arcade-mcp/examples/mcp_servers/telemetry_passback/pyproject.toml
Sankara R. Avula 78c8e6fb99
feat: Add TelemetryPassbackMiddleware for serverExecutionTelemetry capability (#797)
**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.
2026-03-25 15:57:50 -07:00

42 lines
1.2 KiB
TOML

[project]
name = "telemetry-passback"
version = "0.1.0"
description = "SEP-0000 reference implementation: cross-org distributed tracing via MCP serverExecutionTelemetry"
requires-python = ">=3.11"
dependencies = [
"arcade-mcp-server>=1.18.0,<2.0.0",
"mcp>=1.26.0",
"langchain>=1.2.13",
"langchain-community>=0.4.1",
"langchain-openai>=1.1.12",
"langgraph>=1.1.3",
"opentelemetry-api",
"opentelemetry-sdk",
"opentelemetry-exporter-otlp-proto-grpc",
"opentelemetry-exporter-otlp-proto-http",
"opentelemetry-instrumentation-langchain",
"opentelemetry-instrumentation-httpx",
"httpx>=0.28.1",
"python-dotenv>=1.2.2",
"protobuf",
]
[project.optional-dependencies]
dev = [
"pytest>=7.0.0",
"pytest-asyncio>=0.21.0",
"mypy>=1.0.0",
"ruff>=0.1.0",
]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["src/telemetry_passback"]
# Use local arcade-mcp-server (TelemetryPassbackMiddleware is not yet published)
[tool.uv.sources]
arcade-mcp-server = { path = "../../../libs/arcade-mcp-server/", editable = true }
arcade-serve = { path = "../../../libs/arcade-serve/", editable = true }