Does Bazel MCP Server require a Bazel binary on the system?
Yes, a Bazel binary must be available. It is usually auto-detected, but the path can be explicitly set via `--bazel_path` or the `MCP_BAZEL_PATH` environment variable.
@MCP-Mirror
Basic information
Mirror of
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"nacgarg_bazel-mcp-server": {
"command": "npx",
"args": [
"-y",
"github:nacgarg/bazel-mcp-server"
]
}
}
}Build specified Bazel targets
Query the dependency graph for targets matching a pattern
Run tests for specified targets
List all available targets in the workspace (requires path parameter, use "//" for all targets)
Fetch external dependencies
Change the Bazel workspace path at runtime
Bazel MCP Server is a local server that exposes functionality of the Bazel build system to MCP-enabled AI agents. It is designed for environments where the command-line tool is absent or the shell has a misconfigured environment preventing Bazel use.
Install and run via npx -y github:nacgarg/bazel-mcp-server or clone the repository and build from source. Configuration can be provided through CLI arguments, environment variables, or a configuration file using keys like --bazel_path, --workspace_path, --workspace_config, and --log_path. The server is invoked automatically by MCP clients such as Cursor (via .cursor/mcp.json) or Claude Desktop.
bazel_build_targetYes, a Bazel binary must be available. It is usually auto-detected, but the path can be explicitly set via `--bazel_path` or the `MCP_BAZEL_PATH` environment variable.
Yes, the `bazel_set_workspace_path` tool allows changing the workspace path at runtime.
The server works with any MCP-compatible client, including Cursor and Claude Desktop. Note that with Cursor Remote SSH sessions, the server runs locally and may not function as expected.
Configuration is resolved in this order: CLI arguments, environment variables, then a configuration file. Key settings include `--bazel_path`, `--workspace_path`, `--workspace_config`, and `--log_path`.
Yes, each tool (except `bazel_set_workspace_path`) supports an `additionalArgs` parameter for passing flags like `--verbose_failures` or `--test_output=all`.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
Hindsight: Agent Memory That Learns

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Open-source MCP to use Blender with any LLM
Comments