bb is an agentic IDE that lets users control, customize, and automate a software-development environment through a desktop app, web app, command-line interface, or HTTP API. Developers use it to run work in observable threads that can be steered or handed off to other agents. Its catalogue add-ons provide skills and instructions for working with bb.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add get-bb/bb --skill mcpgit clone --depth 1 https://github.com/get-bb/bbWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/get-bb/bb/mcp)<a href="https://agentmods.dev/skills/get-bb/bb/mcp"><img src="https://agentmods.dev/badge/skills/get-bb/bb/mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/get-bb/bb/mcp"><img src="https://agentmods.dev/badge/skills/get-bb/bb/mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00026 | $0.00575 |
| Opus 5.5 | $0.00010 | $0.00230 |
| Sonnet 5.5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bb MCP server
The MCP server plugin lets an MCP client control this bb. It is off by default. Turn it on in Settings → Plugins or with bb plugin enable bb--mcp.
Addresses
bb mcp status [--json] prints both addresses.
- Remote:
https://<your bb connect address>/mcp. This needs a signed-in bb account (bb account login) and bb connect. Add it as a custom connector in ChatGPT or Claude. The app sends you to a bb account page where you approve access for this bb. - Local:
http://127.0.0.1:<port>/api/v1/plugins/bb--mcp/http/mcp. Apps on the same machine can use it without signing in. It has the same trust as thebbCLI on that machine. Requests from web pages are refused.
What approving an app grants
Access is all or nothing. An approved app can run any bb command: it can see everything in this bb, and it can start and message agents and open terminals, which run commands and change files on the machines this bb controls. Approve only apps you trust, and disconnect the ones you no longer use.
Connected apps
bb mcp clients [--json]lists the remote apps with access to this bb.bb mcp revoke <grant-id> [--json]disconnects one. The app loses access within about a minute.
The bb account dashboard lists the same apps under Connected apps.
Tools the client sees
searchfindsbbcommands for a task.readruns a JavaScript snippet that can call only commands that inspect bb. It is marked read-only so the app can run it without asking you each time; it is not a separate permission.runruns a JavaScript snippet that can call anybbcommand.
Snippets call bb.cli([...argv]) or bb.json([...argv]) and run in a sandbox on the bb server with no network or file access. A snippet is stopped after 25 seconds, after 3 seconds of computation, or when it runs out of its 64 MB of memory, and runs at most 4 bb commands at a time.
Three commands cannot run over MCP because they need an interactive terminal or never exit: bb terminal attach, bb plugin dev, and bb browser watch.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed 28d6de1a16ed
- 2d ago First seen · 41 lines · 26 tokens per session scan A fff2d6994098
mcp is a skill published in the GitHub repository get-bb/bb (4,324 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 575 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.
Other skills, from other repositories
using-grove
Use when orchestrating Grove workspaces from outside, including creating or supervising host or container agents, steering a fleet, using Grove CLI or MCP tools, or having agents write to each other through the mailbox. Also use when splitting work across workspaces, reviewing a diff from several angles, managing…
working-in-grove
Use when working inside a Grove workspace, including reporting task phase, updating a workspace or its ticket links, using GROVEPHASEFILE, writing to another Grove agent through the mailbox, or waiting on slow work like CI by registering a watch instead of sleeping. Also use when a worktree has a phase file, when…
collaborating-on-diagrams
Use when working with an existing .drawio diagram through Grove collaboration. Triggers on opening, reading, editing, updating, stopping, or recovering a diagram in a Grove workspace. Covers revisioned managed writes, XML-preserving edits, collaboration state, conflicts, read-only stop, and container/editor limits.
mocking-up-in-grove
Use when a visual or frontend task in a Grove workspace needs a mockup approved before code — a new control, a redesigned surface, a layout change. Covers drawing a draw.io mockup through Grove's diagram tools, previewing it in the browser, getting sign-off, filing the approved image on the tracker issue, and handing…
leading-in-grove
Use when you lead a fleet of Grove teammates toward one deliverable, including deciding how many to spawn and how to split the work, writing their onboarding prompt, getting acknowledgment, running scheduled check-ins, answering their mailbox questions, keeping tickets and your own status compaction-proof, reviewing…
configuring-grove
Use when configuring Grove for a user or project, including agent rosters, init scripts, containers, private credentials, daemon or MCP setup, or the native-versus-terminal launch of a Claude Code or Codex agent. Also use when resolving config layers, validating a config schema, or explaining why a workspace starts…