mcpField
F
flatbread

flatbread

Local
flatbread.ioDeveloper Tools2Updated 6d ago
RepositoryVisit website

About flatbread

Flatbread is a CLI and local review flow for sharing coding-agent sessions as links. It redacts secrets and personal details on the user's machine before upload, and lets people or agents retrieve a shared run's account and continue from it.

Key features

  1. 01Read sessions from multiple coding agents
  2. 02Review runs locally before sharing
  3. 03Redact secrets and personal details before upload
  4. 04Choose private, unlisted, or public access
  5. 05Let agents retrieve and continue shared runs

Use cases

  1. 01Share a coding-agent run for human review
  2. 02Let another agent pick up findings from a prior run

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "flatbread-cli-flatbread": {
      "command": "npx",
      "args": [
        "-y",
        "flatbread-cli"
      ]
    }
  }
}
Run commandnpx -y flatbread-cli

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmflatbread-cli0.9.8

Tools

3

Saved tool list · updated 5d ago

ParameterTypeRequiredDescription
querystringNoTwo to four words from the task or the error. Runs with every word in their title or ID come first; when none has them all, the closest are listed, marked with how many words they share
harnessenumNoOnly runs from this agent harnessclaude-code | codex | cursor | opencode | antigravity | gemini | cline | copilot | terminal | otel

Details

From the project README

Flatbread

Flatbread turns an agent session into one link: what was asked, every step, what broke, what fixed it and the diff. People read it. Agents pull it and pick up where it ended.

The package is flatbread-cli. Never run npx flatbread or npm install flatbread: that npm name belongs to an unrelated project.

Share your first run

  1. Install it: npm install -g flatbread-cli. You need Node.js 20 or newer (nodejs.org).
  2. Connect your agents, once: flatbread setup. Then you can share from their chat. Updates keep it current, and an agent you install later is connected the next time Flatbread runs, so you never run it again.
  3. When a session is done, say share this run in its chat, or run flatbread share in a terminal. From a terminal it says which session it took. Not the session you meant? It prints the command for every other tool's newest, such as flatbread share gemini.
  4. A review page opens in your browser. It runs on your own computer (127.0.0.1), and nothing has left it yet. No tab? Open the link the terminal or your agent printed.
  5. Check it. Keys, passwords and personal details are already hidden. Hide more words if you like, and choose who can open the run: Private (only you), Unlisted (anyone with the link) or Public.
  6. Press Confirm & share. Not signed in yet? Press Sign in to Flatbread first: it opens a new tab, and this page keeps what you chose.
  7. Copy your link: the page that follows shows it, with Copy link.

Rather have your agent do steps 1 and 2? Tell it: Install and set up Flatbread using https://flatbread.io/install.md

Anyone's agent can then say "pull flatbread " to read what that run learned.

Flatbread reads sessions from Claude Code, Codex, Cursor, OpenCode, Google Antigravity, Gemini CLI, Cline and GitHub Copilot CLI. flatbread setup connects Claude Code, Codex, Cursor, Google Antigravity, OpenCode, Gemini CLI, GitHub Copilot CLI and Cline.

In this repository

The docs, the changelog and the issue forms. The CLI is published on npm as flatbread-cli; its source is not published here.

Issues are for bugs, missed redactions and agents you want Flatbread to read. Site: https://flatbread.io

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.