# How to integrate Blazemeter MCP with CrewAI

```json
{
  "title": "How to integrate Blazemeter MCP with CrewAI",
  "toolkit": "Blazemeter",
  "toolkit_slug": "blazemeter",
  "framework": "CrewAI",
  "framework_slug": "crew-ai",
  "url": "https://composio.dev/toolkits/blazemeter/framework/crew-ai",
  "markdown_url": "https://composio.dev/toolkits/blazemeter/framework/crew-ai.md",
  "updated_at": "2026-05-12T10:03:21.344Z"
}
```

## Introduction

This guide walks you through connecting Blazemeter to CrewAI using the Composio tool router. By the end, you'll have a working Blazemeter agent that can start a new performance test on your main project, fetch results from the latest test run, list all test runs for project alpha through natural language commands.
This guide will help you understand how to give your CrewAI agent real control over a Blazemeter account through Composio's Blazemeter MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Blazemeter with

- [OpenAI Agents SDK](https://composio.dev/toolkits/blazemeter/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/blazemeter/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/blazemeter/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/blazemeter/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/blazemeter/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/blazemeter/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/blazemeter/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/blazemeter/framework/cli)
- [Google ADK](https://composio.dev/toolkits/blazemeter/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/blazemeter/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/blazemeter/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/blazemeter/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/blazemeter/framework/llama-index)

## TL;DR

Here's what you'll learn:
- Get a Composio API key and configure your Blazemeter connection
- Set up CrewAI with an MCP enabled agent
- Create a Tool Router session or standalone MCP server for Blazemeter
- Build a conversational loop where your agent can execute Blazemeter 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 Blazemeter MCP server, and what's possible with it?

The Blazemeter MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Blazemeter account. It provides structured and secure access so your agent can perform Blazemeter operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `BLAZEMETER_CONVERT_TRANSACTIONS` | Convert Transactions | Tool to convert transaction files to BlazeMeter DSL format for service virtualization. Use when importing API specifications (Swagger, HAR, YAML) to create virtual service transactions. |
| `BLAZEMETER_CREATE_API_MONITORING_SCHEDULE` | Create API Monitoring Schedule | Tool to create a new schedule for running API monitoring tests. Use when you need to automate test runs at defined intervals after determining the correct cron expression and test or collection ID. |
| `BLAZEMETER_CREATE_MULTI_TEST` | Create Multi Test | Tool to create a new multi-test within a specified project. Use after confirming the project ID. Example: "Create a multi-test named 'load-test' in project 12345." |
| `BLAZEMETER_CREATE_PRIVATE_LOCATION` | Create Private Location | Tool to create a new private location in BlazeMeter. Private locations allow you to run performance tests from your own infrastructure. Use when you need to test internal applications or simulate load from specific geographic regions. Requires valid account and workspace IDs. |
| `BLAZEMETER_CREATE_PRIVATE_LOCATIONS_SERVERS` | Create Private Location Agent | Creates a new agent (server) within a BlazeMeter private location. Use this when you need to add an agent to handle test execution in your private infrastructure. Save the returned agent ID for subsequent private location setup steps. |
| `BLAZEMETER_CREATE_PROJECT` | Create Project | Creates a new project within a BlazeMeter workspace. Projects are containers for organizing performance tests. Requires a valid workspace_id which can be obtained using the GET_WORKSPACES action. Returns the created project with its unique ID, timestamps, and other metadata. |
| `BLAZEMETER_CREATE_SEARCH` | Create Search | Execute a search query against BlazeMeter entities using advanced filtering and sorting. Use when you need to find tests, multi-tests, masters, or other entities with complex criteria like name patterns, date ranges, or workspace filters. |
