@decantr/mcp-server 3.6.2 → 3.8.0

package/README.md

@@ -12,7 +12,7 @@ AI Frontend Governance for codebases touched by AI agents. Give Claude, Cursor,
 
 ![Decantr MCP demo](https://raw.githubusercontent.com/decantr-ai/decantr/main/packages/mcp-server/assets/decantr-demo.gif)
 
-- **Structured Contract context** -- gives your AI assistant patterns, layouts, component specs, typed graph context, Brownfield/Hybrid authority, local law, behavior obligations, and task-time context instead of letting it guess
+- **Structured Contract context** -- gives your AI assistant patterns, layouts, component specs, shared Brownfield discovery metadata, typed graph context, Brownfield/Hybrid authority, local law, behavior obligations, and task-time context instead of letting it guess
 - **Evidence-backed repair loops** -- gives AI agents Project Health, component reuse drift, accepted behavior-obligation drift, accepted style bridge drift, stable diagnostic codes, typed repair IDs, graph-anchored Evidence Bundles, workspace health, and scoped repair prompts without uploading source
 - **Drift detection** -- catches when generated code deviates from your design intent
 - **Zero config** -- run with `npx`, no API keys or accounts required
@@ -138,12 +138,12 @@ The server exposes a hard 8-tool MCP surface. Pass an `action` to select the rou
 
 | Tool | Description | Example Input |
 |------|-------------|---------------|
-| `decantr_project` | Read local project state and workspace health | `{ "action": "state", "project_path": "apps/web" }` |
+| `decantr_project` | Read local project state, shared discovery summary, and workspace health | `{ "action": "state", "project_path": "apps/web" }` |
 | `decantr_contract` | Read Essence, validate, check drift, generate a skeleton, or read the Contract capsule | `{ "action": "validate", "path": "./decantr.essence.json" }` |
-| `decantr_context` | Read scaffold, section, page, task, and execution-pack context | `{ "action": "task", "project_path": "apps/web", "route": "/feed", "task": "improve recipe card loading" }` |
+| `decantr_context` | Read scaffold, section, page, task, shared discovery summary, and execution-pack context | `{ "action": "task", "project_path": "apps/web", "route": "/feed", "task": "improve recipe card loading" }` |
 | `decantr_graph` | Read graph snapshots, query graph nodes/edges, or traverse graph relations | `{ "action": "query", "project_path": "apps/web", "file_path": "src/app/page.tsx", "include_impact": true }` |
-| `decantr_registry` | Search and resolve hosted registry content, benchmarks, and execution packs | `{ "action": "resolve_pattern", "id": "data-table", "preset": "product" }` |
-| `decantr_verify` | Run audit, critique, findings, v2 evidence bundles, or health-loop reads | `{ "action": "evidence_bundle", "project_path": "apps/web" }` |
+| `decantr_registry` | Compatibility content-corpus tool for official vocabulary, benchmarks, and execution packs | `{ "action": "resolve_pattern", "id": "data-table", "preset": "product" }` |
+| `decantr_verify` | Run audit, critique, findings, v2 evidence bundles with discovery metadata, or health-loop reads | `{ "action": "evidence_bundle", "project_path": "apps/web" }` |
 | `decantr_repair` | Return typed findings, repair plans, repair prompts, and v2 health-loop guidance | `{ "action": "health_loop", "project_path": "apps/web" }` |
 | `decantr_contract_write` | Explicit write surface for accepting drift, deferring drift to the drift log, or mutating Essence v4 | `{ "action": "update_essence", "operation": "add_feature", "payload": { "feature": "billing" } }` |
 
@@ -155,7 +155,7 @@ For Decantr 3 assistant prompt migration, see the MCP migration guide: https://d
 
 The MCP server reads Decantr files, including `.decantr/graph` typed graph artifacts, and selected project files from the active workspace. Write access is limited to the explicit `decantr_contract_write` tool with `accept_drift` and `update_essence` actions. `accept_drift` may defer a finding to `.decantr/drift-log.json` when the caller explicitly requests that resolution. Paths are contained to the active workspace root.
 
