# How to connect Particl to Grok Bot ```json { "title": "How to connect Particl to Grok Bot", "toolkit": "Particl MCP", "toolkit_slug": "particl_mcp", "framework": "Grok Bot", "framework_slug": "grok-bot", "url": "https://composio.dev/toolkits/particl_mcp/framework/grok-bot", "markdown_url": "https://composio.dev/toolkits/particl_mcp/framework/grok-bot.md", "updated_at": "2026-11-08T06:01:15.255Z" } ``` ## Introduction Grok is xAI's assistant, and its bot builder lets you create a personal agent that holds context, runs skills, and connects to the apps you already use through plugins. This guide explains how to connect Particl to a Grok bot using Composio Connect, which handles OAuth, token refresh, and reliability so you do not have to. You add Composio as a plugin, authenticate once, then ask your bot to work with Particl in plain language. ## Also integrate Particl MCP with - [ChatGPT](https://composio.dev/toolkits/particl_mcp/framework/chatgpt) - [Claude Cowork](https://composio.dev/toolkits/particl_mcp/framework/claude-cowork) - [Hermes](https://composio.dev/toolkits/particl_mcp/framework/hermes-agent) - [Atomic Agent](https://composio.dev/toolkits/particl_mcp/framework/atomic-agent) ## TL;DR Composio exposes 1,500+ apps to your Grok bot through a single connection, so you get: - Connect to 1,500+ apps with on-demand tool loading, so you do not fill your context window with unnecessary tool definitions. - Use programmatic tool calling through a remote workbench, letting the model write its own code to handle complex tool chaining. This reduces back-and-forth for frequent tool calls. - Handle large tool responses outside the model context to keep conversations lean. ## Connect Particl MCP to Grok Bot ### Connecting Particl to Grok Bot Once Grok Bot is set up, you connect Particl entirely from its interface, and the whole flow takes under a minute. ### Set up Grok Bot Get access. Grok Bot is included with Cursor Ultra, Cursor Premium Teams, and SuperGrok Heavy. Get the desktop app for macOS or Windows from [x.ai/bot](https://x.ai/bot) and sign in. An iPhone companion app is also available, and your bots sync across devices. Create a bot. Pick a suggested role or define your own, then give it a short name, one primary job, and a short description of how it should work. Focused bots work best, because a clear role gives the bot more useful context over time. ### Connect Particl ### 1. Add the Composio plugin Click the button. The Composio listing on x.ai opens and launches Grok Bot for you. If the app does not open on its own, click Add to Grok Bot. [Add to Grok Bot](https://x.ai/bot/plugin/32661537) Grok Bot opens the Composio plugin, showing its connector and skills. Click Add. ### 2. Authenticate Go to the Installed section and click the Composio entry. You'll see its connector and skills listed. Click Authenticate. You'll be taken to the Composio consent screen. Review the access it requests and click Authorize. Composio handles the OAuth handshake for you, so you never touch API keys or tokens. ### 3. Connect your Particl account Back in the chat, ask your bot to connect to Particl or give it any Particl task. For example, ask it to: - "List competitors' pricing for Product X" - "Show sales estimates for Company Acme" - "Retrieve recent marketing spend trends for Acme" It will prompt you to authenticate and authorize access. That's it. Composio's tools are now available in your Grok bot, and your Particl account is ready to use. ## What is Grok Bot? Grok is xAI's assistant, available as a chat interface and a bot builder for creating personal agents that run skills and connect to external apps. With Composio Connect, your Grok bot can securely access apps like Particl through MCP without you sharing account credentials directly with the agent. ## What is the Particl MCP server, and what's possible with it? The Particl MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Particl account. It provides structured and secure access to authorized market intelligence, so your agent can research companies, analyze products and pricing, review sales estimates, and examine marketing activity on your behalf. - Company and competitor research: Have your agent search for companies, retrieve company details, and explore their product catalogs. - Market and sales analysis: Direct your agent to review market sales, historical sales trends, top-performing companies, and best-selling products. - Product and pricing intelligence: Let the agent analyze market pricing, inspect product details and variants, browse product categories, and compare products by attributes such as brand, material, color, or gender. - Marketing activity research: Instruct your agent to examine promotional events, emails, social posts, ads, SMS messages, homepage screenshots, and aggregated engagement statistics for a company. - Focused asset and account insights: Have your agent retrieve full details for a specific marketing asset and check your remaining export credits. