Blazemeter for AI agents
BlazeMeter is a continuous testing platform where engineering teams create, run, and analyze performance and functional tests for web and mobile applications before release. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Blazemeter.
Kick off a load test
Create and run a test or multi-test against a project to check how an application handles traffic.
Require approval before deleting tests
Flag a request to delete tests or a project as destructive so a team member confirms before removal.
Check a test's asset dependencies
Look up which workspace assets and packages a test depends on before duplicating or exporting it.
92 Blazemeter actions, graded by risk.
Every Blazemeter action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
47Look things up. Allowed by default.
- blazemeter.get_tagsGet Tags
- blazemeter.get_userGet User
- blazemeter.get_testsGet Tests
- blazemeter.get_regionsGet Regions
- blazemeter.get_accountsGet Accounts
- blazemeter.get_projectsGet Projects
- blazemeter.get_multi_testGet Multi Test
- blazemeter.get_workspacesGet Workspaces
- blazemeter.get_info_healthGet Info Health
- blazemeter.get_multi_testsGet Multi Tests
- blazemeter.get_tests_filesGet Tests Files
- blazemeter.get_info_versionGet Info Version
- blazemeter.get_test_detailsGet Test Details
- blazemeter.get_user_invitesGet User Invites
- blazemeter.get_user_projectsGet User Projects
- blazemeter.get_shared_foldersGet Shared Folders
write
32Create and change things. Allow, or ask the user first.
- blazemeter.create_tagsCreate Tag
- blazemeter.create_testCreate Test
- blazemeter.update_testUpdate Test
- blazemeter.create_searchCreate Search
- blazemeter.create_projectCreate Project
- blazemeter.update_projectUpdate Project
- blazemeter.create_multi_testCreate Multi Test
- blazemeter.update_workspace_userUpdate Workspace User
- blazemeter.create_private_locationCreate Private Location
- blazemeter.create_workspaces_assetsCreate Workspace Asset
- blazemeter.update_workspaces_assetsUpdate Workspace Asset
- blazemeter.create_workspaces_packagesCreate Workspace Package
- blazemeter.update_workspaces_packagesUpdate Workspace Package
- blazemeter.create_api_monitoring_scheduleCreate API Monitoring Schedule
- blazemeter.create_workspaces_transactionsCreate Workspace Transactions
- blazemeter.update_api_monitoring_scheduleUpdate API Monitoring Schedule
destructive
13Delete, cancel or archive. Ask first, or deny outright.
- blazemeter.delete_testsDelete Tests
- blazemeter.delete_projectDelete Project
- blazemeter.delete_test_fileDelete Test File
- blazemeter.delete_workspaces_logsDelete Workspace Logs
- blazemeter.delete_workspaces_assetsDelete Workspace Asset
- blazemeter.delete_workspaces_managersDelete Workspace Managers
- blazemeter.delete_workspaces_packagesDelete Workspace Package
- blazemeter.delete_api_monitoring_scheduleDelete API Monitoring Schedule
- blazemeter.delete_private_location_workspaceDelete Private Location Workspace
- blazemeter.delete_workspace_asset_dependencyDelete Workspace Asset Dependency
- blazemeter.delete_workspaces_assets_dependenciesDelete Workspace Assets Dependencies
- blazemeter.terminate_workspaces_mastersTerminate Workspaces Masters
- blazemeter.terminate_user_active_sessionsTerminate User Active Sessions
Blazemeter in three steps.
- 01Your users connect BlazemeterThey add their Blazemeter username and password on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Tag” can wait for the user, and “delete Tests” can be denied outright.
- 03Any agent can actYour agent calls Blazemeter through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('blazemeter', { read: 'allow', write: 'ask', // create_tags destructive: 'deny', // delete_tests }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Blazemeter connects.
Users add their Blazemeter username and password on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Blazemeter connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- Username and password
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Blazemeter from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Blazemeter and Arc0, answered.
Can I use Blazemeter with Claude, ChatGPT or Cursor?
Yes. Connect Blazemeter to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Blazemeter actions you allow.
How do users connect Blazemeter?
Users add their Blazemeter username and password on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Blazemeter actions can my agent take?
92 in total: 47 read, 32 write and 13 destructive, such as “create Tag”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in Blazemeter?
Yes. Actions like “delete Tests” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call Blazemeter too?
Yes. The same Blazemeter connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Blazemeter into your agent.
Your users connect Blazemeter once, under your brand. Your agent gets 92 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan