Non-diff blockers surface missing Conan, pip/uv, npm, or Docker artifacts and 401/403 auth errors alongside code bugs.
Inspect blocker coverage.triageguard.yml + Multi-CI OIDCDiagnose code bugs & external blockers inside every PRLet’s automate CI failure triage
Compress 20–30 MB failing logs into <2,500 grounded tokens, catch deleted packages or auth errors outside PR diffs, and trigger safe reruns without leaving GitHub.
Connects natively with your CI pipelines, issue trackers, and observability stack ↴
- GitHub Actions
- Jenkins
- CircleCI
- Buildkite
- Azure Pipelines
- GitLab CI
- Jira MCP
- Sentry MCP
- JFrog Artifactory
Productivity
Stop digging through 30 MB CI logs. Pinpoint verified root causes in a single sticky PR comment.
![GitHub PR failing build check alongside a concise triageguard[bot] root-cause comment, suggested memcpy fix, and non-blocking Rerun and Open Revert PR buttons](/assets/marketplace/01-in-pr-diagnosis.png)
![GitHub Checks tab across Azure Pipelines, CircleCI, Buildkite, and Jenkins alongside a triageguard[bot] comment flagging Additional Issues Noted for a missing Conan boost package](/assets/marketplace/05-multi-ci-non-diff-checks.png)

.triageguard.yml MCP Hub: Connect Jenkins, Jira, Sentry, or Artifactory via signed OIDC JWTs.
revert/triage-* PRs protect main.
/mcp: Track hours saved and expose native MCP + Google A2A endpoints.<2,500 tokens
extracted from 20–30 MB CI logs in <0.25s via C-level literal prefix scanning
Webhook Ack SLA
<250ms HTTP 202
Constant-time signature verify + async worker enqueue.
Check Conclusion
Always Neutral
Opt-in 1-click actions (via TRIAGE_PUBLISH_CHECK_RUN) never block green merges.
Interactive .triageguard.yml → PR Preview
Switch presets to inspect validated zero-secret MCP configuration alongside representative PR diagnosis previews (click “View Live PR” for the live bot thread).
1. Commit zero-secret .triageguard.yml
mcp_servers:
jenkins:
url: https://jenkins-mcp.acme.example/mcp
ci_source: jenkins
auth_mode: oidc
capabilities:
get_failure_diagnostics: get_build_failure_cause
rerun_build: trigger_rebuild
jira:
url: https://jira-mcp.acme.example/mcp
auth_mode: oidc
marker_triggers:
- marker: "*"
tool_name: jira_get_issue
arg_name: issue_key
extract_pattern: '([A-Z]+-\d+)'
helix-qac:
url: https://qac-mcp.acme.example/mcp
auto_discover: trueValidated by RepoMCPConfigLoader: strict HTTPS hosts, OIDC-only tokens, and allow_scm_writes=false.
2. Single Sticky PR Diagnosis + Check Run
Root Cause: MISRA C:2012 Rule 11.3 unaligned pointer cast in src/can_bus.c (Line 42) plus missing Conan binary boost/1.86.0@corp/stable.
MCP Diagnostics & Repo AI Skills Consulted (3 OIDC calls)
azure_devops.get_pipeline_failure_cause— fetched static analysis diagnostics via OIDCjira.jira_get_issue— linked ticket blocker from PR branch metadatahelix-qac+AGENTS.md— loadedmisra-c-compliance& prescribed alignedmemcpy()
Previous TriageGuard Diagnoses on this PR (Sticky Update)
1. Enable auto_discover (Read-Only Tool Filter)
mcp_servers:
sentry:
url: https://sentry-mcp.acme.example/mcp
auth_mode: oidc
auto_discover: true
artifactory:
url: https://artifactory-mcp.acme.example/mcp
auto_discover: trueGitHub Actions runs MCP-first when configured and falls back cleanly to GitHub App workflow logs — SCM write tools are stripped automatically.
2. Kernel OOM Diagnosis (INFRA_OOM_TIMEOUT)
Root Cause: Linux kernel OOM killer terminated ld.lld with SIGKILL (Exit 137) during 64-thread LTO linking. Prescribes -DCMAKE_BUILD_PARALLEL_LEVEL=8 or raising container RAM.
MCP Diagnostics & Repo AI Skills Consulted (2 sources)
AGENTS.mdrepo rule matched — LTO link memory budget & parallelism boundsartifactoryread-only check — prebuilt archives intact; zero application logic fault
Previous TriageGuard Diagnoses on this PR (3 seen)
1. Connect External Pipelines via Pluggable Adapter
mcp_servers:
gitlab:
url: https://gitlab-mcp.acme.example/mcp
ci_source: gitlab
auth_mode: oidc
capabilities:
get_failure_diagnostics: get_pipeline_failure
rerun_build: retry_pipeline_job
docker-registry:
url: https://registry-mcp.acme.example/mcp
auto_discover: trueNo third-party CI providers are registered globally by default; configure POST /webhooks/ci/{source} and per-repo .triageguard.yml cleanly.
