Support MCP observability for Envoy AI Gateway

[wu-sheng]

Support MCP (Model Context Protocol) observability for Envoy AI Gateway

• If this is non-trivial feature, paste the links/URLs to the design doc.
  • Extends SWIP-10 per review comment requesting MCP metrics support.
  • MCP metrics defined in envoyproxy/ai-gateway mcp_metrics.go.
• Update the documentation to include this new feature.
• Tests(including UT, IT, E2E) are added to verify the new feature.
• If it's UI related, attach the screenshots below.

Changes

MAL rules (new files):

• gateway-mcp-service.yaml — 13 MCP service-level metrics (request CPM/latency/percentile, method CPM, error CPM, initialization latency, capabilities, per-backend breakdown)
• gateway-mcp-instance.yaml — 13 MCP instance-level metrics

LAL rules (modified envoy-ai-gateway.yaml):

• Split into two rules: envoy-ai-gateway-llm-access-log and envoy-ai-gateway-mcp-access-log
• LLM logs: persist error responses (>= 400) and upstream failures only
• MCP logs: persist error responses (>= 400) only
• Both rules tag ai_route_type (llm or mcp) for searchable filtering

Dashboard (modified service + instance JSON):

• Added MCP tab with 9 widgets (service) / 6 widgets (instance): request CPM, latency avg/percentile, error CPM, method CPM, initialization latency, backend breakdown

E2E test (modified):

• Added mcp-server service (tzolov/mcp-everything-server:v3 — MCP reference server with StreamableHttp)
• Added MCP request steps (initialize + tools/list + tools/call)
• Added MCP metric verification cases
• Log query uses ai_route_type=llm tag filter

Config:

• Added ai_route_type to searchableLogsTags in application.yml

• Fixed aigw healthcheck binary path (/app instead of aigw)

• If this pull request closes/resolves/fixes an existing issue, replace the issue number. Closes #.

• Update the CHANGES log.

[Copilot]

Pull request overview

Adds MCP (Model Context Protocol) observability support for Envoy AI Gateway in SkyWalking, extending the existing Envoy AI Gateway (SWIP-10) integration with MCP metrics, dashboards, log tagging/sampling, and E2E verification.

Changes:

• Add new MAL rules to derive MCP service/instance metrics (aggregate, per-method, per-backend, init latency, capabilities).
• Split LAL into LLM vs MCP log rules and tag logs with ai_route_type for filtering; update default searchable log tags.
• Extend dashboards + docs + E2E docker-compose scenario to include an MCP backend and MCP metric verification.

Reviewed changes

Copilot reviewed 12 out of 12 changed files in this pull request and generated 5 comments.

Show a summary per file

File	Description
test/e2e-v2/cases/envoy-ai-gateway/expected/logs.yml	Updates expected log tags to include ai_route_type=llm.
test/e2e-v2/cases/envoy-ai-gateway/envoy-ai-gateway-cases.yaml	Adds MCP metric query cases; filters log query by ai_route_type=llm.
test/e2e-v2/cases/envoy-ai-gateway/e2e.yaml	Adds MCP request steps (initialize/tools) for metric verification.
test/e2e-v2/cases/envoy-ai-gateway/docker-compose.yml	Adds mcp-server service and configures ai-gateway-cli MCP routing; fixes healthcheck path.
oap-server/server-starter/src/main/resources/ui-initialized-templates/envoy_ai_gateway/envoy-ai-gateway-service.json	Adds “MCP” tab/widgets to the service dashboard template.
oap-server/server-starter/src/main/resources/ui-initialized-templates/envoy_ai_gateway/envoy-ai-gateway-instance.json	Adds “MCP” tab/widgets to the instance dashboard template.
oap-server/server-starter/src/main/resources/otel-rules/envoy-ai-gateway/gateway-mcp-service.yaml	New MAL rules for MCP service-level metrics.
oap-server/server-starter/src/main/resources/otel-rules/envoy-ai-gateway/gateway-mcp-instance.yaml	New MAL rules for MCP instance-level metrics.
oap-server/server-starter/src/main/resources/lal/envoy-ai-gateway.yaml	Splits access-log processing into LLM vs MCP rules; adds ai_route_type.
oap-server/server-starter/src/main/resources/application.yml	Adds ai_route_type to default searchableLogsTags.
docs/en/setup/backend/backend-envoy-ai-gateway-monitoring.md	Documents MCP metrics, dashboards, and log filtering/sampling behavior.
docs/en/changes/changes.md	Adds a CHANGES entry for MCP observability support.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

Pull request overview

Copilot reviewed 13 out of 13 changed files in this pull request and generated 2 comments.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[wu-sheng]

@peachisai I updated this part, as the Bar seems not correct visualization for percentile.