Skip to main content
Glama

Mason – der Kontext-Builder für LLMs 👷

npm version CI npm downloads license issues

Mason gibt LLMs eine persistente Karte Ihrer Codebasis, damit sie nicht in jeder Sitzung von Grund auf neu suchen müssen.

Das Problem: Jedes Mal, wenn ein LLM ein neues Gespräch über Ihren Code beginnt, führt es Grep-Befehle aus, liest Dateien und setzt die Architektur zusammen – dabei werden Token für Kontext verschwendet, den es bereits am Vortag verstanden hat. Bei einem Projekt mit 164 Dateien erfordert die Beantwortung der Frage „Welche Funktionen hat diese App?“ das Lesen von mehr als 8 Dateien über mehrere Tool-Aufrufe hinweg.

Masons Lösung: Eine Konzeptkarte, die über Sitzungen hinweg bestehen bleibt. Ein Tool-Aufruf liefert eine Nachschlagetabelle von Funktionen zu Dateien – das LLM weiß genau, wo es suchen muss, ohne zu explorieren.

Gemessenes Ergebnis (deepeval, Claude Sonnet, 164-Dateien-KMP-Projekt):

Frage

Mit Mason

Ohne Mason

Token-Einsparung

Alle Funktionen auflisten

10.258 Tok

31.346 Tok

67%

Datenfluss nachverfolgen

12.010 Tok

15.258 Tok

21%

Plattformen vergleichen

10.897 Tok

19.353 Tok

44%

Onboarding-Ablauf

10.271 Tok

11.432 Tok

10%

Durchschnitt

36%

Gleiche Antwortqualität (0,9/1,0 bei allen Tests, beide Pfade). Reproduktion: bench/.

Schnellstart

claude mcp add mason --scope user -- npx -p mason-context mason-mcp

Starten Sie Claude Code neu und fragen Sie dann: "use mason to analyze this project and create a snapshot."

Das ist alles – Mason analysiert Ihre Codebasis und erstellt eine Konzeptkarte. In der nächsten Sitzung lädt es die Karte, anstatt alles neu zu explorieren.

Related MCP server: ontomics

Funktionsweise

Konzeptkarte

Masons Kernfunktion. Es speichert eine Funktions-zu-Datei-Karte in .mason/snapshot.json, die über Konversationen hinweg erhalten bleibt. Wenn das LLM Ihr Projekt verstehen muss, liest es diese Karte, anstatt Ihre gesamte Codebasis zu durchsuchen:

{
  "features": {
    "home screen": {
      "files": ["HomeScreen.kt", "HomeViewModel.kt", "GetWeatherDataUseCase.kt"]
    }
  },
  "flows": {
    "weather fetch": {
      "chain": ["HomeViewModel.kt", "WeatherRepositoryImpl.kt", "WeatherServiceImpl.kt"]
    }
  }
}

Die Karte wird vom LLM selbst generiert – Mason stellt die Analysetools bereit, und das LLM interpretiert Ihren Code, um zu entscheiden, was die Funktionen und Abläufe sind. Das bedeutet, dass die Karte ein architektonisches Verständnis erfasst, nicht nur Dateiauflistungen.

Erstellen Sie eine, indem Sie Ihren KI-Assistenten bitten: "create a mason snapshot", oder über die CLI:

mason set-llm gemini          # configure a provider (no API key needed)
mason snapshot ~/my-project   # generate concept map
mason snapshot --install-hook # auto-update on every commit

Analyse der Änderungsauswirkungen

Bevor Sie eine Datei bearbeiten, kann Mason Ihnen sagen, was sonst noch betroffen sein könnte. Es kombiniert drei Signale, für die man manuell jeweils mehrere Tool-Aufrufe benötigen würde:

  • Co-Change-Historie – Dateien, die sich historisch gesehen in Git-Commits gemeinsam ändern

  • Referenzen – Dateien, die das Ziel importieren oder namentlich erwähnen

  • Zugehörige Tests – Testdateien, die durch Namenskonventionen mit dem Ziel verknüpft sind

mason impact WeatherRepository.kt -d ~/my-project

Auch als get_impact MCP-Tool verfügbar – fragen Sie Ihren Assistenten: "what would be affected if I changed WeatherRepository?"