-Registry and pack-resolution tools may call the configured Decantr API. Source upload fallbacks for hosted critique/audit are disabled unless the tool call explicitly passes `allow_hosted_upload: true`. The MCP server does not emit Decantr telemetry. See [security permissions](https://decantr.ai/reference/security-permissions.md).
+Content-corpus and pack-resolution tools may call the configured Decantr API. Source upload fallbacks for hosted critique/audit are retired; verification tools run local reads unless a future major version introduces a new upload contract. The MCP server does not emit Decantr telemetry. See [security permissions](https://decantr.ai/reference/security-permissions.md).
 
 ## Compatibility
 
@@ -167,11 +167,11 @@ Registry and pack-resolution tools may call the configured Decantr API. Source u
 
 ### 3.4 Tool Surface Migration
 
-Decantr 3.4 consolidated legacy MCP tool names into the eight action-based tools above. Decantr 3.6 keeps that surface, preserves v2 task/evidence/workspace-health/health-loop contracts, and adds compatible metadata only through the consolidated tools. For example, `decantr_get_project_state` becomes `decantr_project` with `{ "action": "state" }`, `decantr_get_graph_snapshot` becomes `decantr_graph` with `{ "action": "snapshot" }`, and the legacy write tools become `decantr_contract_write` with `{ "action": "accept_drift" }` or `{ "action": "update_essence" }`.
+Decantr 3.4 consolidated legacy MCP tool names into the eight action-based tools above. Decantr 3.7 keeps that surface, preserves v2 task/evidence/workspace-health/health-loop contracts, and adds compatible discovery metadata only through the consolidated tools. For example, `decantr_get_project_state` becomes `decantr_project` with `{ "action": "state" }`, `decantr_get_graph_snapshot` becomes `decantr_graph` with `{ "action": "snapshot" }`, and the legacy write tools become `decantr_contract_write` with `{ "action": "accept_drift" }` or `{ "action": "update_essence" }`.
 
 ## How It Works
 
-An Essence spec (`decantr.essence.json`) captures your design intent -- archetype, theme, page structure, patterns, and guard rules -- in a single declarative file. The MCP server exposes this spec and the Decantr registry to your AI assistant, giving it concrete layout specs, component lists, and visual treatments instead of relying on the model's generic training data. The result is generated code that follows a coherent design system, and drift detection that catches deviations before they ship.
+An Essence spec (`decantr.essence.json`) captures your design intent -- archetype, theme, page structure, patterns, and guard rules -- in a single declarative file. The MCP server exposes this spec and the official Decantr content corpus to your AI assistant, giving it concrete layout specs, component lists, and visual treatments instead of relying on the model's generic training data. The result is generated code that follows a coherent contract, and drift detection that catches deviations before they ship.
 
 ## Example Workflow
 
@@ -180,11 +180,11 @@ An Essence spec (`decantr.essence.json`) captures your design intent -- archetyp
 The AI assistant calls these tools behind the scenes:
 
 1. `decantr_contract` with `create_essence`, `validate`, or `check_drift` actions to generate and verify the contract
-2. `decantr_registry` with `resolve_archetype`, `suggest_patterns`, `resolve_pattern`, or `compile_execution_packs` actions to fetch vocabulary and packs
+2. `decantr_registry` with `resolve_archetype`, `suggest_patterns`, `resolve_pattern`, or `compile_execution_packs` actions to fetch official content-corpus vocabulary and packs
 3. `decantr_context` with `execution_pack` or `task` actions to load the compact task contract before editing
 4. `decantr_project` with `state` to check Essence, packs, graph readiness, local law, diagnostics, and next useful action calls
 5. `decantr_contract` with `capsule` and `decantr_graph` with `snapshot`, `query`, or `traverse` to read typed graph context
-6. `decantr_verify` with `critique`, `audit_project`, or `evidence_bundle` to produce local v2 evidence; hosted upload remains opt-in with `allow_hosted_upload: true`
+6. `decantr_verify` with `critique`, `audit_project`, or `evidence_bundle` to produce local v2 evidence
 7. `decantr_repair` with `findings`, `repair_plan`, `repair_prompt`, or `health_loop` to enter a scoped evidence-backed repair loop
 
 The AI now generates code with the right layout structure, correct components, and consistent styling, then gets a scoped evidence-backed repair loop instead of a generic guess.

