mcp-architector

Bulk delete entries matching kind/moduleName/tags filter. Requires confirm=true. Use before full re-import or to clear a module slice. Prefer replace-entries with deleteOrphans for idempotent sync.

Removes one entry and updates the index. Use when a fact is obsolete. Do not use to delete modules—use delete-module. Cannot delete slice definitions—use delete-slice.

Deletes one module from architecture and its module detail file. Does not delete entries—remove those with delete-entry if needed. Does not delete custom slices.

Deletes a custom slice definition only. Built-in slices (api, domain, …) cannot be deleted. Does not delete entries—use delete-entry.

Run when catalog JSON is corrupt (list-modules, get-module-details, or validate fail with extra data after JSON). Rewrites the first valid JSON object in architecture, modules, entries, and slices; removes leftover .tmp files; rebuilds the entry index. Does not delete facts. Optional dryRun previews without writing.

Returns one full entry by id. Use after list-entries or search-entries when you need payload and refs. Do not use for a full API list—use get-slice sliceId=api. Do not use for module structure—use get-module-details.

Returns entry counts grouped by kind, module, and tag. Use after replace-entries/import to verify catalog size.

Returns one module's full detail (files, dependencies, examples). Use when you know the module name from get-project-architecture or list-modules. If module has files but get-slice is empty, add entries with refs.moduleName=this module. For cross-cutting API/domain lists use get-slice. moduleName must match architecture exactly.

Returns vertical structure: project description, module list, dataFlow. Use for refactoring boundaries between components. For all HTTP endpoints or domain terms use get-slice—not this tool. For one module's files and examples use get-module-details. projectId is required—call list-projects first.

Returns a horizontal project view: filtered entries transformed for agents. Empty slice = no entries with matching kind. Call list-slices first to pick sliceId. format=compact default; table for api/ui slice. Use offset/limit for pagination. Filter further by moduleName or tags.

Max 50 entries per bulk call—split large catalogs into batches of ~50 to avoid oversized tool payloads. For full re-import: delete-entries once, then set-entries in 50-entry chunks; or replace-entries with deleteOrphans=false until the final batch (deleteOrphans=true). Alias for replace-entries (mode=replace). Pass filter as scope; send up to 50 entries per call.

Returns the entry catalog (id, kind, title, tags, moduleName)—no payload. Supports kind/moduleName/tags filters and pagination (limit max 200). Unlinked entries lack moduleName; run validate after edits. For typed horizontal views use get-slice.

Lists module summaries from architecture (name, description)—vertical structure only. For horizontal facts (endpoints, tables, terms) use list-slices then get-slice. After edits run validate. Use module names in set-entry refs.moduleName.

Call first. Lists projects in ~/.mcp-architector with projectId, description, moduleCount, updatedAt, isCurrent, forbidden. Match this workspace by folder name (query). Pass that projectId to every other tool—never omit, never use default-project. isCurrent is only a hint from MCP_PROJECT_ID. If none matches, create with set-project-architecture using a stable id from the workspace path.

Lists built-in and custom slice views (filters over entries—not separate stored data). Empty slice = no entries with matching kind, not a missing slice definition. Use before get-slice to pick sliceId (api, domain, persistence, …).

Rebuilds dataFlow for all modules from module file dependencies or existing dependsOn edges. Recomputes providesTo and optionally syncs module files. Use instead of editing architecture.json directly.

Rebuilds entries/index.json from entry files on disk. Use when list-entries or get-slice miss entries that exist as files (index drift). Does not modify entry bodies.

Preview or apply in-repo refactor sync to architector data (no workspace access). Default dryRun=true. Workflow: (1) scan with file/text to list hits, (2) build 1-3 mutation ops, (3) dryRun preview, (4) apply with dryRun=false and confirm=true. Mutations: move-file, replace-path-prefix, rename-text, patch-entry, merge-files, remove-file-ref. Orphan entries with empty refs.files and no entryIds are deleted. Does not change module names or dataFlow.

Max 50 entries per bulk call—split large catalogs into batches of ~50 to avoid oversized tool payloads. For full re-import: delete-entries once, then set-entries in 50-entry chunks; or replace-entries with deleteOrphans=false until the final batch (deleteOrphans=true). Idempotent sync for up to 50 entries in scope; optionally delete orphans not in this batch. Match by upsertBy (default kind+title). For large catalogs use deleteOrphans=false on intermediate batches, true only on the last batch.

