Category ยท 17 integrations
MCP tools for agents integrations
These connections run in one direction: your TestingOps agents call an external tool through the Model Context Protocol (MCP) when a task needs it.
An MCP tool gives agents an extra capability, for example reading documentation or searching logs. It does not import data into TestingOps by itself.
Tools that can change data in the external system are subject to the approval settings described on each page.
Compare
How these tools differ
| Tool | What TestingOps does with it | Connection |
|---|---|---|
| BrowserStack | Two roles: an agent tool over MCP that the policy does not block, and a direct Automate runner that the policy switches off. | Execution provider, MCP tool for agents Available with limits |
| Postman | Agents call Postman's hosted MCP server with your Postman API key; separate from importing a collection file into API cases. | MCP tool for agents Available |
| Datadog | Agents query your Datadog US1 organisation through its MCP server with a read-scoped token; other Datadog sites cannot connect yet. | MCP tool for agents Available with limits |
| Grafana Cloud | Agents query your Grafana Cloud stack through Grafana's hosted MCP server after an OAuth sign-in; not for self-hosted Grafana. | MCP tool for agents Available with limits |
| PagerDuty | Agents check incidents and services in your PagerDuty US account with an API key; best used with a read-only key. | MCP tool for agents Available with limits |
| TestMu AI (LambdaTest) | Agents call TestMu AI's MCP server on your account after an OAuth sign-in; an agent tool, not a TestingOps execution provider. | MCP tool for agents Available with limits |
| Supabase | Agents query Supabase through its MCP server in read_only mode with a scoped token: checking data, not seeding it. | MCP tool for agents Available |
| Stripe | Agents call Stripe's MCP server with a sandbox restricted key; the key's permissions, not TestingOps, decide what Stripe allows. | MCP tool for agents Available |
| Airtable | Agents use Airtable bases as live test-data tables; the token's scopes and bases decide the reach, and writes ask first. | MCP tool for agents Available |
| Cloudflare | Agents read your Cloudflare account through its API MCP server with a read-only token, for diagnosis only; they never get around bot protection. | MCP tool for agents Available |
| Context7 | No key: agents query Context7's library documentation directly, and everything it offers is open on connect. | MCP tool for agents Available |
| Microsoft Learn | No key: agents search Microsoft's official documentation and code samples, useful when the application under test is built on Microsoft products. | MCP tool for agents Available |
| AWS Knowledge | No key: agents search AWS documentation and regional availability, useful for systems under test that run on AWS. | MCP tool for agents Available |
| Notion | Agents search and read shared Notion pages live after an OAuth sign-in; every Notion write tool is on an explicit ask-first list. | MCP tool for agents Available with limits |
| monday.com | For teams that track work in monday.com: agents use boards and items over MCP, since monday.com has no built-in TestingOps integration. | MCP tool for agents Available |
| Intercom | Agents read your support conversations as a source of defects and test ideas; read-only by setup, US region only. | MCP tool for agents Available with limits |
| Zapier | Agents reach other apps only through the actions you add to your Zapier MCP server; each call uses two Zapier tasks. | MCP tool for agents Available |
Integrations in this category
BrowserStack
Agents can call BrowserStack's hosted MCP tools; the direct Automate runner is switched off on testingops.ai.
Execution providerMCP tool for agentsAvailable with limitsPostman
Agents can work with the Postman collections, environments and workspaces your API key can see.
MCP tool for agentsAvailableDatadog
Agents can look up Datadog logs, traces, RUM and Synthetics around a failed run (US1 site).
MCP tool for agentsAvailable with limitsGrafana Cloud
Agents can query Loki, Prometheus, dashboards and alerts in your Grafana Cloud stack after you sign in.
MCP tool for agentsAvailable with limitsPagerDuty
Agents can check PagerDuty for an open incident before a failure is filed as a defect (US region).
MCP tool for agentsAvailable with limitsTestMu AI (LambdaTest)
Agents can reach HyperExecute results, SmartUI visual checks and accessibility tools on your TestMu AI account.
MCP tool for agentsAvailable with limitsSupabase
Agents can check test data and read logs in your Supabase projects, read-only.
MCP tool for agentsAvailableStripe
Agents can inspect sandbox payments, customers and disputes with a Stripe restricted key.
MCP tool for agentsAvailableAirtable
Agents can read the test-data tables in the Airtable bases your token allows, and update them with approval.
MCP tool for agentsAvailableCloudflare
Agents can look into zone settings, security rules and Workers logs when test traffic is blocked or fails.
MCP tool for agentsAvailableContext7
Agents can look up current documentation for the software libraries your application uses.
MCP tool for agentsAvailableMicrosoft Learn
Agents can search Microsoft's documentation and code samples for Azure, Dynamics 365, Power Platform and .NET.
MCP tool for agentsAvailableAWS Knowledge
Agents can search AWS documentation and check the regional availability of services and features.
MCP tool for agentsAvailableNotion
Agents can search and read the Notion pages you share, and write pages or comments with approval.
MCP tool for agentsAvailable with limitsmonday.com
Agents can read boards, items and docs and, with approval, add or update items on a bug board.
MCP tool for agentsAvailableIntercom
Agents can read support conversations, contacts and help articles as input for tests and defects (US workspaces).
MCP tool for agentsAvailable with limitsZapier
Agents can run the Zapier actions you enable on your Zapier MCP server, in the apps connected to Zapier.
MCP tool for agentsAvailable
Other categories
Issue trackers, wikis and code
Requirements, work items, documentation and code changes are where test design starts. These connections give TestingOps agents that context and, where supported, a place to report back.
Test management
Keep your test management tool as the system of record. TestingOps can send cases with their steps, bring existing cases into its knowledge base and report run results where the tool supports it.
Design tools
Screens, flows and workshop boards describe the intended behaviour before any code exists. These connections bring that material into the knowledge base that agents write test cases from.
Test execution
TestingOps runs test cases on an execution provider and brings back results, steps and evidence. Which providers a workspace can use is decided by its execution policy.
Low-code platforms
Low-code platforms keep the application as a model: data, screens and logic in a structured form. Reading that model lets agents design tests around what the application actually contains.
Process models (BPMN)
A business process model already describes the paths a case can take. TestingOps turns BPMN 2.0 elements into bounded test scenario candidates for review.
App markets
Store reviews show where real users struggle. TestingOps turns them into insights for the knowledge base: themes, version-level signals and test ideas.
AI model providers
Choose the model provider your agents run on and use your own account and API key.
Connection guides
Use TestingOps from the apps you already work in. These are setup guides: you connect the app to TestingOps, and the app calls TestingOps.
Private networks
Many test environments are only reachable inside a company network. These options let test runs reach them without opening the environment to the internet.