# Awesome Grok Bot Plugins > A directory of plugins in Grok Bot's in-app marketplace: 219 Cursor Marketplace listings from the 2026-08-12 catalog capture, organized by category with descriptions and use cases. - **Type:** MCP server - **Install:** `agentstack add mcp-rdmgator12-awesome-grok-bot-plugins` - **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior - **Seller:** [rdmgator12](https://agentstack.voostack.com/s/rdmgator12) - **Installs:** 0 - **Category:** [Integrations](https://agentstack.voostack.com/c/integrations) - **Latest version:** 0.1.0 - **License:** CC0-1.0 - **Upstream author:** [rdmgator12](https://github.com/rdmgator12) - **Source:** https://github.com/rdmgator12/awesome-grok-bot-plugins ## Install ```sh agentstack add mcp-rdmgator12-awesome-grok-bot-plugins ``` Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent. ## About # Awesome List for Grok Bot Plugins [](https://awesome.re) [](https://github.com/rdmgator12/awesome-grok-bot-plugins/commits/main) > A directory of the plugins in [Grok Bot](https://x.ai/bot)'s in-app marketplace (Settings, Plugins) — 219 listings across the 2026-08-12 catalog capture, plus 0 held pending marketplace-URL verification, organized by the catalog's own categories with descriptions and use cases. **Last updated:** August 12, 2026 | **Plugins tracked:** 219 listed + 0 held | **Categories:** 13 xAI's teammate product: named agents on a persistent cloud computer. The full model, eligibility, and how plugins fit are in What is Grok Bot, first section below. This list is maintained weekly. To contribute, see [CONTRIBUTING.md](CONTRIBUTING.md). > This is an independent, community-maintained list. Not affiliated with, endorsed by, or sponsored by xAI Corp, X.AI LLC, Cursor (Anysphere), SpaceX, or any Musk-affiliated entity. "Grok", "Grok Bot", and related marks are the property of xAI. "Cursor" is the property of Anysphere. Each plugin is the property of its respective owner. > [!TIP] > ### Plugin Snap Stack — August 12, 2026 > > Same format as the connector lists: a persona plus a small stack that clicks together. Past stacks will live in [docs/stacks](docs/stacks/). Sweep history lives in the [changelog](docs/CHANGELOG.md). > > **The overnight sales outbound Bot** — Apollo.io · Clay · Gong · HubSpot · running on **Grok Bot** > > One Bot, four plugins: research and score accounts in Apollo, enrich the shortlist in Clay, pull the last-call brief from Gong, then write the CRM note and next step in HubSpot before asking for approval on the outbound draft. Composed from the day-0 Grok Bot catalog, not yet field-tested — if you run it on a live book, send a Field Report (see CONTRIBUTING). > > Disclaimer: This is a free, public, community-maintained list. Not affiliated with, endorsed by, or sponsored by Grok, xAI Corp, SpaceX, or any Musk-affiliated entity. "Grok" and related marks are the property of xAI Corp. Each connector is the property of its respective owner. No fees, no paid placement, no commercial relationship with any vendor listed. --- ## Contents - [What is Grok Bot](#what-is-grok-bot) - [Agent Orchestration](#agent-orchestration) - [Canvas](#canvas) - [Customer Support](#customer-support) - [Data Analytics](#data-analytics) - [Featured](#featured) - [Finance And Legal](#finance-and-legal) - [Inbox And Collaboration](#inbox-and-collaboration) - [Infrastructure](#infrastructure) - [MCP](#mcp) - [Payments](#payments) - [Productivity](#productivity) - [Sales](#sales) - [Scheduling](#scheduling) - [Held for Verification](#held-for-verification) - [Related](#related) --- ## What is Grok Bot [Grok Bot](https://x.ai/news/introducing-grok-bot) is xAI's teammate product, opened as an early beta on August 11, 2026. It is not a chat window with a few tools bolted on. Each Bot is a named, persistent agent that works on a **cloud computer of its own** — browser, filesystem, and terminal — and keeps working after the laptop closes. You message a Bot the way you would text a colleague. A good handoff names the outcome, the apps or files it should use, the constraints, the deliverable, and when to stop for approval. The Bot then signs into those tools and finishes the work *in the actual product*, not as a draft in chat. Passwords, passkeys, 2FA, CAPTCHAs, and payments stay with you: the Bot pauses, you take over the computer