| `BLAZEMETER_CREATE_TAGS` | Create Tag | Creates a new tag in BlazeMeter for organizing and categorizing resources. Tags can be used in searches and filters to group related assets. Use when you need to create a new tag category with a name and description. |
| `BLAZEMETER_CREATE_TEST` | Create Test | Tool to create a new single test within a specified project. Use when registering a new performance test via API. |
| `BLAZEMETER_CREATE_WORKSPACES_ASSETS` | Create Workspace Asset | Tool to create an asset in a workspace for test data management. Use when you need to create data models, test data, or other assets within a BlazeMeter workspace. Assets are used for organizing and managing test data, configurations, and related resources. |
| `BLAZEMETER_CREATE_WORKSPACES_ASSETS_DEPENDENCIES2` | Create Asset Dependency | Tool to create a dependency relationship between two assets in a BlazeMeter workspace. Use when establishing that one asset depends on another asset. The source asset (aId) will depend on the target asset (targetDepId). This is useful for tracking asset relationships in the BlazeMeter Asset Repository. |
| `BLAZEMETER_CREATE_WORKSPACES_PACKAGES` | Create Workspace Package | Creates a new package within a BlazeMeter workspace. Packages are used for managing and organizing test artifacts and dependencies. Use when you need to create a new package with a specific name, version, and optional dependencies. |
| `BLAZEMETER_CREATE_WORKSPACES_TRANSACTIONS` | Create Workspace Transactions | Tool to create transactions in a BlazeMeter workspace for service virtualization. Use when you need to define mock API behaviors by specifying request matching criteria and response definitions. Transactions allow you to virtualize services and simulate API responses for testing purposes. |
| `BLAZEMETER_DELETE_API_MONITORING_SCHEDULE` | Delete API Monitoring Schedule | Tool to delete a specific test schedule by its ID. Use when you need to remove a scheduled test by its unique schedule identifier. |
| `BLAZEMETER_DELETE_PRIVATE_LOCATION_WORKSPACE` | Delete Private Location Workspace | Tool to remove a workspace from a private location. Use when you need to revoke a workspace's access to a specific private location by providing both the harbor ID and workspace ID. |
| `BLAZEMETER_DELETE_PROJECT` | Delete Project | Tool to delete a specific project by its ID. Use when you need to remove a project from BlazeMeter. If the project contains tests or test reports, use the force parameter to delete it including all contents. |
| `BLAZEMETER_DELETE_TEST_FILE` | Delete Test File | Tool to delete a file from a test. Use when you need to remove an uploaded file asset (JMX script, CSV data, or configuration) from a BlazeMeter test. |
| `BLAZEMETER_DELETE_TESTS` | Delete Tests | Tool to delete a test by its ID. Use when you need to remove a performance test from BlazeMeter. |
| `BLAZEMETER_DELETE_WORKSPACE_ASSET_DEPENDENCY` | Delete Workspace Asset Dependency | Tool to delete a dependency from a workspace's asset repository by its ID. Use when you need to remove a specific asset dependency. |
| `BLAZEMETER_DELETE_WORKSPACES_ASSETS` | Delete Workspace Asset | Tool to delete an asset from a workspace in BlazeMeter's Asset Repository. Use when you need to remove an asset that is no longer needed. This permanently deletes the asset from the workspace. |
| `BLAZEMETER_DELETE_WORKSPACES_ASSETS_DEPENDENCIES` | Delete Workspace Assets Dependencies | Tool to delete asset dependencies by source/target in a workspace. Use when you need to remove dependency relationships between workspace assets. |
| `BLAZEMETER_DELETE_WORKSPACES_LOGS` | Delete Workspace Logs | Tool to delete master test execution logs from a BlazeMeter workspace. Use when you need to remove logs for specific test masters to free up storage space. The operation is irreversible and removes all logs associated with the specified master IDs. |
| `BLAZEMETER_DELETE_WORKSPACES_MANAGERS` | Delete Workspace Managers | Tool to remove managers from a workspace. Use when you need to revoke manager access for one or more users by providing the workspace ID and an array of manager IDs. |
