IPMC MCP
IPMC MCP
Ein kleiner, abhängigkeitsfreier MCP-Server für Ansichten zur Aufsicht durch das Apache Incubator PMC.
Er setzt sich zusammen aus:
Podling-Lebenszyklusdaten von
PodlingsMCPCommunity- und Berichtssignalen von
apache-health
Er stellt meinungsbasierte Tools auf Incubator-Ebene bereit, um das IPMC zu unterstützen bei:
der Identifizierung von Podlings, die Aufmerksamkeit benötigen
der Bewertung der Abschlussreife
der Erstellung von Podling-Briefings
der Kennzeichnung von notwendigen Mentoring-Interventionen
der Zusammenfassung von Mustern der Community-Gesundheit über Podlings hinweg
Anforderungen
Python 3.12+
Related MCP server: Podlings MCP
Ausführen
python3 server.pyDer Server verwendet stdio und ist daher dafür vorgesehen, von einem MCP-Client gestartet zu werden.
Installation
python3 -m pip install -e .Für Entwicklungstools:
python3 -m pip install -e .[dev]Beispiel-Konfiguration für den MCP-Client
{
"mcpServers": {
"ipmc": {
"command": "python3",
"args": [
"/Users/justinmclean/IncubatorMCP/server.py",
"--podlings-mcp-repo",
"/Users/justinmclean/PodlingsMCP",
"--health-mcp-repo",
"/Users/justinmclean/HealthMCP",
"--health-source",
"/Users/justinmclean/incubator/tools/health/reports"
]
}
}
}Die Standard-Laufzeitumgebung geht davon aus, dass die zugehörigen Quell-MCP-Repositories und Gesundheitsberichte unter folgenden Pfaden verfügbar sind:
/Users/justinmclean/PodlingsMCP/Users/justinmclean/HealthMCPreports, sofern nicht--health-sourcefestgelegt ist
Tool-Aufrufe können die Quelldatenpfade auch mit podlings_source und health_source überschreiben.
Konfigurieren Sie die MCP-Quellorte und das Verzeichnis für Gesundheitsberichte mit Startargumenten:
--podlings-mcp-repo: Pfad zumPodlingsMCP-Checkout--health-mcp-repo: Pfad zumHealthMCP-Checkout--health-source: Standardverzeichnis für apache-health-Berichte
Testen
python3 -m unittest discover -s tests -vAbdeckung
python3 -m coverage run -m unittest discover -s tests
python3 -m coverage report -mDie Abdeckung ist auf das lokale ipmc-Paket beschränkt, sodass importierte MCPs von Drittanbietern den Bericht nicht verwässern.
Architektur
Siehe docs/architecture.md für das Modullayout, den Laufzeitablauf und die Teststruktur.
Tools
ipmc_watchlist
Gibt Podlings zurück, die basierend auf kombinierten Lebenszyklus- und Gesundheitssignalen am dringendsten die Aufmerksamkeit des IPMC benötigen.
Argumente:
podlings_source: optionale URL oder lokaler Dateipfad fürpodlings.xmlhealth_source: optionales Berichtsverzeichnis für apache-health-Markdown-Berichteas_of_date: optionalesYYYY-MM-DD-Datum für zeitabhängige Ansichtenlimit: optionale maximale Anzahl der Ergebnisseseverity_at_least: optionaler Filter für die Mindestschwereinclude_reasons: optionale Liste von Grundfiltern
graduation_readiness
Bewertet, ob ein Podling für den Abschluss bereit, fast bereit oder noch nicht bereit erscheint.
Argumente:
podling: erforderlicher Podling-Namepodlings_sourcehealth_sourceas_of_dateinclude_evidence: optionaler boolescher Wert, standardmäßig truestrict_mode: optionaler boolescher Wert
podling_brief
Gibt ein auf das IPMC ausgerichtetes Briefing für einen Podling zurück.
