fix(mcp): report the exception a tool raised when the SDK masks it

[bernatixer]

💡 Motivation and Context

The MCP SDK CI matrix went red on Aug 31 with no repo change. The cause is the repo's rolling exclude-newer = "7 days" quarantine: mcp 2.1.0 (published Aug 24, 19:04 UTC) aged into eligibility at 19:04 UTC, between two runs of the same commit, so the unpinned mcp>=2,<3 leg resolved 2.0.0 in the morning and 2.1.0 in the evening. Three of the four red jobs are fail-fast cancellations of the one real failure.

mcp 2.1 masks unexpected tool exceptions: the dispatch wrapper's message becomes Error executing tool <name> with the original kept only on __cause__ (documented in the SDK at tools/base.py). $mcp_error_message and $mcp_error_type read $exception_list[0], so every unexpected tool failure reported the same masked string and the failures view lost the reason a call failed, which is the one thing these properties exist to carry.

The scalars now read the entry behind the SDK's dispatch wrapper. exceptions_from_error_tuple already records the __cause__ chain, so the original exception is sitting right behind the wrapper; the match requires the type name (ToolError / UnexpectedToolError), the Error executing tool message prefix, and a module from an SDK namespace (mcp., fastmcp.), and it walks every consecutive wrapper because a tool invoking a failing tool is wrapped once per dispatch. A wrapper without a chained cause is kept as is, an application's own exception that merely shares the wrapper's name is kept, and the $exception sibling still carries the full chain, so error-tracking grouping is unchanged.

On mcp 1.x the wrapper includes the original text, so the scalars there change from Error executing tool boom: explode / ToolError to explode / ValueError. The tool name is already its own property on the event.

💚 How did you test it?

• The previously failing gate test (test_instrumented_server_failure_carries_them) passes untouched under every mcp version CI can resolve: 2.0.0 (yesterday's resolution), 2.1.0 (today's), and 2.1.1 (ages in Sep 1, verified with an --exclude-newer override).
• Four tests pin the unwrap through the public paths: a real SDK wrapper with a chained cause yields the cause's message and type while the $exception sibling keeps the wrapper; a wrapper without a cause is kept; an application exception sharing the wrapper's name is kept; and a nested-server test asserts both the inner and outer events report the root cause. The unit tests import the real per-major ToolError classes.
• Revert-proven at each round: against main, the gate test and the unwrap test fail; against the first revision of this PR, both review findings reproduce as failing tests (nested wrappers and the same-named application exception); with the final change, all pass.
• Full posthog/test/mcp suite: 235 passed on the lockfile env (mcp 1.28.1 + fastmcp 3.2.0), 215 passed + 13 skipped on each of mcp 2.0.0, 2.1.0, and 2.1.1.
• ruff format, ruff check, and the CI mypy command (through mypy-baseline filter) pass.
• Redaction covers the unwrapped entry: _sanitize_exception_values maps over every chain entry, not just the first.

📝 Checklist

• I reviewed the submitted code.
• I added tests to verify the changes.
• I updated the docs if needed.
• No breaking change or entry added to the changelog.

If releasing new changes

• Added a changeset under .sampo/changesets/ (hand-written in the sampo add format)

🤖 Agent context

Autonomy: Human-driven (agent-assisted)

Written by Claude Code in a PostHog Desktop session directed by @bernatixer, after tracing why the MCP SDK matrix went red on #906 with a snapshot-only diff. Rejected alternatives: pinning the v2 leg below 2.1 (defeats the gate's purpose and ships masked messages to customers anyway), version-gating the test assertion (accepts the masked string as the product), and raising ToolError in the test (stops exercising the unexpected-exception path customers actually hit). The SDK documents __cause__ as the channel for the original error, so the instrumentation reads it.

The advisory review's two blocking findings (nested double-wrapping, and type-name matching catching application exceptions) were both reproduced first and are fixed in the second commit: the match is gated on the entry's recorded SDK module and traverses consecutive wrappers.

Skills invoked: writing-tests, writing-pr-descriptions.

