Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@build-mcp build the project and fix any compiler errors"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP server that runs a build tool and returns structured compiler errors to an LLM agent in opencode.
The value is in the parser: instead of dumping thousands of lines of noisy
build output into the agent's context, it returns a clean list of
{file, line, severity, message} diagnostics.
build_mcp.py — the MCP server. Exposes build and clean tools.
fake_junkbuild.py — a noisy fake build tool for testing without a real toolchain.
opencode.jsonc — example opencode config registering the server.
requirements.txt — the mcp package.
Related MCP server: Build Runner MCP Server
git clone https://github.com/bpbenpatterson/build-mcp.git
cd build-mcp
python3 -m venv .venv
. .venv/bin/activate
pip install -r requirements.txtpython build_mcp.py --selftestYou should see JSON with "error_count": 3 and structured error objects.
Copy the mcp block from opencode.jsonc into your opencode config
(~/.config/opencode/opencode.jsonc or a project opencode.json), replacing
/absolute/path/to/build-mcp with the path you cloned to. Point
BUILD_CMD at the real build tool, and command at the venv's python.
Then restart opencode and prompt:
use the build-tools tool to build the project, then fix the errorsThe agent will call build, receive the structured diagnostics, and act on them.
Set BUILD_CMD to your real command. The server appends --target <name>
(or --clean --target <name>). If your tool uses different flags, edit
run_build() in build_mcp.py.
Adapt ERROR_RE in build_mcp.py to match your tool's actual error format.
That regex is the part that carries your domain knowledge, and it is what
makes the tool useful.
build has a timeout (BUILD_TIMEOUT_S, default 300s).
No destructive targets are exposed. If you add deploy or similar, put an
approval gate in front of it.
This server cannot be deployed
Stateless TS/JS compiler facts for agents: references, imports, impact. No repo index or OAuth.
Discover software problems, analyze evidence, and create implementation-ready Build plans.
Validate JSON, YAML, XML and CSV with exact line/column errors and silent-corruption warnings.
Structured knowledge base for AI agent solutions. Search, explore, and retrieve build logs.
