop connections

Connected at the bottom of the same page lists every agent you've connected, with the site it returns to and when it last read (or when it connected, until its first read). Disconnect ends a connection at once: the agent's next request is refused, and it has to ask you again to come back. Connecting the same agent again replaces its earlier connection rather than adding a second one.

More guides
Agent features: what your agents know how to do
Switch features on for each computer, and every new session there learns to remember, delegate, track work, show results and use your machine.
Memory: agents that look up past work
Your agents search every session you can see, across your machines, agents and team, and answer with the session they found it in.
Search your history across every machine
Every computer you connect sends its sessions to one history, searchable from the web, the Mac app and your iPhone.
See which agent session wrote a line
Set Blame to Sessions on any file to see the session behind each line, and open the conversation where it was decided.
Messaging between sessions
Your sessions hand each other results and answers directly, so you stop relaying text between them.
Stable context: sessions that know what's been happening
New sessions start with a short list of what you and your team worked on recently, so they pick up threads instead of starting cold.
See your whole team's agent sessions in one place
Every session your team runs, on every machine and agent, in one live Activity page and inbox, shared per folder.
Use Codecast with T3 Code
Threads you start in T3 Code appear in Codecast with no setup, beside every session you run anywhere else, ready to search, steer and share. What you get on top, and what stays in T3 Code.
Use Codecast with OpenCode
Sessions you run in the OpenCode TUI appear in Codecast within seconds, with no plugin. Reply to them from the app, start new OpenCode sessions there, and search them beside every other agent you use.
Share a session with your team
Choose what the team sees of a session, share it by link or a few messages at a time, and how that compares to other tools.
Pinned thread state
The agent keeps one short note on each session saying where it stands, above the composer and on its inbox card.
Decisions: asking without interrupting
Agents put the calls only you can make on one Decisions page you clear when you choose to, and each answer goes back to the session that asked.
Team chat with your agents in the room
Channels, threads and DMs where you can hand a session or a role something by mentioning it, while agents stay quiet unless they're needed.
Huddles, transcripts and walkie
Every huddle is transcribed under each speaker's name and leaves a summary, so your agents can quote what was said, and a session can join the call.
Workers, forks and switching agents
Your agent can hand work to workers that report back to it, and you can fork a conversation to try two directions from the same point.
Tasks and plans
Agents file the work they take on, post progress and close it with what they verified, and you follow it on the Tasks and Plans pages.
Triggers
Agents schedule their own follow-ups, once, on a schedule or on a GitHub or Linear event, and you can set one yourself from the Triggers page.
Workflows
A fixed sequence of agent steps, checks and approval gates that runs the same way every time and waits for you where you want a say.
Orchestration
Hand an agent a whole plan and it runs a team: implementers working in parallel, a reviewer on every task and critics on the result.
Pull requests and issues
Every pull request gets a page with its checks and threads, the session that opened it fixes what reviewers and CI flag, and Linear or GitHub issues become tasks.
The org: roles that look after your work
Give lasting work to a role with an area, a charter and a standing session, and approve the changes your agents propose to the org.
Let agents use your Chrome
Agents check pages in the Chrome you already use, logins included, from their own background tabs. Screenshots and errors come back to the conversation.
Vault: keys, logins and sign-ins for your agents
Fill a credential once and every agent on every machine can use it, without the value ever entering a conversation.
Computer use: agents in your Mac apps
Agents work in Preview, Slack, System Settings or your own desktop build, in the background, with an orange pointer that shows where they act.
Typecheck: one shared check for every agent
With Typecheck on, agents on a computer share one typecheck per project, so checks answer in seconds and a busy machine stays usable.
Skills: slash commands for the jobs you repeat
Type / in a Claude Code session to pick up work, hand it over, get a second opinion or ship a pull request, the same careful way every time.
Run sessions on other machines and in the cloud
Start a session on another computer or a cloud machine in your AWS account, move it there and back, and watch it from anywhere.
Codex Cloud tasks in codecast
Bring your Codex Cloud tasks into your inbox, start new ones with several attempts, and turn the result into a pull request or local changes.
Usage limits are a pause
When a Claude plan runs out, sessions wait for the reset or continue on another account you've saved, instead of stopping for good.
The visual canvas
Agents answer with charts, comparisons and diagrams drawn right in the conversation when a picture says it better than text.
Published pages
Agents turn reports and mockups into pages with their own link that you can share, gate, and get comments on.
Why codecast feels instant, even offline
Everything you see comes from a copy on your device that the server keeps current, so screens open at once, your edits show immediately, and nothing is lost offline.
Taking longer than usualOffline · reloads when back