# How to integrate Grafbase MCP with CrewAI ```json { "title": "How to integrate Grafbase MCP with CrewAI", "toolkit": "Grafbase", "toolkit_slug": "grafbase", "framework": "CrewAI", "framework_slug": "crew-ai", "url": "https://composio.dev/toolkits/grafbase/framework/crew-ai", "markdown_url": "https://composio.dev/toolkits/grafbase/framework/crew-ai.md", "updated_at": "2026-05-12T10:14:17.775Z" } ``` ## Introduction This guide walks you through connecting Grafbase to CrewAI using the Composio tool router. By the end, you'll have a working Grafbase agent that can retrieve the latest audit log entry, delete a specific api key by id, get the current federated graph schema through natural language commands. This guide will help you understand how to give your CrewAI agent real control over a Grafbase account through Composio's Grafbase MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved. ## Also integrate Grafbase with - [OpenAI Agents SDK](https://composio.dev/toolkits/grafbase/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/grafbase/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/grafbase/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/grafbase/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/grafbase/framework/codex) - [OpenClaw](https://composio.dev/toolkits/grafbase/framework/openclaw) - [Hermes](https://composio.dev/toolkits/grafbase/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/grafbase/framework/cli) - [Google ADK](https://composio.dev/toolkits/grafbase/framework/google-adk) - [LangChain](https://composio.dev/toolkits/grafbase/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/grafbase/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/grafbase/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/grafbase/framework/llama-index) ## TL;DR Here's what you'll learn: - Get a Composio API key and configure your Grafbase connection - Set up CrewAI with an MCP enabled agent - Create a Tool Router session or standalone MCP server for Grafbase - Build a conversational loop where your agent can execute Grafbase operations ## What is CrewAI? CrewAI is a powerful framework for building multi-agent AI systems. It provides primitives for defining agents with specific roles, creating tasks, and orchestrating workflows through crews. Key features include: - Agent Roles: Define specialized agents with specific goals and backstories - Task Management: Create tasks with clear descriptions and expected outputs - Crew Orchestration: Combine agents and tasks into collaborative workflows - MCP Integration: Connect to external tools through Model Context Protocol ## What is the Grafbase MCP server, and what's possible with it? The Grafbase MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, and more directly to your Grafbase account. It provides structured and secure access to your GraphQL API management, so your agent can perform actions like enabling or disabling MCP, managing API keys, retrieving schemas, and working with audit logs on your behalf. - Enable or disable MCP server: Instantly activate or turn off the Model Context Protocol for your Grafbase project, all by agent command. - API key management: Let your agent securely delete existing API keys to control and rotate access as needed. - Schema and federation management: Retrieve federated graph schemas or remove unwanted schemas for streamlined development workflows. - Audit log retrieval: Fetch specific audit log entries, giving your agent the power to surface key changes or events in your Grafbase environment. - Extension and server configuration cleanup: Delete extension configurations or obsolete MCP server setups to keep your backend lean and secure. ## Supported Tools | Tool slug | Name | Description | |---|---|---| | `GRAFBASE_ADD_ZITADEL_REDIRECT` | Add Zitadel Redirect URI | Add a redirect URI to Zitadel OAuth configuration in Grafbase. Use when you need to register a new redirect URI for OAuth flows with Zitadel identity provider. | | `GRAFBASE_ASSIGN_TEAM_ROLE` | Assign Team Role | Tool to assign a role to a team member in Grafbase. Use this when you need to change a team member's role between MEMBER and ADMIN. ADMIN role grants team management privileges including adding/removing members and changing roles. | | `GRAFBASE_DELETE_API_KEY` | Delete Grafbase API Key | Delete an existing Grafbase API key (access token) by ID. Use after confirming the key ID via the List API Keys action. This action permanently revokes the API key's access. | | `GRAFBASE_DELETE_AUDIT_LOG` | Delete Grafbase Audit Log | Tool to delete a specific Grafbase audit log entry. IMPORTANT: Grafbase does not expose a public API to delete audit logs. Audit logs are read-only compliance records retained for 90 days and can only be exported