Analyse der Git-Historie

Mason aggregiert Hunderte von Commits zu aussagekräftigen Statistiken: Welche Dateien ändern sich am häufigsten (Hot-Files, bei denen Sie vorsichtig sein sollten), welche Verzeichnisse wurden seit Monaten nicht mehr angefasst (potenziell veralteter Code) und welche Commit-Konventionen das Team befolgt. Dies ist die Art von Analyse, für die man manuell Dutzende von git log-Aufrufen benötigen würde.

mason analyze ~/my-project

MCP-Tools

Mason stellt 6 Tools über das Model Context Protocol bereit. Jeder MCP-kompatible Client (Claude Code, Cursor usw.) kann diese verwenden:

Tool

Was es tut

get_snapshot

Lädt die Konzeptkarte – ordnet Funktionen/Abläufe Dateien zu

save_snapshot

Speichert die Konzeptkarte für zukünftige Sitzungen

get_impact

Änderungsauswirkung: Co-Change-Historie, Referenzen, zugehörige Tests

analyze_project

Git-Historie: Commit-Muster, Hot-Files, veraltete Verzeichnisse

full_analysis

Alles-in-einem beim ersten Besuch: Git-Statistiken + Struktur + Code-Beispiele + Test-Map

get_code_samples

Intelligente Dateivorschauen, ausgewählt nach architektonischer Rolle

CLI-Nutzung

Mason funktioniert auch als eigenständige CLI zum Generieren von CLAUDE.md-Dateien und zum Ausführen von Analysen ohne MCP-Client. Konfigurieren Sie einen LLM-Anbieter einmal und verwenden Sie dann jeden beliebigen Befehl:

mason set-llm claude|gemini|ollama|openai  # configure provider
mason generate                # analyze codebase + LLM -> CLAUDE.md
mason analyze                 # git stats only (no LLM needed)
mason impact File.kt          # change impact analysis
mason snapshot                # create/update concept map

Die meisten Anbieter funktionieren ohne API-Schlüssel – claude, gemini und ollama verwenden alle direkt ihre jeweiligen CLIs.

Sicherheit

Was der Snapshot enthält: Funktionsnamen, relative Dateipfade und Ablaufbeschreibungen. Kein Quellcode, keine Geheimnisse oder Geschäftslogik.

Was nicht angefasst wird: Mason respektiert .gitignore (via git ls-files) und verfügt über eine Deny-Liste, die .env, .pem, .key, Anmeldeinformationen und andere sensible Dateien von der Stichprobenentnahme ausschließt. Der Schutz vor Pfad-Traversal stellt sicher, dass der gesamte Dateizugriff innerhalb des Projekt-Roots bleibt.

LLM-Datenfluss: Das Generieren eines Snapshots über die CLI sendet stichprobenartige Dateiinhalte an Ihren konfigurierten LLM-Anbieter – genau so, wie jeder KI-Programmierassistent Ihren Code liest. Verwenden Sie ollama für eine vollständig lokale Generierung. Die MCP-Server-Tools (get_snapshot, get_impact usw.) lesen nur lokale Dateien.

Sprachunterstützung

Mason ist vollständig sprachunabhängig. Es verwendet Dateinamensmuster und Git-Historie anstelle von sprachspezifischem Parsing und funktioniert daher mit jedem Projekt, das Quelldateien und ein Git-Repository hat – TypeScript, Kotlin, Python, Go, Rust, Swift, Java, C#, Dart und mehr.

Lizenz

MIT

Available Tools

12 tools
get_contextA

Assemble task context: matching decisions with rationale, approval, owner, sources, last review, and freshness, plus related tests, file impact, and any available map entries. Map verification is rechecked against sampled source contents; stale or unknown verification requires a fresh review, and recordedVerdict preserves the historical verdict. Proposals are suggestions; legacy records are unreviewed; accepted decisions are constraints subject to freshness. No initialization or map required. Pass task and optional files. map.status and diagnostics preserve missing or invalid knowledge. Impact covers up to three unique files, expanding directory anchors.

