Skip to main content
The Spur MCP does more when your AI assistant also has context from your other tools. By connecting MCPs for project management, source control, or communication, your agent can pull in context from across your workflow — and make smarter decisions about what to test, when to test it, and how to interpret results.
This page covers MCP servers that you connect to your own AI assistant. To connect MCP servers to Spur AI inside Spur, see MCP Servers in Spur AI.

GitHub

Connect a GitHub MCP so your agent can read pull requests, commits, and code changes — then match them to the right Spur tests.
Using the Spur MCP alongside GitHub

Example prompts

  • “Run any Spur tests that cover the files changed in this PR”
  • “This commit broke checkout — find the relevant Spur test and show me what failed”
  • “What Spur test coverage do I have for the code in PR #142?”

How it works

1

Agent reads the PR or commit

Your agent uses the GitHub MCP to fetch the changed files, commit messages, or PR description.
2

Agent matches changes to tests

Using the context from GitHub, the agent calls list_tests with a search object (e.g. name_contains or steps_contains) to find Spur tests that cover the affected areas, then reads full detail for the best matches with list_tests(test_id).
3

Agent runs and reports

The agent runs the matching tests with run_tests, then summarizes results — so you know whether your changes are safe before merging.

Jira

Connect a Jira MCP so your agent can read tickets, acceptance criteria, and bug reports — then tie them directly to Spur test runs.
Using the Spur MCP alongside Jira

Example prompts

  • “Run the Spur test that covers Jira ticket SHOP-451”
  • “This Jira bug says checkout is broken — find and run the relevant Spur tests”
  • “Check if I have Spur test coverage for the acceptance criteria in SHOP-302”

How it works

1

Agent reads the Jira ticket

Your agent uses the Jira MCP to fetch the ticket summary, description, and acceptance criteria.
Agent matching Jira ticket to Spur tests
2

Agent matches ticket to tests

The agent calls list_tests with a search object to find Spur tests that match the ticket scope, then reads full detail for candidates with list_tests(test_id) and presents them for you to run.
Agent reporting Spur test results for a Jira ticket
3

Agent runs and reports

The agent runs the matching tests with run_tests, then summarizes the results — so you know which acceptance criteria are passing and which need attention.

Linear

Connect a Linear MCP so your agent can read issues, project context, and cycle priorities — then link them to your Spur test suite.
Using the Spur MCP alongside Linear

Example prompts

  • “Run Spur tests related to the issues in the current sprint”
  • “This Linear issue says the login flow is broken — find and run the matching Spur test”
  • “What Spur test coverage do I have for the issues assigned to me?”

How it works

1

Agent reads the Linear issue

Your agent uses the Linear MCP to fetch issue details, labels, and project context.
2

Agent matches issues to tests

The agent calls list_tests with a search object to find Spur tests that align with the issue scope, then reads full detail for candidates with list_tests(test_id).
3

Agent runs and reports

The agent executes the relevant tests and reports back with results mapped to the Linear issue, so you can update the issue status with confidence.

Other tools

Any MCP that gives your agent context about what changed or what matters pairs well with Spur. The pattern is always the same: the external tool provides context, and Spur provides the testing. Examples of other MCPs that work well alongside Spur:
  • Slack — “Someone reported a bug in #engineering — find and run the relevant Spur test”
  • Notion — “Run Spur tests for the features listed in this Notion spec”
  • GitLab — “Run tests covering the files in this merge request”