---

Created with PostHog Desktop

[github-actions]

posthog-python Compliance Report

Date: 2026-09-01 10:03:17 UTC
Duration: 256431ms

✅ All Tests Passed!

111/111 tests passed

---

Capture_V1 Tests

✅ 94/94 tests passed

View Details

Test	Status	Duration
Endpoint And Method.Targets V1 Endpoint	✅	518ms
Endpoint And Method.Does Not Use Legacy Endpoints	✅	511ms
Required Headers.Has Authorization Bearer Header	✅	510ms
Required Headers.Has Content Type Json	✅	511ms
Required Headers.Has Posthog Sdk Info Format	✅	510ms
Required Headers.Has Posthog Attempt Header	✅	511ms
Required Headers.Has Posthog Request Id	✅	511ms
Required Headers.Has Posthog Request Timestamp	✅	510ms
Required Headers.Has User Agent	✅	511ms
Body Format.Body Has Created At And Batch	✅	511ms
Body Format.No Api Key In Body	✅	511ms
Body Format.No Sent At In Body	✅	510ms
Event Format.Event Has Required Root Fields	✅	510ms
Event Format.Event Uuid Is Valid	✅	511ms
Event Format.Event Timestamp Is Rfc3339	✅	510ms
Event Format.Distinct Id Is String	✅	510ms
Event Format.Distinct Id At Root Not Properties	✅	510ms
Event Format.Custom Properties Preserved	✅	510ms
Event Format.Set Properties Preserved	✅	511ms
Event Format.Set Once Properties Preserved	✅	510ms
Event Format.Groups Properties Preserved	✅	510ms
Event Format.Sdk Generates Uuid If Not Provided	✅	510ms
Event Format.Event Has Required Root Fields Batch	✅	514ms
Event Format.Event Uuid Is Valid Batch	✅	514ms
Event Format.Event Timestamp Is Rfc3339 Batch	✅	514ms
Event Format.Distinct Id Is String Batch	✅	514ms
Event Format.Distinct Id At Root Not Properties Batch	✅	514ms
Event Format.Custom Properties Preserved Batch	✅	515ms
Event Format.Set Properties Preserved Batch	✅	515ms
Event Format.Set Once Properties Preserved Batch	✅	513ms
Event Format.Groups Properties Preserved Batch	✅	514ms
Event Format.Sdk Generates Uuid If Not Provided Batch	✅	514ms
Batch Behavior.Multiple Events In Single Batch	✅	518ms
Batch Behavior.Batch Envelope Smoke	✅	515ms
Batch Behavior.Flush With No Events Sends Nothing	✅	507ms
Batch Behavior.Flush At Triggers Batch	✅	1011ms
Batch Behavior.Created At Reflects Batch Creation Time	✅	511ms
Deduplication.Generates Unique Uuids	✅	518ms
Deduplication.Different Events Same Content Different Uuids	✅	513ms
Deduplication.Preserves Uuid On Retry	✅	6519ms
Deduplication.Preserves Timestamp On Retry	✅	6520ms
Deduplication.Preserves Uuid And Timestamp On Batch Retry	✅	6523ms
Deduplication.No Duplicate Events In Batch	✅	519ms
Header Behavior On Retry.Attempt Header Starts At One	✅	510ms
Header Behavior On Retry.Attempt Header Increments On Retry	✅	13527ms
Header Behavior On Retry.Request Id Preserved On Retry	✅	6520ms
Header Behavior On Retry.Different Requests Have Different Request Ids	✅	3019ms
Header Behavior On Retry.Request Timestamp Changes On Retry	✅	6519ms
Response Format Validation.Success Response Has Uuid Keyed Results	✅	511ms
Response Format Validation.Success Response Has Ok For Each Event	✅	513ms
Response Format Validation.Success No Retry After When All Ok	✅	512ms
Response Format Validation.Success Retry After Present When Retry Events	✅	1515ms
Response Format Validation.Success No Retry After When Drop Only	✅	513ms
Response Format Validation.Response Echoes Request Id	✅	510ms
Retry Behavior.Retries On 408	✅	6519ms
Retry Behavior.Retries On 500	✅	6520ms
Retry Behavior.Retries On 503	✅	8519ms
Retry Behavior.Retries On 504	✅	6520ms
Retry Behavior.Retryable Errors Have Retry After	✅	3517ms
Retry Behavior.Respects Retry After On Retryable Error	✅	11521ms
Retry Behavior.Does Not Retry On 400	✅	2514ms
Retry Behavior.Does Not Retry On 401	✅	2513ms
Retry Behavior.Does Not Retry On 402	✅	2513ms
Retry Behavior.Does Not Retry On 413	✅	2514ms
Retry Behavior.Does Not Retry On 415	✅	2513ms
Retry Behavior.Non Retryable Errors Have No Retry After	✅	2513ms
Retry Behavior.Implements Backoff	✅	22537ms
Retry Behavior.Max Retries Respected	✅	22536ms
Partial Batch Handling.Handles 200 Full Success	✅	2511ms
Partial Batch Handling.Handles 200 With All Ok	✅	3515ms
Partial Batch Handling.Does Not Retry Dropped Events	✅	3514ms
Partial Batch Handling.Does Not Retry Limited Events	✅	3516ms
Partial Batch Handling.Prunes Ok Events On Partial Retry	✅	6522ms
Partial Batch Handling.Prunes Dropped Events On Partial Retry	✅	6516ms
Partial Batch Handling.Retries Only Retry Events From Partial	✅	6523ms
Partial Batch Handling.Partial Retry Preserves Uuids	✅	6518ms
Partial Batch Handling.Partial Retry Attempt Header Increments	✅	6521ms
Partial Batch Handling.Partial Retry Request Id Preserved	✅	6521ms
Partial Batch Handling.Respects Retry After On Partial	✅	8519ms
Partial Batch Handling.Unknown Result Treated As Terminal	✅	3517ms
Partial Batch Handling.Mixed Ok Drop Limited No Retry	✅	3520ms
Compression.Sends Gzip Content Encoding	✅	511ms
Compression.No Content Encoding When Disabled	✅	510ms
Compression.Compressed Body Is Decompressible	✅	510ms
Error Handling.Does Not Retry On Unknown 4Xx	✅	2512ms
Event Options.Cookieless Mode Override	✅	510ms
Event Options.Disable Skew Correction Override	✅	510ms
Event Options.Process Person Profile Override	✅	511ms
Event Options.Product Tour Id Override	✅	510ms
Event Options.Unset Options Omitted	✅	510ms
Event Options.Options Override In Batch	✅	513ms
Geoip And Historical Migration.Geoip Disable Injected Into Properties	✅	511ms
Geoip And Historical Migration.Historical Migration Set In Body	✅	510ms
Geoip And Historical Migration.Historical Migration Absent By Default	✅	510ms

