Import an MCP client configuration — three servers a coding assistant uses
A Claude Code .mcp.json listing three Model Context Protocol servers — two
started from a command line and one someone else runs — drafted into Aggrega
files by aggrega import, each server mapped to the realization of how it
runs, and built for Kubernetes.
Import an MCP client configuration walks it step by step: the command, the files it writes and why each line is there, the build, and the servers running. This folder holds each stage of that walkthrough:
| folder or file | what it holds |
|---|---|
source/ | the client configuration, .mcp.json, the .aggrega-config.yaml that makes the folder a workspace, and import-answers.yaml, the name of the Kubernetes Secret the GitHub server’s token is read from |
draft/ | the files aggrega import .mcp.json --target helm wrote, unchanged, release.lock included, and what it printed: stdout.txt on standard output, import.txt on standard error |
In a checkout of the documentation repository, check.sh runs the import
again, compares what it writes and prints with draft/, compares the blocks
the walkthrough quotes with these files, and validates and builds what the
import wrote. It needs the standard-library catalog
(where to get one)
checked out beside this repository, or its directory named in
AGGREGA_CATALOG_DIRS.
Scaffold the example
You can run this example’s import with the commands below, or have your AI assistant run it for you.
Write the example into a new folder named after it:
aggrega scaffold --example import-mcpIt then prints the commands to run next. The first changes into the new folder:
cd import-mcpBuild
The import drafts the Aggrega files beside the project, in source/. It weighs
the project against the standard-library catalog, which the workspace’s default
registry publishes as a signed snapshot: the first import fetches it, verifies
it, keeps it in the workspace’s content cache and names it by its digest in the
record it writes beside the drafts. A workspace that names its own catalog
folders — in AGGREGA_CATALOG_DIRS, or under workspace.catalog_dirs —
imports against those instead. The import reads the Secret’s name from
import-answers.yaml, then pulls what the drafted Release depends on, so the
build follows at once:
cd sourceaggrega import .mcp.json --target helmaggrega build --release release.yamlThe build writes the Kubernetes manifests under dist/helm/; creating the
Secret and applying them is in the walkthrough linked above.
With an AI assistant
An AI assistant set up with Aggrega’s tools can do the same: paste this prompt into it.
Use the Aggrega tools only, and create no folder yourself. If the Workspace folder holds no `import-mcp` folder yet, call the `scaffold` tool once with `example` set to `import-mcp` and no `dir`: it writes the example into a new `import-mcp` folder, whose `source` folder holds what this example imports. Then call the `import` tool with `workspace_root` set to `import-mcp/source`, `source` set to `.mcp.json` and `target` set to `helm`: it reads the answers it needs from `import-answers.yaml` beside `.mcp.json`, writes its drafts into `import-mcp/source` and pulls what they need. Then call the `validate` tool with `workspace_root` set to `import-mcp/source` and `release` set to `release.yaml`, and the `build` tool with `workspace_root` set to `import-mcp/source`, `release` set to `release.yaml` and `write` set to true. Tell me which files the build wrote; they are under `import-mcp/source/dist/`.Test it
With the build applied, forward a local port to the fetch server’s Service and leave the command running:
kubectl port-forward svc/fetch-default 8080:8080From another terminal, ask the server to open a session with MCP’s
initialize request:
curl -sS http://127.0.0.1:8080/mcp \ -H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' \ -d '{"jsonrpc": "2.0", "id": 1, "method": "initialize", "params": {"protocolVersion": "2025-06-18", "capabilities": {}, "clientInfo": {"name": "test-it", "version": "1.0.0"}}}': keepalive
: keepalive
event: messagedata: {"jsonrpc":"2.0","id":1,"result":{"capabilities":{"prompts":{"listChanged":false},"resources":{"listChanged":false,"subscribe":false},"tools":{"listChanged":false}},"protocolVersion":"2025-06-18","serverInfo":{"name":"mcp-fetch","version":"2026.11.11"}}}The walkthrough makes the same call on Docker Compose and to the GitHub server.