Skip to content
UsecaseBoard
Saved0
← All use cases
blogGrok-Build

Grok Build Plugin Marketplace: install MongoDB/Vercel/Sentry packs in-terminal

At a glance

xAI’s built-in Grok Build Plugin Marketplace lets the coding agent install partner packs (MongoDB, Vercel, Sentry, Chrome DevTools, Cloudflare, Superpowers) without leaving the terminal—each plugin bundles skills, slash commands, agents, hooks, MCP servers, and LSPs, pinned to a commit SHA verified at install. Browse with `/marketplace` or `grok plugin install <name> --trust`; publish via PR to xai-org/plugin-marketplace. This workflow is listed under Grok-Build, plugins, MCP, coding-agents, marketplace.

Agents / tools
Grok Build, Grok Build Plugin Marketplace, MCP, Vercel, Sentry

Building a tool for these workflows? Sponsor / inquire.

Save ideas in this browser. Upvotes count across the board.

Prompt excerpt

In Grok Build: /marketplace, install [Vercel|Sentry|MongoDB] --trust, then use its skills to [deploy|debug|query] for this repo.

Related workflows

Explore all →
githubmulti-agent

Claustrum: harness-neutral architect that delegates to any coding agent via MCP

Claustrum (alpha, .NET NativeAOT) is a harness-neutral conductor: an architect in Claude Code, Cursor, Copilot CLI, opencode, or desktop delegates builds/reviews/tests to agents on any other harness/model and gets one normalized JSON receipt. Two doors — `claustrum run` CLI and `claustrum mcp` stdio server. Parallel builders on git worktrees, budget ledger, backends doctor. Role-based routing (strong model for architect/reviewer, cheap for builders) without locking the pipeline to one vendor.

ClaustrumClaude Codeopencode+3
Source ↗
productMCP

Kerno: local runtime QA that verifies agent changes against your stack

MCP-connected runtime QA maps critical flows and entry points, then re-tests the blast radius of each Claude Code/Cursor/Codex change against live Postgres/Kafka/APIs/MCP tools—contracts, authz, OWASP, errors—before merge, with self-heal when behavior changes on purpose.

KernoClaude CodeCursor+3
Source ↗
hnagent-memory

MuscleMemory: test-gated procedural memory for coding agents

Open-source local procedural memory that learns only after tests pass, then hands Claude Code/Codex/Cursor a short verified skill note on similar tasks (reported token/tool cuts in published benchmarks).

MuscleMemoryClaude CodeCodex+2
Source ↗
xmcp

REA: one MCP for agent reverse engineering (binaries to apps)

Open-source CLI+MCP (morluto/rea) lets Claude Code/Cursor inspect binaries, Electron/.NET/apps via Hopper/Ghidra/IDA, returning evidence-backed observations so agents can rebuild features from behavior without copying source.

REArea-agentsClaude Code+4
Source ↗