| `BLAZEMETER_DELETE_WORKSPACES_PACKAGES` | Delete Workspace Package | Tool to delete a package from a workspace in the BlazeMeter Asset Repository. Use when you need to remove a package by its workspace and package identifiers. |
| `BLAZEMETER_DUPLICATE_TEST` | Duplicate Test | Tool to duplicate an existing test by its ID. Use when you need to create a copy of a test with all its configuration settings. |
| `BLAZEMETER_EXPORT_PACKAGE` | Export Package | Tool to export a package from BlazeMeter Asset Repository as a zip file. Use when you need to download or backup a package's assets and metadata. |
| `BLAZEMETER_EXPORT_WORKSPACES_PACKAGES` | Export Workspaces Packages | Tool to export multiple packages from a workspace as a zip file. Use when you need to download and bundle multiple test packages for backup, transfer, or sharing purposes. |
| `BLAZEMETER_GENERATE_WORKSPACES_DATAMODELS` | Generate Test Data from Data Model | Tool to generate test data from a data model in Asset Repository. Use when you need to create synthetic test data based on a predefined data model structure. |
| `BLAZEMETER_GENERATE_WORKSPACES_TESTDATA` | Generate Workspace Test Data | Tool to generate synthetic test data on-the-fly without storing in Asset Repository. Use when you need to quickly generate test data based on a data model schema with generator functions. The data model defines entity schemas with properties, data types, and generator function requirements. Generator functions (like randText, regExp, randInt) create realistic synthetic data. Use the GET_GENERATOR_FUNCTIONS action to discover available generator functions and their parameters. |
| `BLAZEMETER_GET_ACCOUNTS` | Get Accounts | Tool to retrieve a list of accounts associated with the authenticated user. Use after confirming valid authentication. |
| `BLAZEMETER_GET_API_MONITORING_SCHEDULE` | Get API Monitoring Schedule | Tool to retrieve details of a specific API monitoring schedule by its ID. Use when you need to inspect the configuration or timing of an existing schedule. |
| `BLAZEMETER_GET_API_MONITORING_SCHEDULES` | Get API Monitoring Schedules | Retrieves a paginated list of API monitoring test schedules. Use to enumerate, review, or manage scheduled test runs. IMPORTANT: At least one of testId, collectionId, workspaceId, or projectId must be provided. Use BLAZEMETER_GET_WORKSPACES or BLAZEMETER_GET_PROJECTS to get valid IDs for filtering. |
| `BLAZEMETER_GET_GENERATOR_FUNCTIONS` | Get Generator Functions | Tool to retrieve all available test data generator functions from BlazeMeter Test Data API. Use when you need to discover what generator functions are available for creating synthetic test data. This action returns a comprehensive list of generator functions organized by category (numeric, text, datetime, logical, CSV, etc.), including function signatures, parameters, return types, descriptions, and usage examples. |
| `BLAZEMETER_GET_GENERATOR_SEEDLISTS` | Get Generator Seed Lists | Tool to retrieve a list of all available seed lists from BlazeMeter Test Data Management API. Use when you need to view available seed list files that contain sample text such as names of countries, persons, streets, banks, months, weekdays, etc., for test data generation. |
| `BLAZEMETER_GET_INFO_HEALTH` | Get Info Health | Tool to retrieve the BlazeMeter service health status. Use when you need to check if the service is operational and healthy. |
| `BLAZEMETER_GET_INFO_VERSION` | Get Info Version | Tool to retrieve BlazeMeter service version information. Returns version details including git branch, commit hash, and build number. Use when you need to check the current version of the BlazeMeter service or verify which build is deployed. |
| `BLAZEMETER_GET_MASTERS_REPORTS_MAIN_SUMMARY` | Get Masters Reports Main Summary | Tool to retrieve request statistics summary for a master test run. Use when you need high-level performance metrics including response times, throughput, error rates, and percentiles for a completed or running test execution. |
| `BLAZEMETER_GET_MULTI_TEST` | Get Multi Test | Tool to retrieve details of a specific multi-test. Use after creating or listing multi-tests when you need full configuration and status. Minimal example: "Get multi-test 12345678 with populated tests." |
| `BLAZEMETER_GET_MULTI_TESTS` | Get Multi Tests | Retrieves a paginated list of multi-tests within a BlazeMeter workspace. Multi-tests allow you to run multiple test configurations together. Use this to list, filter by project, and paginate through available multi-tests. Requires workspaceId (obtain via GET_WORKSPACES). |
| `BLAZEMETER_GET_PRIVATE_LOCATIONS` | Get Private Locations | Tool to retrieve a list of private locations filtered by account or workspace. Use when you need to list available private locations for performance testing. |
| `BLAZEMETER_GET_PROJECT_DETAILS` | Get Project Details | Tool to retrieve detailed information about a specific project by its ID. Use when you need to fetch metadata for a single project including name, description, workspace association, and timestamps. |
| `BLAZEMETER_GET_PROJECTS` | Get Projects | Tool to retrieve a list of projects within a specified workspace. Use when you need to enumerate or page through projects under a given workspace. |
| `BLAZEMETER_GET_REGIONS` | Get Regions | Tool to retrieve a list of all available test regions for API monitoring. Use when you need to identify valid region codes for scheduling tests or determining where tests can run. |
| `BLAZEMETER_GET_SEARCH_METADATA` | Get Search Metadata | Retrieve metadata about searchable entities, fields, relationships, and operators in BlazeMeter's search API. Use when you need to understand available search entities, their fields, relationships between entities, or supported query operators. |
| `BLAZEMETER_GET_SHARED_FOLDERS` | Get Shared Folders | Tool to retrieve a list of shared folders within a specified workspace. Use when you need to list or enumerate shared folders for organizing tests and assets. |
| `BLAZEMETER_GET_TAGS` | Get Tags | Tool to retrieve a list of all tags from BlazeMeter Mock Services API. Use when you need to enumerate or page through tags for service virtualization. |
| `BLAZEMETER_GET_TEST_DETAILS` | Get Test Details | Tool to retrieve complete details of a specific test by its ID. Use when you need full information about a test including configuration, executions, tags, and metadata. |
| `BLAZEMETER_GET_TESTS` | Get Tests | Retrieve a list of performance tests filtered by workspace or project. Either workspaceId or projectId is required. Use this action to list all tests within a specific workspace or project, with support for pagination and sorting. Example: Get all tests in workspace 2225472: {"workspaceId": 2225472, "limit": 10} |
| `BLAZEMETER_GET_TESTS_FILES` | Get Tests Files | Tool to list all files associated with a test. Use when you need to view the files attached to a specific test, such as JMX scripts, CSV data files, or YAML configurations. The download links in the response are valid for 20 minutes. |
| `BLAZEMETER_GET_TEST_VALIDATIONS` | Get Test Validations | Tool to retrieve validation results for a specific test by its ID. Use after uploading or modifying test files to confirm file validation status. |
| `BLAZEMETER_GET_USER` | Get User | Retrieve the authenticated user's profile information including their default project and preferences. This tool fetches details about the currently authenticated BlazeMeter user, including: - Basic profile info (name, email, timezone) - Account status (enabled, roles) - Activity timestamps (created, last login, last access) - Default project and workspace configuration - User preferences and settings No parameters required - returns information based on the authentication credentials used. |
| `BLAZEMETER_GET_USER_ACTIVE_SESSIONS` | Get User Active Sessions | Tool to retrieve the list of active test sessions for the authenticated user. Use when you need to check which performance tests or functional tests are currently running for the user. Returns an empty list if no sessions are active. |
| `BLAZEMETER_GET_USER_INVITES` | Get User Invites | Tool to retrieve pending invites for the authenticated user. Use when checking for workspace or account invitations. |
| `BLAZEMETER_GET_USER_PROJECTS` | Get User Projects | Tool to retrieve all projects belonging to the authenticated user. Use when you need to list projects accessible by the current user across all workspaces. |
| `BLAZEMETER_GET_WORKSPACE_DETAILS` | Get Workspace Details | Tool to retrieve detailed information about a specific workspace by its ID. Use when you need to fetch workspace configuration, owner details, member count, allowances, available locations, and capabilities. |