Inputs: dir (required), task (required), files.

get_impactA

Trace historical co-change partners, related tests, and references with evidence: resolved imports, explicit paths, or uncertain name candidates. Candidates are not proven dependencies. Deterministic and read-only; no initialization or concept map required.

Inputs: dir (required), files (required).

get_snapshotA

Return the optional feature-to-file architecture map with drift and trust evidence. Map verification is rechecked against sampled source contents; stale or unknown verification requires a fresh review, and recordedVerdict preserves the historical verdict. If no map exists, returns exists:false and points to decision context. Decision capture, get_context, and get_impact still work. No initialization required.

Inputs: dir (required).

mason_automationB

Inspect installed automation, observed host events, pending decision records and the notification baseline, or check all retained documentation findings across sessions. status is read-only; check saves local baselines and verification reports without editing source, approving advisories or consuming pending completion notices. Returns concise results with a full report path. Works without a map.

Inputs: dir (required), action (required).

mason_check_driftA

Check how far the concept map has drifted from HEAD. Deterministic (git + filesystem, no LLM). Returns which features/flows are stale and the changed files behind them, new source files not yet mapped, ghost files (mapped but deleted), renames, and a recommendation: up-to-date (nothing to do), incremental (update just the stale entries via save_snapshot), or full-rebuild (broad source review required). Call this before trusting the map in a long session, or when maintaining an existing map.

Inputs: dir (required).

mason_complete_initA

Record assistant instruction setup locally in ignored .mason/local/project.json, with feature settings in shared .mason/config.json. Other tools work without this marker. Repeated calls preserve the original setup time and existing settings.

Inputs: dir (required).

mason_initA

Inspect this project now: returns documentation audit findings, committed-diff review findings, decision/map status, and a quickstart playbook. Quickstart is read-only and deterministic. Explicit mode: setup validates shared configuration and activates locally without editing shared files; mode: init explicitly prepares MCP, instructions and lifecycle hooks for review and commit. Neither runs audits or prepares repairs; use only when requested. Optional host selects codex or claude. Optional base selects the review comparison; evidence imports CI manifests with check outcomes, commit freshness, and links to changed files and accepted decisions. Repeat calls refresh findings even after setup.

Inputs: dir (required), base, host, mode, +2 more.

review_decisionA

Prepare a decision review: returns the claim and any operative accepted revision, provenance, the latest inspection and history event (notes shortened), changed files with hunk and line counts and anchor commits since the latest valid inspection for both sets of anchors, and a reviewToken. Request the diff (optionally for specific diffFiles), source previews or full history with include; the token is unchanged. For accepted-guidance inspection use inspectionScope operative on both prepare and inspect; pending proposals remain unassessed. Default all scope covers both revisions. After source inspection, record inspect with inspector, note and token to report no contradiction found without human acceptance. For human review, prepare with all scope, then record accept, reaffirm, or retire with its token, the authorized reviewer, and a reason. Acceptance replaces the operative revision; retirement withdraws the entire record including its proposal. Acceptance requires owner, source, readable Git HEAD, and committed anchor changes. Changed records or code invalidate the token. Identities and approvals are recorded assertions for normal PR review, not authenticated proof.

Inputs: id (required), dir (required), note, action, +7 more.

save_decisionA

Capture or revise a decision proposal as soon as the lesson is supported by evidence, without waiting for implementation or merge. Keep unimplemented remedies tentative. Include rationale, anchors, optional owner, sources, and a known actor. Compare matching get_context records and pending proposals before saving. When new evidence changes the same lesson's assumptions, scope, or recommended action, pass its existing id, including for accepted records. Preserve supported rationale and sources and replace obsolete instructions. Create a new record for a genuinely distinct lesson; skip unchanged restatements. No setup or map required. Writes a local record and preserves content history. Changes create a pending proposal while the last accepted revision remains operative; unchanged content does not re-verify or refresh it. Use review_decision for authorized acceptance or reaffirmation. A proposal cannot supersede a record with an operative accepted revision; review its replacement and retire the original separately.