package/dist/bin.js

@@ -1,2 +1,2 @@
 #!/usr/bin/env node
-import "./chunk-XCTAGWHI.js";
+import "./chunk-M45XVAPP.js";

package/dist/{chunk-XCTAGWHI.js → chunk-M45XVAPP.js}

@@ -8,7 +8,7 @@ import { execFileSync } from "child_process";
 import { createHash } from "crypto";
 import { existsSync, readdirSync, readFileSync } from "fs";
 import { readFile as readFile2 } from "fs/promises";
-import { basename as basename2, dirname as dirname2, isAbsolute as isAbsolute2, join as join2, relative as relative2, resolve as resolve2 } from "path";
+import { dirname as dirname2, isAbsolute as isAbsolute2, join as join2, relative as relative2, resolve as resolve2 } from "path";
 import {
   buildGraphImpactContext,
   buildGraphRouteContext,
@@ -35,6 +35,7 @@ import {
   createEvidenceTier,
   createLoopReadiness,
   deriveVerificationDiagnostic,
+  discoverProject,
   KNOWN_VERIFICATION_DIAGNOSTICS,
   LOOP_READINESS_V2_SCHEMA_URL,
   PROJECT_HEALTH_REPORT_V2_SCHEMA_URL,
@@ -234,6 +235,65 @@ function displayProjectFile(projectRoot, path) {
   if (isAbsolute2(path)) return displayWorkspacePath(path);
   return displayWorkspacePath(join2(projectRoot, path));
 }
+function mcpDiscoverySummary(projectRoot) {
+  const discovery = discoverProject(projectRoot);
+  return {
+    schema_version: "discovery.v1",
+    project_path: discovery.workspace.projectPath,
+    workspace_scope: discovery.workspace.scope,
+    project: {
+      framework: discovery.project.framework,
+      framework_version: discovery.project.frameworkVersion,
+      package_manager: discovery.project.packageManager,
+      primary_language: discovery.project.primaryLanguage,
+      has_typescript: discovery.project.hasTypeScript,
+      has_tailwind: discovery.project.hasTailwind,
+      has_decantr: discovery.project.hasDecantr,
+      package_name: discovery.project.packageName,
+      evidence: discovery.project.evidence
+    },
+    routes: {
+      strategy: discovery.routes.strategy,
+      route_signal_count: discovery.routes.routeSignalCount,
+      taskable_route_count: discovery.routes.taskableRouteCount,
+      confidence: discovery.routes.confidence,
+      taskable_routes: discovery.routes.taskableRoutes.slice(0, 20).map((route) => ({
+        path: route.path,
+        file: route.file,
+        source: route.source,
+        confidence: route.confidence
+      })),
+      signals: discovery.routes.routeSignals.slice(0, 20).map((signal) => ({
+        path: signal.path,
+        file: signal.file,
+        kind: signal.kind,
+        taskable: signal.taskable,
+        confidence: signal.confidence
+      }))
+    },
+    components: {
+      component_count: discovery.components.componentCount,
+      page_count: discovery.components.pageCount,
+      confidence: discovery.components.confidence,
+      directories: discovery.components.directories,
+      evidence: discovery.components.evidence,
+      limitations: discovery.components.limitations
+    },
+    styling: {
+      approach: discovery.styling.approach,
+      config_file: discovery.styling.configFile,
+      css_variable_count: discovery.styling.cssVariableCount,
+      color_token_count: discovery.styling.colorTokenCount,
+      dark_mode: discovery.styling.darkMode,
+      theme_signals: discovery.styling.themeSignals
+    },
+    assistant: {
+      rule_files: discovery.assistant.ruleFiles
+    },
+    confidence: discovery.confidence,
+    limitations: discovery.limitations
+  };
+}
 function graphAvailableRoutes(snapshot) {
   return snapshot.nodes.filter((node) => node.type === "Route").map((node) => graphPayloadString(node.payload, "path") ?? node.id.replace(/^rt:/, "")).sort();
 }
@@ -950,111 +1010,6 @@ async function getHostedExecutionPackManifestPayload(args) {
     typeof args.namespace === "string" ? { namespace: args.namespace } : void 0
   );
 }
-async function getHostedFileCritiquePayload(args) {
-  const client = getAPIClient();
-  const filePath = args.file_path;