| `BLAZEMETER_GET_WORKSPACE_PACKAGE` | Get Workspace Package | Tool to retrieve a specific package by its ID from a workspace in the BlazeMeter Asset Repository. Use when you need to fetch detailed information about a package, including its metadata, version, and optionally its dependencies. |
| `BLAZEMETER_GET_WORKSPACES` | Get Workspaces | Tool to retrieve a list of workspaces for a specified account. Use when you need to list or filter workspaces by account, status, or name. |
| `BLAZEMETER_GET_WORKSPACES_ASSETS` | Get Workspace Assets | Tool to retrieve all data models (assets) in a workspace for Test Data Management. Use when you need to list or search for test data assets within a specific workspace. |
| `BLAZEMETER_GET_WORKSPACES_ASSETS2` | Get Workspace Asset By ID | Tool to retrieve a specific asset by ID from the Test Data Management Asset Repository. Use when you need to fetch details of a single asset including metadata, data content, or dependencies. |
| `BLAZEMETER_GET_WORKSPACES_ASSETS_DATA` | Get Workspace Asset Data | Tool to retrieve data from a specific asset in a workspace's asset repository. Use when you need to fetch the actual content/data of an asset stored in BlazeMeter's Asset Repository. |
| `BLAZEMETER_GET_WORKSPACES_ASSETS_DEPENDENCIES` | Get Workspace Assets Dependencies | Tool to retrieve all dependencies for a given workspace with optional filtering criteria. Use when you need to understand asset relationships and dependencies within a workspace. |
| `BLAZEMETER_GET_WORKSPACES_ASSETS_DEPENDENCIES2` | Get Workspace Asset Dependency | Tool to retrieve a specific dependency by ID from a workspace's asset repository. Use when you need to fetch detailed information about a particular dependency asset. |
| `BLAZEMETER_GET_WORKSPACES_ASSETS_DEPENDENCIES3` | Get Asset Dependencies | Tool to retrieve dependencies for a specific asset in a workspace from the BlazeMeter Asset Repository. Use when you need to list dependencies of an asset. |
| `BLAZEMETER_GET_WORKSPACES_DATAMODELS2` | Get Workspace Data Model By ID | Tool to retrieve a specific data model by ID from a workspace in Test Data Management. Use when you need to fetch the schema and details of a particular data model for test data generation. |
| `BLAZEMETER_GET_WORKSPACE_SERVICE_MOCK_TEMPLATE_BY_ID` | Get Virtual Service Template by ID | Tool to get virtual service template details from a specific workspace. Use when you need to retrieve configuration and metadata for a specific service mock template by its ID. |
| `BLAZEMETER_GET_WORKSPACES_PACKAGES` | Get Workspace Packages | Tool to retrieve packages from a BlazeMeter workspace. Use when you need to list or filter packages within a specific workspace using the Asset Repository API. |
| `BLAZEMETER_GET_WORKSPACES_PACKAGES_DEPENDENCIES` | Get Workspace Package Dependencies | Tool to retrieve package dependencies for a specific package in a workspace. Use when you need to list dependencies for a package managed in BlazeMeter's artifact repository. |
| `BLAZEMETER_GET_WORKSPACES_SERVICE_MOCK_TEMPLATES` | Get Workspace Service Mock Templates | Tool to list virtual service templates available in a workspace. Use when you need to retrieve available service mock templates for service virtualization. |
| `BLAZEMETER_GET_WORKSPACES_TRANSACTIONS` | Get Workspace Transactions | Tool to list transactions for virtual services in a workspace. Use when you need to retrieve transactions (request/response pairs) for service virtualization. |
| `BLAZEMETER_GET_WORKSPACES_USERS` | Get Workspace Users | Tool to retrieve a list of users within a specified workspace. Use when you need to enumerate users, filter by roles, or check user status in a workspace. |
| `BLAZEMETER_IMPORT_WORKSPACE_PACKAGE` | Import Workspace Package | Import a package from a ZIP file into a BlazeMeter workspace. Use to upload and deploy test packages, with an optional force parameter to overwrite existing packages with the same name. |
| `BLAZEMETER_LIST_GENERATOR_CARD_ISSUERS` | List Generator Card Issuers | Tool to retrieve a list of available card issuers for test data generation. Use when you need to generate credit card test data and want to know which card issuer types are supported and their valid digit lengths. |
