Click on "Install 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., "@claude-code-traceparent echo 'testing trace propagation'"
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.
Claude Code が MCP Server へのリクエストに W3C Trace Context を付与するのか検証
bun installRelated MCP server: Echo MCP Server
bun run src/server.ts # http（デフォルト）環境変数 | デフォルト | 説明 |
|
|
|
|
| HTTP モードの待受ポート |
|
| 受信内容を追記するログファイル |
echo ツール引数: message: string
処理: message をエコーバック。_meta / HTTP ヘッダーを解析して traceparent を抽出しデバッグログに残す
bun run src/server.tsOpenTelemetry のトレースを可視化するために Grafana を起動する。
docker run -p 3000:3000 -p 4317:4317 -p 4318:4318 --name lgtm grafana/otel-lgtmclaude# Claude Code 内で確認
> /mcp
> use the echo tool with message "hello"補足：以下のファイルで OpenTelemetry の有効設定と MCP の登録を行っている
.claude/settings.json — MCP 登録の有無や traceparent の伝播設定
.mcp.json — MCP サーバの登録内容
ツール実行後、debug.log / Claude Code のセッション履歴 / Claude Code OTel Traces の突合を確認する
debug.log から trace_id を確認
grafana の Web UI から trace_id で Log や Trace を検索する
grep で Claude Code のセッション履歴ファイルを特定する
trace_id=<YOUR_TRACE_ID>
grep -r $trace_id ~/.claudeサーバ単体の動作だけ確かめたい場合:
# stdio
TP="00-0af7651916cd43dd8448eb211c80319c-b7ad6b7169203331-01"
printf '%s\n%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"cli","version":"0"}}}' \
'{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"echo","arguments":{"message":"hi"},"_meta":{"traceparent":"'"$TP"'"}}}' \
| TRANSPORT=stdio bun run src/server.ts
# HTTP（サーバ起動後）
curl -s -X POST http://localhost:3456/ \
-H 'Content-Type: application/json' \
-H 'Accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"echo","arguments":{"message":"hi"},"_meta":{"traceparent":"'"$TP"'"}}}'This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for verifying EUDI/Talao wallet data via OIDC4VP (pull) for AI agents.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yokonao/claude-code-traceparent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server