Argumente:
podling: erforderlicher Podling-Namepodlings_sourcehealth_sourceas_of_datefocus: optionale Liste von Bereichenbrief_format: optionalsummaryoderdetailed
mentoring_attention_needed
Gibt Podlings zurück, bei denen eine Mentoring-Intervention notwendig erscheint.
Argumente:
podlings_sourcehealth_sourceas_of_datelimit: optionale maximale Anzahl der Ergebnisseurgency_at_least: optionaler Filter für die Mindestdringlichkeitinclude_causes: optionale Liste von Ursachenfiltern
community_health_summary
Gibt eine Zusammenfassung der Community-Gesundheitsmuster über Podlings hinweg auf IPMC-Ebene zurück.
Argumente:
podlings_sourcehealth_sourceas_of_datescope: optionalall_podlings,active_podlingsoderreporting_podlingsgroup_by: optionalnone,risk_band,mentor_loadoderage_bandinclude_examples: optionaler boolescher Wert
Standards
Wenn weggelassen, verwendet
podlings_sourcestandardmäßig die ASFpodlings.xml-URL.Wenn weggelassen, verwendet
health_source--health-sourceoderreports, falls dieses Startargument nicht gesetzt ist.Aufsichtsansichten konzentrieren sich standardmäßig auf aktuelle Podlings.
Die Gesundheitsanalyse bevorzugt das aktuellste verfügbare Zeitfenster in dieser Reihenfolge:
3m,6m,12m,to-date.
Meinungsmodell
Dieser Server hält Quellfakten von abgeleiteten Meinungen getrennt. Risiko- und Bereitschaftsansichten werden abgeleitet aus:
Mentorenabdeckung
Zuverlässigkeit der Berichterstattung
Signalen zur Mentor-Abzeichnung
Community-Aktivität
Sichtbarkeit von Releases
Dauer der Inkubation
Breite der Beteiligung
Die resultierenden Ausgaben sollen das Urteilsvermögen des IPMC unterstützen, nicht ersetzen.
Available Tools
21 toolscommunity_health_summaryC
Return an IPMC-level summary of community health across podlings, including strong patterns, risks, and mentoring-capacity signals.
Inputs: podlings_source, health_source, report_source, mail_source, +5 more.
configure_sourcesA
Set or inspect process-level source defaults so later IPMC tool calls can omit source override arguments.
Inputs: podlings_source, health_source, report_source, mail_source, +3 more.
cross_source_mismatchesB
Return concrete mismatches between cached report narrative and current health or release evidence.
Inputs: podlings_source, health_source, report_source, mail_source, +5 more.
current_podlings_overviewB
Return a factual overview of current Incubator podlings from podlings.xml lifecycle metadata.
Inputs: podlings_source, as_of_date, limit, include_descriptions.
graduation_readinessB
Assess whether a podling appears ready, near ready, or not yet ready for graduation.
Inputs: podling (required), podlings_source, health_source, report_source, +5 more.
ipmc_watchlistA
Return podlings that most need IPMC attention based on combined lifecycle and health signals.
Inputs: podlings_source, health_source, report_source, mail_source, +5 more.
mentoring_attention_neededA
Return podlings where mentoring intervention appears necessary, with urgency and likely causes.
Inputs: podlings_source, health_source, report_source, mail_source, +5 more.
podling_briefB
Return an IPMC-oriented briefing for a single podling, including status, trajectory, and attention areas.
Inputs: podling (required), podlings_source, health_source, report_source, +5 more.
recent_changesC
Return per-podling recent deltas the IPMC should scan, excluding unchanged or static fields.
Inputs: podlings_source, health_source, report_source, mail_source, +4 more.
refresh_mail_cacheC
Refresh cached general@incubator.apache.org message summaries used by IPMC mail evidence tools.
Inputs: mail_source, mail_api_base, mail_timespan, query, +1 more.
refresh_report_cacheB
Refresh cached ASF Incubator report data used by IPMC report-narrative tools.