as CSV from the Grafbase Dashboard. This action validates connectivity to the Grafbase API and returns an informative response about this limitation. | | `GRAFBASE_DELETE_EXTENSION` | Delete Extension | Tool to delete a Grafbase extension configuration by its unique ID. Note: Grafbase extensions are primarily configured via grafbase.toml configuration file and WebAssembly modules, not through a REST API. This action attempts to delete via the API endpoint if it exists; otherwise, it returns guidance on how to remove extensions via configuration. Use this action when you need to programmatically attempt to remove an extension configuration, understanding that the operation may require manual configuration changes if the API endpoint is not available. | | `GRAFBASE_DELETE_MCP_SERVER` | Delete MCP Server | Tool to delete a Grafbase MCP server configuration by its unique ID. Note: Grafbase MCP is primarily configured via grafbase.toml configuration file, not through a REST API. This action attempts to delete via the API endpoint if it exists; otherwise, it returns guidance on how to disable MCP via configuration. Use this action when you need to programmatically attempt to remove an MCP server configuration, understanding that the operation may require manual configuration changes if the API endpoint is not available. | | `GRAFBASE_DELETE_SCHEMA` | Delete Grafbase Subgraph | Tool to delete a subgraph from a Grafbase federated graph. Use this when you need to remove a subgraph from the schema registry. The operation can be run as a dry run first to check if deletion would cause composition errors in the federated graph. Required: account_slug, subgraph_name Optional: branch (defaults to 'main'), graph_slug, message, dry_run | | `GRAFBASE_DELETE_SCHEMA_CHECK` | Delete Schema Check | Attempt to delete a schema check from the Grafbase platform. IMPORTANT LIMITATION: The Grafbase Platform API does not support deleting schema checks. Schema checks are immutable audit records that provide a historical trail of schema validations. They cannot be deleted through the API. This action will verify the schema check exists and return an informative response indicating that deletion is not supported by the Grafbase API. If you need to manage schema checks, consider: - Using the 'List Schema Checks' action to view existing checks - Using the 'Get Schema Check' action to retrieve details of a specific check - Schema checks are automatically created via 'grafbase check' CLI command or API | | `GRAFBASE_DELETE_TEAM` | Delete Grafbase Team | Tool to delete a team from the Grafbase organization. Use when removing a team that is no longer needed. This action permanently removes the team and its associated permissions. | | `GRAFBASE_DISABLE_MCP` | Disable MCP Server | Disable the Model Context Protocol (MCP) server for a Grafbase project. MCP enables AI agents to query your GraphQL APIs using natural language. Use this action when you need to turn off MCP access to your API. Note: In most Grafbase deployments, MCP is configured via grafbase.toml (setting [mcp].enabled = false). This action attempts to disable MCP via API if the endpoint supports it, otherwise returns guidance for configuration-based disabling. | | `GRAFBASE_ENABLE_MCP` | Enable Grafbase MCP Server | Enable the Model Context Protocol (MCP) server on a Grafbase gateway. MCP allows AI tools (like Cursor, Windsurf, VS Code) to explore and query your GraphQL API using natural language. This tool attempts to enable MCP via the gateway API. Note: MCP is typically enabled via gateway configuration (grafbase.toml with [mcp].enabled = true). If the API endpoint is not supported or the gateway is unreachable, this tool returns guidance for manual configuration. Use this when you need to activate MCP support on a Grafbase gateway. | | `GRAFBASE_GET_AUDIT_LOG` | Get Grafbase Audit Log | Tool to retrieve a specific Grafbase audit log entry by searching organization activity. Note: Grafbase does not expose a direct API to fetch individual audit log entries by ID. This action queries organization member activity via the GraphQL API and attempts to find a matching entry based on the provided log_id (which can be a timestamp, user ID, or action type). For full audit log access, use the CSV export feature in the Grafbase dashboard (Settings > Audit Logs) which is available to organization owners and admins. | | `GRAFBASE_GET_EXTENSION_BY_NAME` | Get Extension by Name | Tool to retrieve a Grafbase extension by its name. Returns detailed information including the extension's ID, name, versions, and ownership details. Use this when you need to look up an extension by name rather than ID. | | `GRAFBASE_GET_EXTENSION_VERSION_BY_NAME_AND_VERSION` | Get Extension Version By Name And Version | Tool to retrieve details of a specific Grafbase extension version by name and version. Use when you need to query information about a particular version of an extension, including its creation date and license. | | `GRAFBASE_GET_FEDERATED_SCHEMA` | Get Federated Schema | Retrieves the composed federated graph schema from Grafbase in SDL format. Use this to inspect the unified schema after all subgraph schemas have been composed. Returns the full GraphQL SDL including all types, queries, mutations, and subscriptions. Requires at least one federated graph with published subgraphs to return a schema. | | `GRAFBASE_GET_INVITATION` | Get Grafbase Invitation | Tool to retrieve details about a specific Grafbase invitation by ID. Use when you need to check the status, email, or creation date of an invitation. | | `GRAFBASE_GET_NOTIFICATIONS_INBOX_MESSAGES` | Get Notifications Inbox Messages | Tool to retrieve notifications inbox messages for the authenticated Grafbase user. Returns all notification messages with counts of total and unread notifications. Use when you need to check for new notifications or see notification history. | | `GRAFBASE_GET_SCHEMA_CHECK` | Get Grafbase Schema Check | Retrieve details of a specific schema check by its ID. This tool fetches comprehensive information about a schema validation check, including error details, git commit information, and approval status. Requires account_slug and graph_slug to identify the graph. Use the check_id from list_schema_checks to retrieve specific check details. | | `GRAFBASE_GET_SUBGRAPH_SCHEMA` | Get Subgraph Schema | Retrieves the GraphQL SDL schema for a specific subgraph by name. Use GRAFBASE_LIST_SUBGRAPHS first to discover available subgraph names. Returns the full schema definition including types, queries, mutations, and subscriptions. | | `GRAFBASE_LIST_API_KEYS` | List API Keys | List all API keys (access tokens) for the authenticated Grafbase user. Uses the Grafbase Management API to retrieve access tokens with pagination support. | | `GRAFBASE_LIST_AUDIT_LOGS` | List Grafbase Audit Logs | Tool to list audit logs for Grafbase organizations. Audit logs track organization member activity including graph management, team operations, access control changes, and configuration updates. Note: Grafbase audit logs are retained for 90 days. Currently, the primary method to access audit logs is via CSV export from the Grafbase dashboard. This action attempts to query organization activity via the GraphQL API and returns available data or an informative response about API limitations. | | `GRAFBASE_LIST_EXTENSIONS` | List Extensions | Tool to list all extensions configured for a Grafbase project. Returns extensions from the project's configuration. Use to discover what extensions are installed in your Grafbase gateway. | | `GRAFBASE_LIST_MCP_SERVERS` | List MCP Servers | Check MCP server configuration status for a Grafbase gateway. Grafbase MCP servers are configured via grafbase.toml files, not through a dynamic API. This tool checks if the MCP endpoint is accessible and provides configuration guidance. Use this tool when you need to: - Check if MCP is enabled on a Grafbase gateway - Get the MCP endpoint URL for a gateway - Understand how to configure MCP for Grafbase | | `GRAFBASE_LIST_SCHEMA_CHECKS` | List Grafbase Schema Checks | List schema checks for a Grafbase graph. This tool retrieves the history of schema validation checks that have been run against a specific graph. Schema checks help detect breaking changes before deploying schema updates. Requires account_slug and graph_slug to identify the target graph. Supports cursor-based pagination using first/after or last/before parameters. | | `GRAFBASE_LIST_SCHEMAS` | List Grafbase Schemas | Tool to list all schemas in the Grafbase schema registry. In Grafbase, the schema registry tracks published subgraphs in federated graphs. Each schema entry represents a subgraph with its name, endpoint URL, and associated graph/branch. | | `GRAFBASE_LIST_SUBGRAPHS` | List Grafbase Subgraphs | Tool to list published subgraphs in your Grafbase federated graphs. Use this to discover all subgraphs, their names, and endpoint URLs across your organizations. Optionally filter by branch name (e.g., 'main', 'dev'). | | `GRAFBASE_MARK_NOTIFICATIONS_AS_READ` | Mark Notifications as Read | Tool to mark Grafbase notifications as read. Use when you need to update the read status of one or more notifications in your notification inbox. | | `GRAFBASE_REMOVE_GRAPH_OWNER` | Remove Graph Owner | Tool to remove an owner from a Grafbase graph. Use when you need to revoke ownership or access rights for a user or team on a specific graph. | ## Supported Triggers None listed. ## Creating MCP Server - Stand-alone vs Composio SDK