MCP for Bazel

Give your coding agent access to build history.

Hermetiq exposes structured build intelligence through MCP so coding agents can inspect a failed build, compare invocations, explain likely causes, and proceed with evidence instead of raw log fragments.

What you can answer

Give an agent scoped build evidence—not permission to guess.

  • Query builds and invocations
  • Inspect targets, tests, and failures
  • Investigate cache and RBE behavior
  • Use with Codex, Claude, and MCP clients
Questions Hermetiq helps answer

Let the agent retrieve the same build record an engineer would inspect.

MCP provides a structured interface to Hermetiq data. The quality of an answer still depends on project access, connected telemetry, and engineer validation.

Latest failure

What failed in the latest recorded build, target, or test, and which evidence supports the answer?

Invocation change

Which recorded inputs, outcomes, timings, or execution conditions differ between two builds?

Cache and RBE context

What cache or remote-execution trend is visible in the connected telemetry?

Data gaps

Which source is missing before the agent can answer the question defensibly?

Integration model

Connect a project, authenticate an MCP client, then ask a scoped question.

Available tools and results depend on the Hermetiq deployment, project permissions, and telemetry connected for that project.

01

Create a project and connect BEP

Establish a real Bazel build record in Hermetiq before asking an agent to investigate it.

02

Configure an MCP client

Connect an authenticated Hermetiq MCP endpoint to a compatible client such as Codex or Claude.

03

Ask, inspect, and validate

Scope the question to a build or comparison, review the returned tool evidence, and validate any recommendation before changing code or infrastructure.

Product evidence

Move from an agent question to the underlying build evidence.

Illustrative MCP-assisted investigation

An explicitly illustrative workflow showing an agent requesting structured build evidence through Hermetiq MCP.

Underlying invocation evidence

Inspect the recorded build comparison behind an agent-assisted explanation instead of relying on prose alone.

Evidence model

Keep the model-facing interface bounded by real project data.

Structured interaction

MCP standardizes discovery and invocation of the tools and resources exposed by a configured server.

Project-scoped results

Hermetiq responses are bounded by authenticated project access and the telemetry retained for that project.

Source-backed answers

Build explanations should point back to the invocation, target, test, profile, action, or infrastructure evidence used.

Client-specific workflow

Available setup and interaction patterns vary by MCP client, Hermetiq deployment, and server version.

Technical references

Verify the underlying telemetry and performance model.

Try it with your builds

Connect a real project, then give your agent build evidence.

Start with one Bazel invocation so every MCP-assisted investigation has an evidence boundary.

Technical review: August 29, 2026 · Verify configuration details against the Bazel and Buildbarn versions deployed in your environment.