for that step, then you hand it back. xAI's own framing is the last ten percent: most assistants get a task almost done; a Bot is supposed to land it where a human would put it. All Bots on an account share one computer. Browser sessions, `/workspace` files, and CLI credentials are account-scoped, not Bot-scoped. That is why a handoff works without re-setup, and why a login you complete for one Bot is available to the others. Several Bots can run in parallel, message each other, and sit in a group thread. Focused Bots (sales outbound, inbox, bug reproduction) beat one catch-all. Show a Bot a workflow once and it can save that path as a **routine** and re-run it on a schedule. Over time it keeps memory, preferences, files, and signed-in sessions, so the second Friday close is cheaper than the first. **Who can use it today.** SuperGrok Heavy, Cursor Ultra, and Cursor Teams Premium. Desktop apps for macOS and Windows, plus iOS. No Linux desktop app yet. Enterprise is a waitlist. Grok Bot requires cloud data storage; Cursor Legacy Privacy Mode accounts have to move to a supported data setting before a Bot will start. **How plugins fit.** In the app, structured connections appear under **Settings, Plugins**. They are [Cursor Marketplace](https://cursor.com/marketplace) bundles — skills, MCP servers, slash commands, and related agent primitives. After install, `@` attaches a plugin to the task and `/` calls a saved skill. Prefer a plugin when one exists: it is usually more reliable than clicking through a website. Use the Bot's browser for services without a plugin, or for visual workflows the plugin does not expose. Installed plugins are account-wide. > [!IMPORTANT] > Four xAI surfaces, four jobs. This list is only Grok Bot's plugin catalog. > > - **Grok** (grok.com) is the chat assistant. > - **Grok Connectors** are OAuth tiles *inside that chat* — email, calendar, files. Tracked in awesome-grok-connectors (see Related). > - **Grok Build** is the local terminal coding agent, with its own marketplace at `xai-org/plugin-marketplace`. > - **Grok Bot** is a team of cloud-computer agents. Plugins here are how a Bot gets a structured hook into a supported service. The public listing lives on the Cursor Marketplace; the inclusion gate for *this* list is the Grok Bot in-app catalog (Settings, Plugins). > > A plugin is not required to use a Bot. Computer-use covers apps with no API. The catalog below is the structured layer. ## Agent Orchestration 19 plugins. - [Arize](https://arize.com) - Add Arize AX observability to LLM applications - auto-instrumentation, trace export, dataset management, experiment workflows, prompt optimization, and deep linking via the ax CLI. *Use case: Exporting traces from a failing eval run, comparing two prompt versions, opening the deep link to the span that blew the score.* - [Atlan](https://atlan.com) - Enterprise context layer for governed metadata, lineage, glossaries, and SQL over organization knowledge repos. *Use case: Looking up the glossary definition before writing a join, walking lineage from a broken dashboard metric, running a governed SQL check.* - [AWS Agents](https://aws.amazon.com/bedrock/agentcore/) - Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production. *Use case: Scaffolding a Bedrock AgentCore worker, attaching a Gateway tool, reading a trace after a failed multi-agent handoff.* - [AWS SageMaker](https://aws.amazon.com/sagemaker/) - Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI. *Use case: Choosing a training job type, checking why a hosted endpoint drifted, generating the deploy config for a new model.* - [Browserbase Browse](https://www.browserbase.com) - Browser automation for Cursor. Navigate, click, fill forms, extract data, capture network, manage tabs, and take screenshots - powered by browse-cli and controlled via MCP. *Use case: Opening a staging URL, filling a form the API does not expose, capturing the network call that failed checkout.* - [Composio](https://composio.dev) - Connect and operate 1000+ external apps from Cursor via the Composio MCP server. Managed OAuth, intelligent tool routing, and a remote sandbox for bulk data processing. *Use case: Connecting a SaaS account over managed OAuth, routing a tool call to the right app, running a bulk pull in the remote sandbox.