The Grafbase MCP server is an implementation of the Model Context Protocol that connects your AI agent to Grafbase. It provides structured and secure access so your agent can perform Grafbase operations on your behalf through a secure, permission-based interface. With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster. ## Step-by-step Guide ### 1. Prerequisites Before starting, make sure you have: - Python 3.9 or higher - A Composio account and API key - A Grafbase connection authorized in Composio - An OpenAI API key for the CrewAI LLM - Basic familiarity with Python ### 1. Getting API Keys for OpenAI and Composio OpenAI API Key - Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) and create an API key. You'll need credits to use the models, or you can connect to another model provider. - Keep the API key safe. Composio API Key - Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs). - Navigate to your API settings and generate a new API key. - Store this key securely as you'll need it for authentication. ### 2. Install dependencies **What's happening:** - composio connects your agent to Grafbase via MCP - crewai provides Agent, Task, Crew, and LLM primitives - crewai-tools[mcp] includes MCP helpers - python-dotenv loads environment variables from .env ```bash pip install composio crewai crewai-tools[mcp] python-dotenv ``` ### 3. Set up environment variables Create a .env file in your project root. What's happening: - COMPOSIO_API_KEY authenticates with Composio - USER_ID scopes the session to your account - OPENAI_API_KEY lets CrewAI use your chosen OpenAI model ```bash COMPOSIO_API_KEY=your_composio_api_key_here USER_ID=your_user_id_here OPENAI_API_KEY=your_openai_api_key_here ``` ### 4. Import dependencies **What's happening:** - CrewAI classes define agents and tasks, and run the workflow - MCPServerHTTP connects the agent to an MCP endpoint - Composio will give you a short lived Grafbase MCP URL ```python import os from composio import Composio from crewai import Agent, Task, Crew from crewai_tools import MCPServerAdapter import dotenv dotenv.load_dotenv() COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set") ``` ### 5. Create a Composio Tool Router session for Grafbase **What's happening:** - You create a Grafbase only session through Composio - Composio returns an MCP HTTP URL that exposes Grafbase tools ```python composio_client = Composio(api_key=COMPOSIO_API_KEY) session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["grafbase"]) url = session.mcp.url ``` ### 6. Initialize the MCP Server **What's Happening:** - Server Configuration: The code sets up connection parameters including the MCP server URL, streamable HTTP transport, and Composio API key authentication. - MCP Adapter Bridge: MCPServerAdapter acts as a context manager that converts Composio MCP tools into a CrewAI-compatible format. - Agent Setup: Creates a CrewAI Agent with a defined role (Search Assistant), goal (help with internet searches), and access to the MCP tools. - Configuration Options: The agent includes settings like verbose=False for clean output and max_iter=10 to prevent infinite loops. - Dynamic Tool Usage: Once created, the agent automatically accesses all Composio Search tools and decides when to use them based on user queries. ```python server_params = { "url": url, "transport": "streamable-http", "headers": {"x-api-key": COMPOSIO_API_KEY}, } with MCPServerAdapter(server_params) as tools: agent = Agent( role="Search Assistant", goal="Help users search the internet effectively", backstory="You are a helpful assistant with access to search tools.", tools=tools, verbose=False, max_iter=10, ) ``` ### 7. Create a CLI Chatloop and define the Crew **What's Happening:** - Interactive CLI Setup: The code creates an infinite loop that continuously prompts for user input and maintains the entire conversation history in a string variable. - Input Validation: Empty inputs are ignored to prevent processing blank messages and keep the conversation clean. - Context Building: Each user message is appended to the conversation context, which preserves the full dialogue history for better agent responses. - Dynamic Task Creation: For every user input, a new Task is created that includes both the full conversation history and the current request as context. - Crew Execution: A Crew is instantiated with the agent and task, then kicked off to process the request and generate a response. - Response Management: The agent's response is converted to a string, added to the conversation context, and displayed to the user, maintaining conversational continuity. ```python print("Chat started! Type 'exit' or 'quit' to end.