Feature_Flags Tests

✅ 17/17 tests passed

View Details

Test	Status	Duration
Request Payload.Request With Person Properties Device Id	✅	11ms
Request Payload.Flags Request Uses V2 Query Param	✅	9ms
Request Payload.Flags Request Hits Flags Path Not Decide	✅	9ms
Request Payload.Flags Request Omits Authorization Header	✅	9ms
Request Payload.Token In Flags Body Matches Init	✅	9ms
Request Payload.Groups Round Trip	✅	9ms
Request Payload.Groups Default To Empty Object	✅	9ms
Request Payload.Disable Geoip False Propagates As Geoip Disable False	✅	9ms
Request Payload.Disable Geoip Omitted Defaults To False	✅	10ms
Request Payload.Flag Keys To Evaluate Contains Only Requested Key	✅	9ms
Request Lifecycle.No Flags Request On Init Alone	✅	3ms
Request Lifecycle.No Flags Request On Normal Capture	✅	510ms
Request Lifecycle.Two Flag Calls Produce Two Remote Requests	✅	14ms
Request Lifecycle.Mock Response Value Is Returned To Caller	✅	9ms
Retry Behavior.Retries Flags On 502	✅	312ms
Retry Behavior.Retries Flags On 504	✅	314ms
Side Effect Events.Get Feature Flag Captures Feature Flag Called Event	✅	512ms

[marandaneto]

Automated advisory code review.