* - [Context7](https://context7.com) - Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context. *Use case: Pulling the current SDK page for a library, grabbing a version-specific example, checking whether a method still exists.* - [Create Plugin](https://cursor.com/marketplace/cursor/create-plugin) **`C`** - Scaffold and validate new agent plugins. Handles directory setup, manifest generation, and pre-submission quality checks for the marketplace. *Use case: Scaffolding a new marketplace plugin, generating the manifest, running the pre-submit quality checks.* - [DataRobot](https://www.datarobot.com) - A collection of DataRobot agent skills for model training, deployment, predictions, monitoring, and more. *Use case: Kicking off a training job, checking a deployment's prediction health, pulling a monitoring alert.* - [Firetiger](https://www.firetiger.com) - Cursor plugin for Firetiger agentic operations plugin with skills and MCP access. *Use case: Asking the ops agent what is on fire, pulling the skill that matches an incident, querying MCP for the latest signal.* - [Langfuse](https://langfuse.com) - Skills for working with Langfuse - the open-source LLM engineering platform for tracing, prompt management, and evaluation. *Use case: Inspecting a trace for a bad generation, pulling the current prompt version, comparing eval scores across two runs.* - [Opsera](https://www.opsera.io) - DevSecOps agent for architecture analysis, security scanning, compliance auditing, and SQL security review. *Use case: Running an architecture scan, checking a SQL query for a security finding, reading a compliance audit result.* - [Parallel](https://parallel.ai) - Web search, content extraction, deep research, and data enrichment powered by parallel-cli. *Use case: Running a deep-research pass on a competitor, extracting structured fields from a set of pages, enriching a lead list.* - [Runlayer](https://www.runlayer.com) - Simpler, safer way to run MCPs, Skills, and Agents. Discover what's running, enforce security policies in real time, protect secrets, and get full audit trails - all built for how developers actually work in Cursor. *Use case: Listing what MCP servers are live, blocking a tool that would leak a secret, pulling the audit trail after a run.* - [shadcn/ui](https://ui.shadcn.com) - UI component and design system framework. Search registries, install components as source code, and audit your project. *Use case: Searching a registry for a component, installing it as source, auditing which components a project already uses.* - [Sourcegraph](https://sourcegraph.com) - Code search plus an MCP server and slash commands for navigating large codebases from the agent. *Use case: Searching a symbol across repos, opening the MCP result for a call site, running a slash command against the graph.* - [Superpowers](https://github.com/obra/superpowers) - Core skills library: TDD, debugging, collaboration patterns, and proven techniques. *Use case: Starting a TDD loop on a failing test, using a debugging pattern mid-incident, handing off a collaboration checklist.* - [Tabnine](https://www.tabnine.com) - Search, explore, and investigate your team's remote repositories using Tabnine's Context Engine. Enables semantic code search, symbol lookup, file navigation, and OpenAPI spec querying across all indexed repositories. Includes AI coaching to help your team write better code. *Use case: Semantically searching a remote repo, looking up a symbol, asking for a coaching note on a PR.* - [Tabnine Context Engine](https://www.tabnine.com/enterprise-context-engine/) - Context Engine CLI (ctx-cli) as focused skills - guided tenant onboarding, code & knowledge-graph search, service investigation, CVE & SAST triage with ready-to-apply fixes, and coding-guideline checks. *Use case: Onboarding a tenant, walking a service in the knowledge graph, applying a suggested CVE fix.* ## Canvas 2 plugins. - [Docs Canvas](https://cursor.com/marketplace/cursor/docs-canvas) **`C`** - Render documentation - architecture notes, API references, runbooks, and codebase walkthroughs - as a navigable canvas with sections, table of contents, diagrams, and cross-references. *Use case: Opening an architecture note as a canvas, jumping a TOC section, following a cross-reference to a runbook.