\n") conversation_context = "" while True: user_input = input("You: ").strip() if user_input.lower() in ["exit", "quit", "bye"]: print("\nGoodbye!") break if not user_input: continue conversation_context += f"\nUser: {user_input}\n" print("\nAgent is thinking...\n") task = Task( description=( f"Conversation history:\n{conversation_context}\n\n" f"Current request: {user_input}" ), expected_output="A helpful response addressing the user's request", agent=agent, ) crew = Crew(agents=[agent], tasks=[task], verbose=False) result = crew.kickoff() response = str(result) conversation_context += f"Agent: {response}\n" print(f"Agent: {response}\n") ``` ## Complete Code ```python from crewai import Agent, Task, Crew, LLM from crewai_tools import MCPServerAdapter from composio import Composio from dotenv import load_dotenv import os load_dotenv() GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY") COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY") COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID") if not GOOGLE_API_KEY: raise ValueError("GOOGLE_API_KEY is not set in the environment.") if not COMPOSIO_API_KEY: raise ValueError("COMPOSIO_API_KEY is not set in the environment.") if not COMPOSIO_USER_ID: raise ValueError("COMPOSIO_USER_ID is not set in the environment.") # Initialize Composio and create a session composio = Composio(api_key=COMPOSIO_API_KEY) session = composio.create( user_id=COMPOSIO_USER_ID, toolkits=["grafbase"], ) url = session.mcp.url # Configure LLM llm = LLM( model="gpt-5", api_key=os.getenv("OPENAI_API_KEY"), ) server_params = { "url": url, "transport": "streamable-http", "headers": {"x-api-key": COMPOSIO_API_KEY}, } with MCPServerAdapter(server_params) as tools: agent = Agent( role="Search Assistant", goal="Help users with internet searches", backstory="You are an expert assistant with access to Composio Search tools.", tools=tools, llm=llm, verbose=False, max_iter=10, ) print("Chat started! Type 'exit' or 'quit' to end.\n") conversation_context = "" while True: user_input = input("You: ").strip() if user_input.lower() in ["exit", "quit", "bye"]: print("\nGoodbye!") break if not user_input: continue conversation_context += f"\nUser: {user_input}\n" print("\nAgent is thinking...\n") task = Task( description=( f"Conversation history:\n{conversation_context}\n\n" f"Current request: {user_input}" ), expected_output="A helpful response addressing the user's request", agent=agent, ) crew = Crew(agents=[agent], tasks=[task], verbose=False) result = crew.kickoff() response = str(result) conversation_context += f"Agent: {response}\n" print(f"Agent: {response}\n") ``` ## Conclusion You now have a CrewAI agent connected to Grafbase through Composio's Tool Router. The agent can perform Grafbase operations through natural language commands. Next steps: - Add role-specific instructions to customize agent behavior - Plug in more toolkits for multi-app workflows - Chain tasks for complex multi-step operations ## How to build Grafbase MCP Agent with another framework - [OpenAI Agents SDK](https://composio.dev/toolkits/grafbase/framework/open-ai-agents-sdk) - [Claude Agent SDK](https://composio.dev/toolkits/grafbase/framework/claude-agents-sdk) - [Claude Code](https://composio.dev/toolkits/grafbase/framework/claude-code) - [Claude Cowork](https://composio.dev/toolkits/grafbase/framework/claude-cowork) - [Codex](https://composio.dev/toolkits/grafbase/framework/codex) - [OpenClaw](https://composio.dev/toolkits/grafbase/framework/openclaw) - [Hermes](https://composio.dev/toolkits/grafbase/framework/hermes-agent) - [CLI](https://composio.dev/toolkits/grafbase/framework/cli) - [Google ADK](https://composio.dev/toolkits/grafbase/framework/google-adk) - [LangChain](https://composio.dev/toolkits/grafbase/framework/langchain) - [Vercel AI SDK](https://composio.dev/toolkits/grafbase/framework/ai-sdk) - [Mastra AI](https://composio.dev/toolkits/grafbase/framework/mastra-ai) - [LlamaIndex](https://composio.dev/toolkits/grafbase/framework/llama-index) ## Related Toolkits - [Supabase](https://composio.dev/toolkits/supabase) - Supabase is an open-source backend platform offering scalable Postgres databases, authentication, storage, and real-time APIs. It lets developers build modern apps without managing infrastructure. - [Codeinterpreter](https://composio.dev/toolkits/codeinterpreter) - Codeinterpreter is a Python-based coding environment with built-in data analysis and visualization. It lets you instantly run scripts, plot results, and prototype solutions inside supported platforms. - [GitHub](https://composio.dev/toolkits/github) - GitHub is a code hosting platform for version control and collaborative software development. It streamlines project management, code review, and team workflows in one place. - [Ably](https://composio.dev/toolkits/ably) - Ably is a real-time messaging platform for live chat