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `PARTICL_MCP_GET_COMPANY_DETAILS` | Get company details | Get detailed information about a specific company. Args: company_id: The Particl company ID (e.g., '1234567') analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 credit per call (not charged if no data is returned). Returns: Company profile including name, domain, country, vertical, start date, product count, whether product-level data exists (has_product_data), and top product categories. The has_product_data field indicates whether the company has product-level data. When has_sales_data is false, sales fields are not populated for this company. When has_pricing_data is false, pricing fields are not populated. | | `PARTICL_MCP_GET_COMPANY_EVENTS` | Get company events | Get promotional events for a company — product launches, sales, restocks, price changes, and discounts — with associated marketing assets and products. Supports pagination. Use search_companies first to find the company_id. Args: company_id: The Particl company ID (e.g., '1234567') - required start_date: Start of date range (ISO format, e.g., '2025-01-01'). Defaults to ~30 days ago. end_date: End of date range (ISO format, e.g., '2025-01-31'). Defaults to ~2 days ago. event_types: Filter by event type(s). Common values: 'Promotion', 'Product Release', 'Special Event', 'Collaboration', 'Restock'. Many other values exist — call without this filter first to discover available types for a company. channels: Filter by marketing channel(s). Options: 'email', 'instagram_post', 'facebook_ads', 'sms', 'homepage_screenshot' page_size: Results per page (default 25, max 100). Set higher to get more results per call. page: Page number (0-indexed, default 0). Increment to get additional pages of results. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 per row returned (e.g., page_size=10 costs up to 10 credits). Returns: List of promotional events with associated marketing assets and products. Includes has_more and total_count for pagination. | | `PARTICL_MCP_GET_COMPANY_MARKETING_ASSETS` | Get company marketing assets | List a company's marketing assets — emails, Instagram posts, Facebook/Meta ads, SMS messages, and homepage screenshots. Supports pagination. Use search_companies first to find the company_id. Args: company_id: The Particl company ID (e.g., '1234567') - required asset_types: Filter by asset type(s). Options: 'email', 'instagram_post', 'facebook_ads', 'sms', 'homepage_screenshot'. Defaults to all types. start_date: Start of date range (ISO format, e.g., '2025-01-01'). Defaults to ~30 days ago. end_date: End of date range (ISO format, e.g., '2025-01-31'). Defaults to ~2 days ago. page_size: Results per page (default 25, max 100). Set to 100 to get up to 100 results in one call. page: Page number (0-indexed, default 0). Increment to get additional pages of results. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 per row returned (e.g., page_size=25 costs up to 25 credits). Returns: List of marketing assets with content, engagement metrics, and metadata. Includes has_more and total_count for pagination. Assets include product_ids when available — use these with get_company_products to look up sales and revenue data for the featured products. | | `PARTICL_MCP_GET_COMPANY_MARKETING_STATS` | Get company marketing stats | Get aggregated marketing engagement statistics for a company — posting frequency by type, average likes, engagement rate, most liked post, and posting hour distribution. Use search_companies first to find the company_id. Args: company_id: The Particl company ID (e.g., '1234567') - required analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Returns: total_assets: total number of marketing assets in the last 30 days assets_by_type: dict of asset counts keyed by type (e.g. {"instagram_post": 42, "email": 10}) engagement_metrics: dict of {avg_likes, avg_comments} keyed by type posting_hours: dict of hour-frequency lists keyed by type estimated_reach: dict of average follower counts keyed by