bazel_build_target
Build specified Bazel targets
LABSCO SUMMARY
The runtime workspace switch is why it beats a shell alias.
bazel_set_workspace_path means the model can point the server at whichever checkout the question is about, so one configuration entry covers every repository on the machine rather than one per project. additionalArgs keeps the escape hatch open — --test_output=all on a failing test gets you the output that the default summary hides. Set --log_path if your client swallows console logs, which is the usual reason a failure looks like silence.
What it is
A local MCP server that wraps the Bazel command line. It exists for environments where the agent has no usable shell, or where the shell it does have has an environment misconfigured enough that Bazel will not run in it.
What you get
- Targets built and tests run —
bazel_build_target,bazel_test_target - The dependency graph queried for targets matching a pattern —
bazel_query_target - Every target in the workspace listed, taking a path where
//means all of them —bazel_list_targets - External dependencies fetched —
bazel_fetch_dependencies - The workspace path changed at runtime, so one running server can move between checkouts —
bazel_set_workspace_path - An optional
additionalArgson every tool except the workspace switch, for flags like--verbose_failuresor--test_output=all
Requirements
No account and no key — it drives your local Bazel. The npm package name is @nacgarg/bazel-mcp-server (0.1.0) and it runs straight from GitHub with npx -y github:nacgarg/bazel-mcp-server. You usually do not need to configure anything: the Bazel binary is picked up automatically and the workspace can be set at runtime by the model. Where that fails, --bazel_path and --workspace_path take absolute paths, and each has an environment-variable equivalent in MCP_BAZEL_PATH and MCP_WORKSPACE_PATH, with a config file as the third fallback. Because it runs locally, it will not work through Cursor's Remote SSH sessions.
Setup effort
One command — npx -y github:nacgarg/bazel-mcp-server
USE CASES
01
Building from an agent that has no working shell
Trigger the build through the server, so a misconfigured environment in the client's shell stops mattering.
02
Finding out what depends on what
Query the dependency graph for a pattern before changing a target, so the blast radius is known rather than discovered by a broken build.
03
Getting real output from a failing test
Run the test with --test_output=all passed through, instead of reading a summary that omits the reason.
04
Exploring an unfamiliar workspace
List every target under // to see what the repository actually builds before picking one.
05
Moving between repositories in one session
Switch the workspace path at runtime, then build and test in the new checkout without restarting anything.
6 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
bazel_fetch_dependencies
Fetch Bazel external dependencies
bazel_list_targets
List all available Bazel targets under a given path
bazel_query_target
Query the Bazel dependency graph for targets matching a pattern
bazel_set_workspace_path
Set the current Bazel workspace path for subsequent commands
bazel_test_target
Run Bazel tests for specified targets
BEFORE YOU INSTALL
What to know first
Tools you get
6 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Light Standing cost
Rated by the size of the 6 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"bazel-mcp-server": {
"command": "npx",
"args": [
"-y",
"github:nacgarg/bazel-mcp-server"
]
}
}
}npx
TERMINAL
npx -y github:nacgarg/bazel-mcp-server