Inputs: dir (required), body (required), title (required), category (required), +7 more.

save_snapshotA

Save a concept-to-files map as a persistent project snapshot. Maps feature names and data flows to the files that implement them. Retained for direct maintenance of legacy maps; the managed map-build workflow has been removed. Persists across conversations — future sessions can call get_snapshot to instantly find relevant files. No API key needed — you are the LLM generating the map.

Inputs: dir (required), flows (required), features (required), removeFlows, +1 more.

save_verificationA

Record verify_snapshot verdicts using each entry’s kind and reviewToken. Missing tokens request a fresh review; changed or deleted entries return conflicts without being stamped. Entries judged ok are stamped verifiedAt; failures are flagged verificationFailed with your note and surface in get_context, get_snapshot, and mason_check_drift until corrected. Verdict notes are required for failures.

Inputs: dir (required), verdicts (required).

verify_snapshotA

Spot-check the concept map's CORRECTNESS (drift checks freshness; this checks entries were right to begin with). Returns a sample of entries — always the never-verified and least-recently-verified first — with skeletons of their claimed files, for you to judge whether the files actually implement what the entry claims. Report verdicts back via save_verification with each entry’s kind and reviewToken. Tokens bind the entry and bounded source evidence; changed evidence requires a fresh review. Run periodically, or after an automated refresh wrote entries no human reviewed.

Inputs: dir (required), sample.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 12 tools

    Disambiguation3/5

    Several clusters overlap: mason_init, mason_complete_init, and mason_automation all touch setup/inspection state, while get_snapshot, get_context, get_impact, and verify_snapshot all return map/context views that an agent could easily conflate. verify_snapshot with save_verification and check_drift form a defensible pairing, and the save/review decision tools are distinct, but the descriptions' dense terminology makes tool selection error-prone.

    Naming Consistency3/5

    Most names follow a verb_noun pattern (get_snapshot, save_decision, review_decision, check_drift), but only some carry the mason_ prefix (mason_check_drift, mason_init, mason_automation, mason_complete_init) while others do not. 'mason_complete_init' also breaks the verb_noun reading and is easily confused with mason_init.

    Tool Count4/5

    Twelve tools is within a reasonable band for a map plus decision-lifecycle server, and each cluster (drift, verification, decisions, setup) earns roughly its place. The setup triplet of mason_init, mason_complete_init, and mason_automation is the one area where consolidation would help.

    Completeness4/5

    The surface covers the full knowledge lifecycle: map save/get, drift checking, verification verdicts, decision save/review/accept/retire, context assembly, and impact analysis. Minor gaps exist — no tool to delete or clear a snapshot map, and no way to enumerate decisions beyond task-matched get_context lookups.

    Maintenance

    ActivityMaintained
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      A
      quality
      D
      maintenance
      A TypeScript tool that ranks files in your codebase by importance, tracks dependencies, and provides file summaries to help understand code structure through Cursor's Model Context Protocol.
      14
      302
      -
    • A
      license
      A
      quality
      D
      maintenance
      Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathers and makes concepts, naming conventions, and vocabulary queryable via MCP.
      19
      44
      MIT
    • F
      license
      B
      quality
      B
      maintenance
      Turns local code repositories into a queryable dependency graph built from AST parsing and git co-edit history, then exposes it alongside an Obsidian vault as persistent memory. Enables context retrieval, impact analysis of proposed changes, and curation of durable prose knowledge through full-text search and Personalized PageRank classification—all fully offline without API keys or embeddings.
      30
      -
    • A
      license
      Not graded
      quality
      A
      maintenance
      Turns a codebase into a persistent knowledge graph so AI coding agents can answer structural questions about functions, call chains, routes, and cross-service links through graph queries instead of reading files one by one.
      MIT