type (e.g. {"instagram_post": 50000.0}) avg_likes: dict of average likes keyed by type (e.g. {"instagram_post": 1200.5}) engagement_rate: dict of engagement rate percentages keyed by type (e.g. {"instagram_post": 4.2}) most_liked_post: dict of most liked post details keyed by type Credits: 1 credit per call (not charged if no data is returned). | | `PARTICL_MCP_GET_COMPANY_PRODUCTS` | Get company products | Deep-dive into a specific company's product catalog. Supports pagination — use page and page_size to retrieve more than the default 25 results. Use search_companies first to find the company_id. Args: company_id: The Particl company ID (e.g., '1234567') - required. Use search_companies to find this. product_type_id: Product type UUID from get_product_types. Pass the product_type_id value, not the name. keyword: Filter by keyword/tag (e.g., 'wool', 'recycled'). Searches product tags only, NOT product titles. Use title_search to search by title. title_search: Search products by title (e.g., 'tank top', 'winter jacket'). Matches against product display title. brand: Filter by brand name min_price: Minimum price filter max_price: Maximum price filter sort_by: Sort by 'sales_revenue' (default), 'sales_volume', 'price', or 'launch_date' sort_direction: 'desc' (default) or 'asc' page_size: Results per page (default 25, max 100). Set to 100 to get up to 100 results in one call. page: Page number (0-indexed, default 0). Increment to get additional pages of results. start_date: Start of sales data aggregation window (ISO format, e.g., '2025-01-01'). Defaults to ~30 days ago. end_date: End of sales data aggregation window (ISO format, e.g., '2025-01-31'). Defaults to today. confidence_threshold: Minimum data confidence score (0-10) for included products. Defaults to 6.0, which filters out products with unreliable sales estimates (e.g., gap-filled or anomalous data). You usually don't need to change this. Lower it (e.g., to 0) only if you're looking for a specific product that isn't appearing in results — it may be hidden due to lower data confidence. Set to 0 to include all products regardless of data quality. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 per row returned (e.g., page_size=25 costs up to 25 credits). Returns: List of products from the specified company with pricing, sales estimates, and metadata. Includes has_more and total_count for pagination. | | `PARTICL_MCP_GET_CREDIT_BALANCE` | Get credit balance | Check your remaining export credits. Credits: Free — no credits charged. Returns: Credit balance including total limit, used, and remaining credits | | `PARTICL_MCP_GET_MARKETING_ASSET_DETAILS` | Get marketing asset details | Get full details of a specific marketing asset — email content, social post with engagement metrics, ad creative with cards, or homepage screenshot. Args: company_id: The Particl company ID (e.g., '1234567') - required asset_id: The asset ID - required analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 credit per call (not charged if no data is returned). Returns: Full asset details including content, engagement metrics, metadata, and product_ids when available. Use product_ids with get_company_products to look up sales and revenue data for the featured products. | | `PARTICL_MCP_GET_MARKET_PRICING_ANALYSIS` | Get market pricing analysis | Get pricing analysis for a market or category. Args: product_type_id: Product type UUID from get_product_types. Pass the product_type_id value, not the name. keyword: Filter by keyword/tag end_date: End of trailing 30-day analysis window (ISO format, e.g., '2025-01-15'). Defaults to ~2 days ago. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 credit per call (not charged if no data is returned). Returns: Pricing summary with average, median, range, and distribution buckets | | `PARTICL_MCP_GET_MARKET_SALES` | Get market sales | Get aggregated market-level sales data with monthly timeseries. Returns total market revenue and volume, plus monthly timeseries showing how the market is trending over time. Use with get_market_top_companies and get_market_top_products for complete market analysis. Args: product_type_id: Product type UUID from get_product_types. Pass the product_type_id value, not the name. keyword: Filter by keyword/tag (e.g., 'sustainable', 'organic') end_date: End of trailing analysis window (ISO format, e.g., '2025-01-15'). Defaults to ~2 days ago. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 credit per call (not charged if no data is returned). Returns: Market sales summary with total revenue/volume and monthly timeseries | | `PARTICL_MCP_GET_MARKET_TOP_COMPANIES` | Get market top companies | Get top-performing companies in a market or category. Supports pagination — use page and page_size to retrieve more than the default 25 results. Args: product_type_id: Product type UUID from get_product_types. Pass the product_type_id value, not the name. keyword: Filter by keyword/tag (e.g., 'luxury', 'athleisure') end_date: End of trailing 30-day analysis window (ISO format, e.g., '2025-01-15'). Defaults to ~2 days ago. page: Page number (0-indexed, default 0). Use with page_size to paginate through results. page_size: Results per page (default 25, max 100). Set to 100 to get up to 100 results in one call. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 per row returned (e.g., page_size=25 costs up to 25 credits). Returns: List of top companies with revenue and sales volume estimates. Includes has_more and total_count for pagination. | | `PARTICL_MCP_GET_MARKET_TOP_PRODUCTS` | Get market top products | Get best-selling products in a market or category. Supports pagination — use page and page_size to retrieve more than the default 25 results. Args: product_type_id: Product type UUID from get_product_types. Pass the product_type_id value, not the name. keyword: Filter by keyword/tag (e.g., 'sustainable', 'organic') end_date: End of trailing 30-day analysis window (ISO format, e.g., '2025-01-15'). Defaults to ~2 days ago. page: Page number (0-indexed, default 0). Use with page_size to paginate through results. page_size: Results per page (default 25, max 100). Set to 100 to get up to 100 results in one call. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 per row returned (e.g., page_size=25 costs up to 25 credits). Returns: List of top products with sales estimates, pricing, and product details. Includes has_more and total_count for pagination. | | `PARTICL_MCP_GET_PRODUCT_BREAKDOWN` | Get product breakdown | Get product data broken down by a specific attribute (color, brand, material, keyword, gender, or location). Useful for understanding product mix — e.g., which colors sell best, which brands dominate, what materials are most popular. Args: company_id: The Particl company ID (e.g., '1234567') - required. Use search_companies to find this. breakdown_type: What to break down by. One of: 'keyword', 'material', 'colors', 'brands', 'gender', 'locations'. product_type_id: Product type UUID from get_product_types to filter by category. keyword: Filter by keyword/tag (e.g., 'sustainable'). Searches product tags only. start_date: Start of date range (ISO format, e.g., '2025-01-01'). Defaults to ~30 days ago. end_date: End of date range (ISO format, e.g., '2025-01-31'). Defaults to today. confidence_threshold: Minimum data confidence score (0-10) for included products. Defaults to 6.0, which filters out products with unreliable sales estimates (e.g., gap-filled or anomalous data). You usually don't need to change this. Lower it (e.g., to 0) only if you're looking for a specific product that isn't appearing in results — it may be hidden due to lower data confidence. Set to 0 to include all products regardless of data quality. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 per row returned. Returns: List of breakdown buckets with name, count, sales_revenue, sales_volume, and pricing | | `PARTICL_MCP_GET_PRODUCT_DETAILS` | Get product details | Get full details for a specific product. Returns comprehensive product information including pricing, brand, gender, ratings, reviews, images, materials, keywords, and category data. Use get_company_products first to find product_ids. Args: company_id: The Particl company ID (e.g., '1234567') - required product_id: The product ID - required. Get this from get_company_products or get_market_top_products. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 credit per call (not charged if no data is returned). Returns: Full product profile with metadata, ratings, and attributes | | `PARTICL_MCP_GET_PRODUCT_TYPES` | Get product types | Browse the product type taxonomy to discover valid categories for filtering. Use the returned product_type_id values in other tools' product_type_id parameter. How to use: 1. Call with no parameters to get root-level categories 2. Pass a product_type_id as parent_product_type_id to see its subcategories 3. Keep drilling deeper until you find the right category 4. Use the chosen product_type_id as the product_type_id filter in other tools Args: parent_product_type_id: Get child categories under this product type. Omit to get root-level categories. Credits: Free — no credits charged. Returns: List of product type categories with product_type_id and name | | `PARTICL_MCP_GET_PRODUCT_VARIANTS` | Get product variants | Get variant-level data for a specific product (colors, sizes, individual pricing and sales). Use get_company_products first to find product_ids. Args: company_id: The Particl company ID (e.g., '1234567') - required product_id: The product ID - required. Get this from get_company_products or get_market_top_products. start_date: Start of sales data window (ISO format, e.g., '2025-01-01'). Defaults to ~30 days ago. end_date: End of sales data window (ISO format, e.g., '2025-01-31'). Defaults to today. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 per row returned. Returns: List of product variants with color, size, pricing, and sales data | | `PARTICL_MCP_GET_SALES_TIMESERIES` | Get sales timeseries | Get historical sales timeseries data for a company or a single product. Returns daily, weekly, or monthly sales data points showing revenue, volume, pricing, and inventory over time. Essential for understanding trends, seasonality, and growth. Pass product_id to get timeseries for a single product, or omit for company-wide data. Args: company_id: The Particl company ID (e.g., '1234567') - required. Use search_companies to find this. product_id: Optional product ID to get timeseries for a single product. Get this from get_company_products or get_market_top_products. product_type_id: Product type UUID from get_product_types to filter by category. keyword: Filter by keyword/tag (e.g., 'sustainable', 'organic'). Searches product tags only. start_date: Start of date range (ISO format, e.g., '2025-01-01'). Defaults to ~30 days ago. end_date: End of date range (ISO format, e.g., '2025-01-31'). Defaults to today. aggregation_type: Time granularity - 'daily', 'weekly', or 'monthly'. Auto-selected if omitted. confidence_threshold: Minimum data confidence score (0-10) for included products. Defaults to 6.0, which filters out products with unreliable sales estimates (e.g., gap-filled or anomalous data). You usually don't need to change this. Lower it (e.g., to 0) only if you're looking for a specific product that isn't appearing in results — it may be hidden due to lower data confidence. Set to 0 to include all products regardless of data quality. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: 1 per data point returned. Returns: Timeseries data points with sales_revenue, sales_volume, avg_current_price, and totals | | `PARTICL_MCP_GET_STARTED` | Get started | Return first-session guidance, sample prompts, and follow-up ideas for new Particl MCP users. Call this when the user is new, asks what they can do with Particl, or seems unsure how to start. Credits: Free — no credits charged. Returns: is_first_time, welcome_message, sample_prompts, suggested_follow_ups, tracked_competitors, and assistant_guidance for presenting options in plain English. | | `PARTICL_MCP_SEARCH_COMPANIES` | Search companies | Search for companies by name or domain. Supports pagination. Args: search: Search term (company name or domain) page_size: Results per page (default 25, max 100). Set higher to get more results per call. page: Page number (0-indexed, default 0). Increment to get additional pages of results. sort_by: Sort results by 'popularity' (default) or 'start_date' country_code: Filter by country code (default 'US'). Common values: 'US', 'CA', 'AU', 'GB'. Pass empty string to search all countries. analysis_goal: Brief summary of the user's research objective for this query. Fill this in based on what the user is trying to learn. Omit if unknown. Credits: Free — no credits charged. Returns: List of matching companies with their basic info. Includes has_more and total_count for pagination. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK Once connected, your Grok bot can access the Particl MCP server through Composio to run the actions you authorize, using plain language in the chat. ## Complete Code None listed. ## Conclusion ### Way Forward Now that Particl is connected, extend your setup by connecting the other apps you already use every day, so your Grok bot can run true cross-app workflows end to end. - Connect Calendar to turn threads into scheduled meetings automatically. - Connect Slack or Teams to post summaries, approvals, and alerts where your team works. - Connect Notion, Linear, Jira, or Asana to convert requests into tickets, tasks, and docs. - Connect Drive, Dropbox, or OneDrive to fetch, file, and share attachments without manual steps. Start with one workflow you do repeatedly, then keep adding apps as you find new handoffs. With everything behind a single connection, your bot can coordinate multiple tools safely and reliably in one conversation. ## How to build Particl MCP Agent with another framework - [ChatGPT](https://composio.dev/toolkits/particl_mcp/framework/chatgpt) - [Claude Cowork](https://composio.dev/toolkits/particl_mcp/framework/claude-cowork) - [Hermes](https://composio.dev/toolkits/particl_mcp/framework/hermes-agent) - [Atomic Agent](https://composio.dev/toolkits/particl_mcp/framework/atomic-agent) ## Related Toolkits - [Firecrawl](https://composio.dev/toolkits/firecrawl) - Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources. - [Tavily](https://composio.dev/toolkits/tavily) - Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research. - [Exa](https://composio.dev/toolkits/exa) - Exa is a data extraction and search platform for gathering and analyzing information from websites, APIs, or databases. It helps teams quickly surface insights and automate data-driven workflows. - [Serpapi](https://composio.dev/toolkits/serpapi) - SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research. - [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management. - [Peopledatalabs](https://composio.dev/toolkits/peopledatalabs) - Peopledatalabs delivers B2B data enrichment and identity resolution APIs. Supercharge your apps with accurate, up-to-date business and contact data. - [Snowflake](https://composio.dev/toolkits/snowflake) - Snowflake is a cloud data warehouse built for elastic scaling, secure data sharing, and fast SQL analytics across major clouds. - [Posthog](https://composio.dev/toolkits/posthog) - PostHog is an open-source analytics platform for tracking user interactions and product metrics. It helps teams refine features, analyze funnels, and reduce churn with actionable insights. - [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters. - [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort. - [AccuWeather](https://composio.dev/toolkits/accu_weather) - AccuWeather is a global weather service providing current conditions, forecasts, MinuteCast precipitation, alerts, and lightning data. Use it for fast, localized forecasts and real-time weather alerts. - [Adafruit IO](https://composio.dev/toolkits/adafruit_io) - Adafruit IO is Adafruit's cloud platform for connected device and IoT project data. It helps you store, visualize, and act on sensor feeds without running your own backend. - [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time. - [Agentql](https://composio.dev/toolkits/agentql) - Agentql is a toolkit that connects AI agents to the web using a specialized query language. It enables structured web interaction and data extraction for smarter automations. - [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions. - [Ahrefs MCP](https://composio.dev/toolkits/ahrefs_mcp) - Ahrefs MCP is Ahrefs' hosted MCP server for SEO data and insights. Use it to access backlinks, organic metrics, keyword research, and competitor analysis. - [Akta](https://composio.dev/toolkits/akta) - Akta is a company intelligence platform providing enrichment, news, and alternative business signals. It helps teams build targeted company lists and enrich data-driven workflows. - [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows. - [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations. - [Amplitude](https://composio.dev/toolkits/amplitude) - Amplitude is a digital analytics platform for product and behavioral data insights. It helps teams analyze user journeys and make data-driven decisions quickly. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Particl MCP? With a standalone Particl MCP server, the agents and LLMs can only access a fixed set of Particl tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Particl and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with Grok Bot? Yes, you can. Grok Bot fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Particl tools. ### Can I manage the permissions and scopes for Particl while using Tool Router? Yes, absolutely. You can configure which Particl scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do. ### How safe is my data with Composio Tool Router? All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Particl data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)