mason
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mason_initA | Inspect this project now: returns documentation audit findings, committed-diff review findings, decision/map status, and a quickstart playbook. Quickstart and map modes are read-only and deterministic. Explicit mode: setup configures MCP, instructions and lifecycle hooks to use mason on PATH while retaining original audit evidence; use it only when the user requests setup. 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. mode: map returns the full Map-Reduce build workflow. Repeat calls refresh findings even after setup. |
| mason_automationB | Inspect installed automation and observed host events, or resume/check retained documentation repair evidence across sessions. status is read-only; check saves local baselines and verification reports without editing source or approving advisories. Returns concise results with a full report path. Works without a map. |
| mason_repairA | Track documentation repairs against original audit evidence. prepare saves a local baseline and returns a scoped work order; verify reads that baseline and reports resolved, unresolved, review-required, unverified, and new findings. Suppressed advisories remain unresolved. Does not edit documentation or approve decisions. No map required. |
| review_advisoryA | Prepare an assessment of an original repair advisory and its exact repository scope, then record authorized addressed, inapplicable or deferred outcomes with reviewToken, reviewer and note. Relevant changes reopen reviews; unrelated commits preserve them. Records belong in Git. Decision findings route to review_decision; this tool never approves decisions. Recorded identities are assertions, not authenticated approvals. |
| 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; pass confluenceConfigured only to change that setting. |
| mason_set_confluenceA | Configure Confluence credentials. Two-step flow: (1) call without |
| full_analysisA | One-shot orientation for a project WITHOUT a concept map (get_snapshot returned exists:false). Returns git history stats, project structure with file counts, curated code sample previews (~60 lines each), and test-to-source mapping. On a mapped project, prefer get_snapshot — it is cheaper and answers feature/architecture questions directly. |
| analyze_projectB | Run git history analysis on a codebase. Returns commit convention patterns, stale directories, and frequently changed files. These are aggregate stats across hundreds of commits that would be expensive to compute manually. |
| get_code_samplesA | Get previews (first ~60 lines) of representative source files from the codebase. Includes entry points, config files, hot files (frequently changed), test examples, and one file per directory for breadth. Read files natively for full content. |
| get_snapshotA | Return the optional feature-to-file architecture map with drift and trust evidence. If no map exists, returns exists:false plus project structure, Git signals, and test pairs. Decision capture, get_context, and get_impact still work. No initialization required. |
| 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. 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. |
| generate_snapshot_batchA | Map step of the concept-map build. Returns one batch of source files (skeletons of every file in the batch plus a few deeper-read bodies for grounding), along with a system prompt instructing you to derive features and flows for ONLY this batch. Call repeatedly with the returned |
| save_partial_snapshotA | Persist the partial concept map you derived for one batch. Call this once per batch, with the |
| reduce_snapshotA | Reduce step of the concept-map build. Returns every partial snapshot plus a system prompt asking you to merge them into one coherent project-wide map. Resolve platform variants into single product features, dedupe near-duplicates, and ensure no file is dropped. After producing the unified map, call |
| save_snapshotB | Save a concept-to-files map as a persistent project snapshot. Maps feature names and data flows to the files that implement them. 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. |
| save_decisionA | Capture or revise a decision proposal with 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. |
| review_decisionA | Prepare a decision review: returns the full record and history, any operative accepted revision, provenance, changes and previews for both sets of anchors, and a reviewToken. Then record accept, reaffirm, or retire with that 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. |
| 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 |
| 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. Run periodically, or after an automated refresh wrote entries no human reviewed. |
| save_verificationA | Record verify_snapshot verdicts. 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. |
| 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. |
| export_to_confluenceA | Sync the project's concept map to Confluence as product-readable wiki pages: an index page, one page per feature (PM-language descriptions, no file paths), and a changelog page. Mason replaces managed page bodies; manual edits to those bodies are overwritten. Requires |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 22 tools
Several tools have overlapping purposes that descriptions only partially resolve: full_analysis vs get_snapshot vs analyze_project vs get_code_samples all return project structure/samples; mason_init vs mason_complete_init vs mason_set_confluence all concern setup; and mason_automation vs mason_repair both touch documentation-repair evidence. The decision/review and map-build/verify pairs are reasonably distinguished, but the boundaries require careful reading.
The underlying verb_noun snake_case convention (get_, save_, review_, verify_, export_) is mostly consistent, but roughly a third of tools carry an unexplained `mason_` prefix (mason_init, mason_repair, mason_check_drift) while siblings like get_snapshot and save_decision do not. The prefix usage is arbitrary rather than domain-driven, muddying predictability.
At 22 tools this sits in the heavy zone, though the surface legitimately spans distinct workflows (Map-Reduce map building, verification, drift, decisions, repairs, Confluence export). Multiple setup/repair/analysis tools could likely be consolidated, so it reads as slightly over-scoped rather than tightly scoped.
Coverage of the code-analysis/concept-map/decision domain is broad: build, save, verify, drift-check, context assembly, impact tracing, decision capture and review, repair tracking, and Confluence export are all present. Minor gaps remain (e.g. no direct map-entry delete or decision supersede beyond retire), but core lifecycles are covered.