and data sync in modern apps. It offers global scale and rock-solid reliability for seamless, instant experiences. - [Abuselpdb](https://composio.dev/toolkits/abuselpdb) - Abuselpdb is a central database for reporting and checking IPs linked to malicious online activity. Use it to quickly identify and report suspicious or abusive IP addresses. - [Alchemy](https://composio.dev/toolkits/alchemy) - Alchemy is a blockchain development platform offering APIs and tools for Ethereum apps. It simplifies building and scaling Web3 projects with robust infrastructure. - [Algolia](https://composio.dev/toolkits/algolia) - Algolia is a hosted search API that powers lightning-fast, relevant search experiences for web and mobile apps. It helps developers deliver instant, typo-tolerant, and scalable search without complex infrastructure. - [Anchor browser](https://composio.dev/toolkits/anchor_browser) - Anchor browser is a developer platform for AI-powered web automation. It transforms complex browser actions into easy API endpoints for streamlined web interaction. - [Apiflash](https://composio.dev/toolkits/apiflash) - Apiflash is a website screenshot API for programmatically capturing web pages. It delivers high-quality screenshots on demand for automation, monitoring, or reporting. - [Apiverve](https://composio.dev/toolkits/apiverve) - Apiverve delivers a suite of powerful APIs that simplify integration for developers. It's designed for reliability and scalability so you can build faster, smarter applications without the integration headache. - [Appcircle](https://composio.dev/toolkits/appcircle) - Appcircle is an enterprise-grade mobile CI/CD platform for building, testing, and publishing mobile apps. It streamlines mobile DevOps so teams ship faster and with more confidence. - [Appdrag](https://composio.dev/toolkits/appdrag) - Appdrag is a cloud platform for building websites, APIs, and databases with drag-and-drop tools and code editing. It accelerates development and iteration by combining hosting, database management, and low-code features in one place. - [Appveyor](https://composio.dev/toolkits/appveyor) - AppVeyor is a cloud-based continuous integration service for building, testing, and deploying applications. It helps developers automate and streamline their software delivery pipelines. - [Backendless](https://composio.dev/toolkits/backendless) - Backendless is a backend-as-a-service platform for mobile and web apps, offering database, file storage, user authentication, and APIs. It helps developers ship scalable applications faster without managing server infrastructure. - [Baserow](https://composio.dev/toolkits/baserow) - Baserow is an open-source no-code database platform for building collaborative data apps. It makes it easy for teams to organize data and automate workflows without writing code. - [Bench](https://composio.dev/toolkits/bench) - Bench is a benchmarking tool for automated performance measurement and analysis. It helps you quickly evaluate, compare, and track your systems or workflows. - [Better stack](https://composio.dev/toolkits/better_stack) - Better Stack is a monitoring, logging, and incident management solution for apps and services. It helps teams ensure application reliability and performance with real-time insights. - [Bitbucket](https://composio.dev/toolkits/bitbucket) - Bitbucket is a Git-based code hosting and collaboration platform for teams. It enables secure repository management and streamlined code reviews. - [Blazemeter](https://composio.dev/toolkits/blazemeter) - Blazemeter is a continuous testing platform for web and mobile app performance. It empowers teams to automate and analyze large-scale tests with ease. - [Blocknative](https://composio.dev/toolkits/blocknative) - Blocknative delivers real-time mempool monitoring and transaction management for public blockchains. Instantly track pending transactions and optimize blockchain interactions with live data. ## Frequently Asked Questions ### What are the differences in Tool Router MCP and Grafbase MCP? With a standalone Grafbase MCP server, the agents and LLMs can only access a fixed set of Grafbase tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Grafbase and many other apps based on the task at hand, all through a single MCP endpoint. ### Can I use Tool Router MCP with CrewAI? Yes, you can. CrewAI 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 Grafbase tools. ### Can I manage the permissions and scopes for Grafbase while using Tool Router? Yes, absolutely. You can configure which Grafbase 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 Grafbase data and credentials are handled as safely as possible. --- [See all toolkits](https://composio.dev/toolkits) ยท [Composio docs](https://docs.composio.dev/llms.txt)