-  const resolvedFilePath = resolveWorkspacePath(filePath);
-  const snapshotFilePath = relative2(process.cwd(), resolvedFilePath).replace(/\\/g, "/") || basename2(resolvedFilePath);
-  const code = await readFile2(resolvedFilePath, "utf-8");
-  const { essence } = await readEssenceFile(args.path);
-  const treatmentsPath = typeof args.treatments_path === "string" ? resolveWorkspacePath(args.treatments_path) : join2(process.cwd(), "src", "styles", "treatments.css");
-  const treatmentsCss = existsSync(treatmentsPath) ? readFileSync(treatmentsPath, "utf-8") : void 0;
-  return client.critiqueFile(
-    {
-      essence,
-      filePath: snapshotFilePath,
-      code,
-      treatmentsCss
-    },
-    typeof args.namespace === "string" ? { namespace: args.namespace } : void 0
-  );
-}
-function extractHostedAssetPaths(indexHtml) {
-  const assetPaths = /* @__PURE__ */ new Set();
-  for (const match of indexHtml.matchAll(/<(?:script|link)[^>]+(?:src|href)="([^"]+)"/g)) {
-    const assetPath = match[1];
-    const assetsIndex = assetPath.indexOf("/assets/");
-    if (assetsIndex === -1) continue;
-    assetPaths.add(assetPath.slice(assetsIndex));
-  }
-  return [...assetPaths];
-}
-async function captureHostedDistSnapshot(projectRoot, distPathArg) {
-  const distRoot = distPathArg ? resolveWorkspacePath(distPathArg, projectRoot) : join2(projectRoot, "dist");
-  const indexPath = join2(distRoot, "index.html");
-  if (!existsSync(indexPath)) {
-    return void 0;
-  }
-  const indexHtml = readFileSync(indexPath, "utf-8");
-  const assets = {};
-  for (const assetPath of extractHostedAssetPaths(indexHtml)) {
-    const snapshotAssetPath = assetPath.replace(/^[/\\]+/, "");
-    const assetFilePath = resolveWorkspacePath(snapshotAssetPath, distRoot);
-    if (existsSync(assetFilePath)) {
-      assets[snapshotAssetPath] = readFileSync(assetFilePath, "utf-8");
-    }
-  }
-  return {
-    indexHtml,
-    assets
-  };
-}
-function isHostedSourceSnapshotFile(path) {
-  if (/\.d\.ts$/i.test(path)) return false;
-  return /\.(?:[cm]?[jt]sx?)$/i.test(path);
-}
-async function captureHostedSourceSnapshot(projectRoot, sourcesPathArg) {
-  if (!sourcesPathArg) {
-    return void 0;
-  }
-  const sourcesRoot = resolveWorkspacePath(sourcesPathArg, projectRoot);
-  if (!existsSync(sourcesRoot)) {
-    return void 0;
-  }
-  const files = {};
-  const ignoredDirNames = /* @__PURE__ */ new Set([
-    "node_modules",
-    ".git",
-    ".decantr",
-    "dist",
-    "build",
-    "coverage"
-  ]);
-  const rootPrefix = basename2(sourcesRoot);
-  const walk = (absoluteDir, relativeDir) => {
-    for (const entry of readdirSync(absoluteDir, { withFileTypes: true })) {
-      if (ignoredDirNames.has(entry.name)) continue;
-      const absolutePath = join2(absoluteDir, entry.name);
-      const relativePath = join2(relativeDir, entry.name).replace(/\\/g, "/");
-      if (entry.isDirectory()) {
-        walk(absolutePath, relativePath);
-        continue;
-      }
-      if (!entry.isFile()) continue;
-      if (!isHostedSourceSnapshotFile(relativePath)) continue;
-      files[relativePath] = readFileSync(absolutePath, "utf-8");
-    }
-  };
-  walk(sourcesRoot, rootPrefix);
-  return Object.keys(files).length > 0 ? { files } : void 0;
-}
-async function getHostedProjectAuditPayload(args) {
-  const client = getAPIClient();
-  const { essence } = await readEssenceFile(args.path);
-  const dist = await captureHostedDistSnapshot(process.cwd(), args.dist_path);
-  const sources = await captureHostedSourceSnapshot(
-    process.cwd(),
-    args.sources_path
-  );
-  return client.auditProject(
-    {
-      essence,
-      dist,
-      sources
-    },
-    typeof args.namespace === "string" ? { namespace: args.namespace } : void 0
-  );
-}
 async function loadHostedExecutionPackBundleFallback(args) {
   try {
     return {
@@ -1094,38 +1049,9 @@ async function loadHostedSelectedExecutionPackFallback(args) {
     };
   }
 }