* - [PR Review Canvas](https://cursor.com/marketplace/cursor/pr-review-canvas) **`C`** - Render PR diffs as interactive canvases organized for reviewer comprehension - groups changes by importance, separates boilerplate from core logic, and highlights tricky or unexpected code. *Use case: Grouping a noisy diff by importance, hiding generated boilerplate, highlighting the unexpected branch.* ## Customer Support 2 plugins. - [Intercom](https://www.intercom.com) **`C`** - Connect to Intercom - search conversations and contacts, look up companies, and manage Help Center articles - via Intercom's official remote MCP server. *Use case: Finding a conversation by customer email, looking up the company record, updating a Help Center article.* - [Plain](https://www.plain.com) - Connect Cursor to Plain - manage support threads, customers, tenants, and help center articles directly from your editor. *Use case: Opening a support thread, attaching it to a tenant, editing the help-center article that should have answered it.* ## Data Analytics 29 plugins. - [Amplitude](https://amplitude.com) - Use Amplitude like an expert - instrument analytics, discover product opportunities, analyze charts, create dashboards, manage experiments, and understand users and accounts. *Use case: Instrumenting a new event, reading a chart that dropped, checking an experiment before a flag flip.* - [Antimetal](https://antimetal.com) - Bring Antimetal's software investigation intelligence into your editor. Triage problems, investigate root causes, and apply remediations without leaving Cursor. *Use case: Triaging a production error, walking the suggested root cause, applying the remediation in the same session.* - [Apify](https://apify.com) - Official Apify agent skills for web scraping, data extraction, and automation. *Use case: Starting a scrape actor, extracting a structured table, checking why a run stopped mid-crawl.* - [Astronomer](https://www.astronomer.io) - Data engineering plugin - warehouse exploration, pipeline authoring, Airflow integration. *Use case: Exploring a warehouse schema, authoring a pipeline, checking an Airflow DAG that missed its slot.* - [AWS Data Analytics](https://aws.amazon.com/big-data/datalakes-and-analytics/) - Data lake, analytics, and ETL workflows with S3 Tables, AWS Glue, and Athena. Covers managed Iceberg tables on S3 Tables, ingestion from JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS), Amazon Redshift, Snowflake, BigQuery, and DynamoDB, AWS Glue Data Catalog inventory and asset. *Use case: Inventorying Glue tables, writing a federated Athena query, checking an S3 Tables Iceberg load.* - [Azure Cosmos DB](https://azure.microsoft.com/en-us/products/cosmos-db) - Access your Azure Cosmos DB accounts and perform tasks like managing databases, querying data, vector search, and schema discovery. *Use case: Listing databases in an account, running a vector search, discovering a container schema.* - [Braintrust](https://www.braintrust.dev) - Connect Cursor to Braintrust for AI-powered access to your projects, experiments, and evaluation logs. *Use case: Opening an experiment, reading evaluation logs, comparing two project runs.* - [Bright Data](https://brightdata.com) - Web search, content extraction, structured data, and browser automation powered by Bright Data's web intelligence platform. *Use case: Searching the live we … ## Source & license This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code. - **Author:** [rdmgator12](https://github.com/rdmgator12) - **Source:** [rdmgator12/awesome-grok-bot-plugins](https://github.com/rdmgator12/awesome-grok-bot-plugins) - **License:** CC0-1.0 Install and usage instructions live in the source repository linked above. ## Pricing - **Free** — Free ## Security capabilities Automated source analysis of v0.1.0 — what this tool can access: - **Network access:** no - **Filesystem access:** no - **Shell / process execution:** no - **Environment & secrets:** no - **Dynamic code execution:** no *"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.* ## Versions - **0.1.0** — security scan: passed — Imported from the upstream source. ## Links - Listing page: https://agentstack.voostack.com/l/mcp-rdmgator12-awesome-grok-bot-plugins - Seller: https://agentstack.voostack.com/s/rdmgator12 - Browse the marketplace: https://agentstack.voostack.com/browse --- Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.