Inputs: report_source, years, full_history, limit, +2 more.
release_artifact_evidenceB
Return ReleaseMCP artifact, sidecar, cadence, Incubator naming evidence, and optional release-page and GitHub/Docker Hub/PyPI/Maven distribution hints for one podling.
Inputs: podling (required), release_dist_base, release_archive_base, release_max_depth, +6 more.
release_visibilityB
Return release-governance visibility concerns, including no releases and activity/release mismatches.
Inputs: podlings_source, health_source, report_source, mail_source, +5 more.
release_vote_evidenceB
Return MailMCP release vote/result thread evidence for one podling alongside IPMC release visibility signals.
Inputs: podling (required), podlings_source, health_source, report_source, +5 more.
reporting_cohortB
Return current reporting podlings grouped into non-ranked IPMC review buckets: reporting issues, release visibility issues, recent significant changes, and no obvious concerns.
Inputs: podlings_source, health_source, report_source, mail_source, +3 more.
reporting_gapsB
Return podlings with Incubator reporting compliance gaps, excluding activity analysis.
Inputs: podlings_source, health_source, report_source, mail_source, +5 more.
reporting_reliabilityB
Return objective reporting reliability patterns over time, separating one-off late reporting from repeated late or missing reporting.
Inputs: podlings_source, health_source, report_source, mail_source, +5 more.
reporting_scheduleB
Return expected Incubator reporting cadence, due-this-month status, and next expected reporting period from PodlingsMCP.
Inputs: podlings_source, podling, as_of_date, report_month, +2 more.
report_narrative_signalsB
Return report-derived narrative signals such as latest reported issues, recurring issues, low observed mentor sign-off, and release visibility mismatches.
Inputs: podlings_source, health_source, report_source, mail_source, +5 more.
significant_changesC
Return a structured factual subset of recent changes: no 12-month releases, large activity shifts, and newly visible reporting or release transitions.
Inputs: podlings_source, health_source, report_source, mail_source, +5 more.
stalled_podlingsB
Return podlings that match the strict low-delivery, no-release stalled definition.
Inputs: podlings_source, health_source, report_source, mail_source, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 21 tools
Each tool has a clearly defined and distinct purpose, focusing on specific aspects of IPMC oversight such as community health, podling status, releases, reporting, or mentoring. There is no ambiguity between tools.
All tool names follow a consistent pattern of descriptive phrases using underscores (e.g., community_health_summary, graduation_readiness). No mixing of camelCase or other conventions is observed.
With 21 tools, the server covers a broad domain of IPMC responsibilities. While the count is relatively high, each tool addresses a necessary function, and the scope justifies the number.
The tool set provides comprehensive coverage of IPMC information needs, including community health, podling lifecycle, releases, reporting, and mentoring. Minor gaps may exist for direct actions, but the analysis surface is thorough.
Related MCP Connectors
MCP server for VC pitch-deck scoring, thesis-fit matching, and deal-flow management.
MCP server for CertScore.ai public website risk-signal workflows.
Guarded MCP server for agent-readable business truth, provenance, readiness, and discovery.
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
Related MCP Servers
- FlicenseAqualityDmaintenanceA deterministic, network-free MCP server for validating repository release hygiene and version alignment in local projects. It enables automated repository health checks and generates standardized release checklists based on project state.1-
- AlicenseBqualityDmaintenanceAn MCP server for accessing and analyzing Apache Software Foundation Incubator podling data from podlings.xml. It provides tools to query podling metadata, generate statistics, and analyze incubation trends over time.22MIT
- AlicenseAqualityDmaintenanceAn MCP server for querying and analyzing Apache Incubator podling health reports. It provides tools to list, search, and compare podling metrics across different time windows from Apache's health report Markdown files.9MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for comprehensive PyPI package intelligence, providing tools for dependency analysis, security scanning, health scoring, license compliance, and trend tracking.MIT