Compact navigation search over entries by title, summary, kind, and tags. Returns snippet, matchedIn, slices, and moduleName per hit—use get-entry for full payload. Prefer get-slice when you know the category (api, domain). Filters (moduleName, kind, tags) narrow agent context. Default limit 10.

Entries need vertical structure: create modules via set-project-architecture / set-module-details before or when adding entries. Set refs.moduleName to an existing module name from list-modules. Run validate after edits to find entries-without-modules, entry-unlinked, or empty slices. Max 50 entries per bulk call—split large catalogs into batches of ~50 to avoid oversized tool payloads. For full re-import: delete-entries once, then set-entries in 50-entry chunks; or replace-entries with deleteOrphans=false until the final batch (deleteOrphans=true). Set refs.moduleName per entry, or pass top-level moduleName as default. Prefer set-entries in 50-entry chunks over one huge replace-entries payload.

Entries need vertical structure: create modules via set-project-architecture / set-module-details before or when adding entries. Set refs.moduleName to an existing module name from list-modules. Run validate after edits to find entries-without-modules, entry-unlinked, or empty slices. Creates or updates one canonical project fact (entry). Use when you discovered a concrete fact while working. Do not use for module structure—use set-module-details. Do not copy module.description into summary; link via refs.moduleName only. Upsert: pass id to update, or omit id to match by kind+title or create new. Example: kind=http-endpoint, title='POST /orders', summary='Creates order', refs.moduleName='orders', refs.files=['src/OrderController.java'].

Patches dataFlow for one module (dependsOn is canonical; providesTo is recomputed). Syncs module file dependencies. Prefer over set-project-architecture for single-module graph edits.

Creates or updates one vertical module (files, dependencies, dataFlow sync). IMPORTANT: Slices (api, domain, persistence) are built from entries, not from module text. When adding or updating a module, also add entries this module owns: pass facts[] (http-endpoint, entity, glossary, …) in this call (max 50 per call), or call set-entry / set-entries in 50-entry batches with refs.moduleName=<module name>. Max 50 entries per bulk call—split large catalogs into batches of ~50 to avoid oversized tool payloads. For full re-import: delete-entries once, then set-entries in 50-entry chunks; or replace-entries with deleteOrphans=false until the final batch (deleteOrphans=true). Without entries, get-slice will be empty for this module. After edits call validate to verify links. Does not replace other modules. Prefer over set-project-architecture for single-module edits.

Creates or updates vertical module structure (components and dataFlow)—not horizontal facts. By default merges modules and dataFlow by name; omit dataFlow to keep existing flow. Use replaceModules or replaceDataFlow for full replace. For one module use set-module-details or set-module-data-flow. For bulk flow rebuild use rebuild-data-flow. Each new module still needs entries—use set-module-details with facts[] or set-entries after bulk structure. For APIs, domain terms, scripts use set-entry + get-slice—not this tool. projectId is required—call list-projects first. Never use default-project. Do not duplicate entry text in module descriptions.

Saves a custom slice definition (filter only—no items). Items always live in entries. Use when built-in slices (api, domain, …) are not enough, e.g. filter kinds godot-scene + tag gameplay. Do not store duplicate entry text here. get-slice reads entries through this filter.

Run after set-project-architecture, set-module-details, set-entry, or set-entries. Returns a compact report (summary, stats, issues by kind)—no need to load the full project in the agent. Checks only known rules: dataFlow consistency, module↔entry links, module detail files, entry index drift, empty api/domain/persistence slices, entry slice coverage, optional module-too-few-entries when moduleEntryMin is set. If catalog JSON is corrupt, run fix-data first. Fix issues[] then call validate again.

Alias for validate with the same checks. Prefer validate after edits. Legacy name kept for compatibility.

Dry-run validation for a proposed import batch (max 50 entries). Max 50 entries per bulk call—split large catalogs into batches of ~50 to avoid oversized tool payloads. For full re-import: delete-entries once, then set-entries in 50-entry chunks; or replace-entries with deleteOrphans=false until the final batch (deleteOrphans=true). Checks duplicate upsert keys and unknown moduleName refs without writing.