| `BLAZEMETER_PUBLISH_API_DATA` | Publish API Data | Publishes test data through the BlazeMeter Test Data Management API. This tool enables API Publishing to initialize test environments by reading, writing, or deleting data before executing tests. Use when preparing stateful test environments with HTTP requests mapped to data entities. |
| `BLAZEMETER_REGISTER_USER` | Register User | Tool to register a new user account in BlazeMeter. Use when creating a new user registration via API. This endpoint creates a new user with the provided credentials and returns the user details upon successful registration. |
| `BLAZEMETER_START_TEST` | Start Test | Tool to start a preconfigured performance load test. Use when you need to execute a test that has already been created and configured. Returns a masterId that can be used to track test status, stop the test, or retrieve results. |
| `BLAZEMETER_STOP_MASTER` | Stop Master | Gracefully stop a running BlazeMeter test execution (master) by its ID. The stop operation signals test sessions to close gracefully and archive test files. Use this to abort a running performance test. To find the master_id, use GET /masters endpoint filtered by testId or workspaceId. Note: This is a graceful stop - for immediate termination, use the terminate endpoint instead. |
| `BLAZEMETER_STOP_TEST` | Stop Test | Tool to stop all active masters (test executions) for a given test ID. Use when you need to terminate all running sessions associated with a test. For more selective control, use the stop master action with a specific masterId to avoid terminating instances launched by other users. |
| `BLAZEMETER_TERMINATE_USER_ACTIVE_SESSIONS` | Terminate User Active Sessions | Tool to immediately terminate active user sessions in BlazeMeter. Use when you need to forcefully stop running test sessions for the authenticated user. This is an immediate termination action - for graceful shutdown, use the stop endpoint instead. |
| `BLAZEMETER_TERMINATE_WORKSPACES_MASTERS` | Terminate Workspaces Masters | Tool to terminate all running masters in a BlazeMeter workspace. Use when you need to stop all active test executions in a workspace. Set dryRun=true to preview which masters would be terminated without actually stopping them. |
| `BLAZEMETER_UPDATE_API_MONITORING_SCHEDULE` | Update API Monitoring Schedule | Tool to update the configuration of an existing API monitoring schedule. Use when you need to enable or disable a schedule after confirming its ID. |
| `BLAZEMETER_UPDATE_PROJECT` | Update Project | Tool to update an existing BlazeMeter project by its ID. Use when you need to modify the name, description, or workspace association of a project. Only the fields you provide will be updated; all other fields remain unchanged. |
| `BLAZEMETER_UPDATE_TEST` | Update Test | Tool to update details of a specific test by its ID. Use when you need to modify test configuration or name of an existing test after confirming its ID. Example: "Update the test name to 'LoadTest' for test with ID '12345'." |
| `BLAZEMETER_UPDATE_WORKSPACES_ASSETS` | Update Workspace Asset | Tool to update an existing asset in a BlazeMeter workspace. Use when you need to modify asset properties such as name, display name, type, metadata, or data content. All fields are optional - provide only the fields you want to update. The asset is identified by workspace_id and asset_id. |
| `BLAZEMETER_UPDATE_WORKSPACES_ASSETS_DEPENDENCIES` | Update Workspaces Assets Dependencies | Tool to update asset dependencies in a BlazeMeter workspace. Use when you need to define or modify the dependency relationships between assets. The provided dependencies list replaces all existing dependencies for the specified asset. |
| `BLAZEMETER_UPDATE_WORKSPACES_PACKAGES` | Update Workspace Package | Tool to update an existing package in a BlazeMeter workspace. Use when you need to modify package properties such as name, display name, version, or dependencies. The package name field is required even when updating other fields. |
| `BLAZEMETER_UPDATE_WORKSPACES_PACKAGES_DEPENDENCIES` | Update Workspace Package Dependencies | Tool to update package dependencies for a specific package in a workspace. Use when you need to add, modify, or remove dependencies for a package managed in BlazeMeter's artifact repository. |
| `BLAZEMETER_UPDATE_WORKSPACES_SERVICE_MOCK_TEMPLATES` | Update Workspace Service Mock Template | Tool to update a virtual service template configuration (Service Virtualization). Use when you need to modify settings like name, description, live system configuration, endpoint preferences, or request handling behavior for an existing virtual service template. |
