78c8e6fb99
**Implements**: [SEP-2448: server execution telemetry] (https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2448) **Description:** **The Observability Gap (The Problem)** MCP clients propagate trace context to servers, but server-side execution remains a black box. The client sees a single tools/call or resources/read span; everything the server does (auth checks, policy evaluation, API calls, sub-tool invocations) is invisible. In cross-organization deployments, clients and servers use separate observability backends with no shared collector access, making traditional span export useless. <img width="1015" height="450" alt="Screenshot 2026-03-23 at 3 43 21 PM" src="https://github.com/user-attachments/assets/58c817b5-fee6-46a3-9877-d523a25368ad" /> **Server Execution Telemetry (The Solution)** Servers advertise serverExecutionTelemetry and return a curated slice of their execution spans directly in _meta.otel of the response. Clients ingest these verbatim OTLP spans into their own collector, stitching server-side execution into their distributed trace; no shared infrastructure required. The black box becomes transparent. <img width="945" height="574" alt="Screenshot 2026-03-23 at 3 43 44 PM" src="https://github.com/user-attachments/assets/38d97c94-aa73-4e62-9b4e-3264600e5ed0" /> . **Summary:** Implement MCP serverExecutionTelemetry capability that enables cross-organization distributed tracing by returning server-side OpenTelemetry spans to clients inline via _meta.otel.traces. Server-side (middleware): - TelemetryPassbackMiddleware intercepts tools/call and resources/read - ContextVarSpanCollector isolates span collection per-request via ContextVar - Propagates traceparent from client request for distributed trace stitching - Serializes collected spans to verbatim OTLP JSON (resourceSpans format), directly POSTable to /v1/traces - Top-level span filtering by default; full span tree via detailed opt-in - Middleware advertises capabilities via get_capabilities() on the Middleware base class - Provisional API: FutureWarning emitted until SEP-2448 is ratified Client-side (reference agent): - LangChain ReAct agent connects to MCP server via streamable_http_client with OAuth 2.1 - Detects serverExecutionTelemetry capability at initialization - Dynamically wraps discovered MCP tools with traceparent propagation and _meta.otel span request - Ingests returned server spans into Jaeger (OTLP JSON) and Galileo (OTLP protobuf) - Two-act demo: --no-passback (black box) vs default (full server-side visibility) Dependencies: - opentelemetry-api and opentelemetry-sdk added to arcade-mcp-server Bump arcade-mcp-server version to 1.18.0.
47 lines
1.4 KiB
TOML
47 lines
1.4 KiB
TOML
[build-system]
|
|
requires = ["hatchling>=1.25"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[project]
|
|
name = "arcade-mcp-server"
|
|
version = "1.18.0"
|
|
description = "Model Context Protocol (MCP) server framework for Arcade.dev"
|
|
readme = "README.md"
|
|
authors = [{ name = "Arcade.dev" }]
|
|
license = { text = "MIT" }
|
|
classifiers = [
|
|
"Development Status :: 5 - Production/Stable",
|
|
"Intended Audience :: Developers",
|
|
"License :: OSI Approved :: MIT License",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
"Programming Language :: Python :: 3.13",
|
|
]
|
|
requires-python = ">=3.10"
|
|
dependencies = [
|
|
"arcade-core>=4.4.2,<5.0.0",
|
|
"arcade-serve>=3.2.0,<4.0.0",
|
|
"arcade-tdk>=3.6.0,<4.0.0",
|
|
"arcadepy>=1.5.0",
|
|
"pydantic>=2.0.0",
|
|
"fastapi>=0.100.0",
|
|
"uvicorn>=0.30.0",
|
|
"watchfiles>=0.18.0", # included with uvicorn, but listed to be explicit
|
|
"sse-starlette>=2.0.0",
|
|
"starlette>=0.37.0",
|
|
"anyio>=4.0.0",
|
|
"python-dotenv>=1.0.0",
|
|
"pydantic-settings>=2.10.1",
|
|
"joserfc>=1.5.0",
|
|
"httpx>=0.27.0,<1.0.0",
|
|
"opentelemetry-api>=1.20.0",
|
|
"opentelemetry-sdk>=1.20.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = ["pytest>=8.0.0", "pytest-asyncio>=0.23.0", "mypy>=1.0.0", "ruff>=0.1.0"]
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["arcade_mcp_server"]
|