2. Max-1-Retry Cap + Episodic Failure Memory
Guardrail Action: 1st failure triggered AUTO_RERUN; 2nd failure on the same SHA halts retries (posting PR_COMMENT; non-PR hooks return NO_OP_SUPPRESSED) and flags CHRONIC_FLAKE Candidate — Recommend Test Quarantine.
MCP Diagnostics & Repo AI Skills Consulted (2 sources)
gitlab.get_pipeline_failure— isolated TLS handshake timeout pulling imagedocker-registry— confirmed upstream mirror intermittent 504
Previous TriageGuard Diagnoses on this PR (Attempt 1 logged)
Neutral Check Runs expose 1-click Rerun and Open Revert PR actions inside GitHub without ever blocking green PR merges.
Explore live Demo PRsGuardrails & Live PRs
Automate with hard safety boundaries. Inspect live PR triage in the public TriageGuard-Demo repository.
GitHub Actions + MISRA & Conan
Zero-config Actions compiler defect (#10) plus src/can_bus.c:42 & Conan blocker (#9).
LTO OOM Exit 137
Separates container memory exhaustion from application logic bugs cleanly.
1-Retry Cap & Chronic Flake
Allows 1st rerun, suppresses loops, and flags CHRONIC_FLAKE.
Isolated revert/triage-*
Protects main by opening automated revert PRs for human review.
More Details & Guardrails
Inspect exact architectural guarantees enforced on every webhook delivery.
In-PR Sticky Comments & Non-Blocking Check Runs
- Updates one sticky comment in-place (
<!-- triageguard-sticky-comment -->) without PR comment spam. - Optional neutral Check Runs (
TRIAGE_PUBLISH_CHECK_RUN=true) add [Rerun Failed CI] and [Open Revert PR] buttons without blocking green merges. - Verifier gate checks cited files/lines against logs and added (
+) diff hunks.
Detects Missing Packages, Auth, DNS & Disk Errors Outside Diffs
- Classifies missing Conan, pip/uv, npm/pnpm, Maven/Gradle, APT & Docker 404 artifacts as
CONFIG_DRIFTwithout blaming unrelated PR files. - Surfaces secondary issues (missing packages, 401/403, network/429 timeouts,
No space left on device) under Additional Issues Noted.
Zero-Secret .triageguard.yml MCP & Repo AI Skills
- GitHub Actions works out of the box; connect Jenkins, CircleCI, Buildkite, Azure, GitLab, Jira, or Sentry in
.triageguard.ymlusing 60s signed OIDC JWTs (/.well-known/jwks.json). - Auto-loads
AGENTS.md,CLAUDE.md, and matching.agents/skills/*/SKILL.mdfiles per repo.
Metadata-Only Storage & Read-Only Branch Protection
- Direct pushes to
main,master,production, orreleaseare blocked; automated branches must match^(?:fix|revert)/triage-*. - Raw CI logs, diffs, and LLM prompts stay in memory only—durable storage holds operational metadata only.
Security & Native MCP
Embed zero-trust verification into triage. Short-lived 60s OIDC JWTs, metadata-only persistence, and native IDE integration.
Connect IDE & AI Agents
{
"mcpServers": {
"triageguard": {
"type": "http",
"url": "https://triageguard.dev/mcp"
}
}
}- Native MCP Server: /mcp
JSON-RPC 2.0 log slicer, episodic flake memory, and safe branch validator tools.
- Google A2A Agent Card: /.well-known/agent.json
Machine-readable multi-agent capability discovery and skill descriptors.
- AI Discovery Manifest: /llms.txt
Concise architectural summary and endpoints for automated coding assistants.
Pricing
Start free on public or private repositories. Scale up cleanly with metadata-only durability and dedicated SLAs.
Starter
The essentials for individuals and small teams
per month forever
Install Free Plan50 triages / month
GitHub Actions & sticky PR comments
Max-1-Retry & Episodic Memory
Repo
AGENTS.md/ Skills
Pro Team
Multi-CI orchestration and live ROI observability
per month per org
Request Pro Team ($99/mo)500 triages / month
Multi-CI
.triageguard.ymlOIDC MCPsNative
/mcp& Google A2A cardSlack, Teams & Executive ROI Dashboard
Enterprise & Embedded
Private VPC deployment and custom MCP adapters
per month flat
Contact Sales10,000+ triages & custom quotas
Custom tenant MCP adapters (QAC, Conan)
Self-hosted Azure / Private VPC
Dedicated engineering SLA
Catch failures faster on every branch
Install TriageGuard on your repositories in seconds or inspect real failing PR diagnostics running live right now.