| `BLAZEMETER_UPDATE_WORKSPACE_USER` | Update Workspace User | Tool to update a user's role and status within a BlazeMeter workspace. Use when you need to change a user's permissions (tester, manager, or viewer) or enable/disable their access. Only ONE role should be assigned per user. Requires valid workspace and user IDs. |
| `BLAZEMETER_UPLOAD_TEST_FILES` | Upload Test Files | Upload a file asset (script, data file, or configuration) to a BlazeMeter test. Use after creating a test via CREATE_TEST to attach JMX scripts, CSV data files, YAML Taurus configs, or other test resources before execution. |
| `BLAZEMETER_UPLOAD_WORKSPACES_ASSETS_DATA` | Upload Workspace Asset Data | Tool to upload asset data to a BlazeMeter workspace. Use when you need to upload CSV, JSON, or other data files to workspace assets for test data or configuration. |
| `BLAZEMETER_VALIDATE_TEST` | Validate Test | Tool to validate a specific test by its ID. Use after creating or updating a test to ensure its configuration is valid. |
| `BLAZEMETER_VALIDATE_WORKSPACES_ASSETS` | Validate Workspace Asset | Tool to validate a data model asset in a workspace for test data management. Use when you need to verify that a data model configuration is correct and passes validation rules before using it in tests. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Blazemeter MCP server is an implementation of the Model Context Protocol that connects your AI agent to Blazemeter. It provides structured and secure access so your agent can perform Blazemeter 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 Blazemeter 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 Blazemeter 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 Blazemeter 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 Blazemeter

**What's happening:**
- You create a Blazemeter only session through Composio
- Composio returns an MCP HTTP URL that exposes Blazemeter tools
```python
composio_client = Composio(api_key=COMPOSIO_API_KEY)
session = composio_client.create(user_id=COMPOSIO_USER_ID, toolkits=["blazemeter"])

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=["blazemeter"],
)
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 Blazemeter through Composio's Tool Router. The agent can perform Blazemeter 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 Blazemeter MCP Agent with another framework

- [OpenAI Agents SDK](https://composio.dev/toolkits/blazemeter/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/blazemeter/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/blazemeter/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/blazemeter/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/blazemeter/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/blazemeter/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/blazemeter/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/blazemeter/framework/cli)
- [Google ADK](https://composio.dev/toolkits/blazemeter/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/blazemeter/framework/langchain)
- [Vercel AI SDK](https://composio.dev/toolkits/blazemeter/framework/ai-sdk)
- [Mastra AI](https://composio.dev/toolkits/blazemeter/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/blazemeter/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.
- [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.
- [Bolt iot](https://composio.dev/toolkits/bolt_iot) - Bolt IoT is a platform for building and managing IoT projects with cloud-based device control and monitoring. It makes connecting sensors and actuators to the internet seamless for automation and data insights.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Blazemeter MCP?

With a standalone Blazemeter MCP server, the agents and LLMs can only access a fixed set of Blazemeter tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Blazemeter 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 Blazemeter tools.

### Can I manage the permissions and scopes for Blazemeter while using Tool Router?

Yes, absolutely. You can configure which Blazemeter 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 Blazemeter data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)