-async function loadHostedFileCritiqueFallback(args) {
-  try {
-    return {
-      report: await getHostedFileCritiquePayload(args),
-      error: null
-    };
-  } catch (error) {
-    return {
-      report: null,
-      error: error.message
-    };
-  }
-}
-async function loadHostedProjectAuditFallback(args) {
-  try {
-    return {
-      report: await getHostedProjectAuditPayload(args),
-      error: null
-    };
-  } catch (error) {
-    return {
-      report: null,
-      error: error.message
-    };
-  }
-}
 function hasExecutionPackPayload(payload) {
   return payload.markdown !== null || payload.json !== null;
 }
-function allowsHostedUpload(args) {
-  return args.allow_hosted_upload === true;
-}
 function toHostedExecutionPackPayload(pack) {
   return {
     markdown: pack && typeof pack.renderedMarkdown === "string" ? pack.renderedMarkdown : null,
@@ -1285,7 +1211,7 @@ function mcpCommandsForFinding(source) {
     case "pack":
       return [
         "decantr refresh",
-        "decantr registry get-pack review --write-context",
+        "decantr content get-pack review --write-context",
         "decantr health"
       ];
     case "runtime":
@@ -1974,7 +1900,7 @@ var TOOLS = [
   consolidatedTool(
     "decantr_registry",
     "Decantr Registry",
-    "Search and resolve hosted registry content, benchmark metadata, and execution packs.",
+    "Compatibility tool for searching the official Decantr content corpus, benchmark metadata, and execution packs.",
     READ_ONLY_NETWORK
   ),
   consolidatedTool(
@@ -2292,7 +2218,7 @@ async function handleLegacyTool(name, args) {
       if (args.components_used && Array.isArray(args.components_used) && args.page_id && typeof args.page_id === "string") {
         const pages = listEssencePages(essence);
         const page = pages.find((p) => p.id === args.page_id);
-        if (page && page.layout) {
+        if (page?.layout) {
           const expectedPatterns = /* @__PURE__ */ new Set();
           for (const item of page.layout) {
             if (typeof item === "string") {
@@ -2621,6 +2547,7 @@ async function handleLegacyTool(name, args) {
         return {
           source: "local_workspace",
           project_root: displayWorkspacePath(projectRoot),
+          discovery: mcpDiscoverySummary(projectRoot),
           essence: essence ? {
             present: true,
             version: typeof essence.version === "string" ? essence.version : null,
@@ -3222,7 +3149,7 @@ async function handleLegacyTool(name, args) {
         const hosted = await loadHostedExecutionPackBundleFallback(args);
         if (!hosted.bundle) {
           return {
-            error: "Scaffold context not found. Run `decantr refresh` or `decantr registry compile-packs --write-context` to materialize scaffold context and execution packs.",
+            error: "Scaffold context not found. Run `decantr refresh` or `decantr content compile-packs --write-context` to materialize scaffold context and execution packs.",
             hosted_fallback_error: hosted.error ?? hostedScaffold.error ?? hostedReview.error
           };
         }
@@ -3353,7 +3280,7 @@ async function handleLegacyTool(name, args) {
         context: derivedContext,
         execution_pack_source: executionPackSource,
         execution_pack: executionPack,
-        note: executionPackSource === "hosted_fallback" ? "Section context file not found. Using hosted compiled execution pack fallback as the readable section context." : `Section context file not found. Run \`decantr refresh\` or \`decantr registry get-pack section ${sectionId} --write-context\` to generate it.`,
+        note: executionPackSource === "hosted_fallback" ? "Section context file not found. Using hosted compiled execution pack fallback as the readable section context." : `Section context file not found. Run \`decantr refresh\` or \`decantr content get-pack section ${sectionId} --write-context\` to generate it.`,
         hosted_fallback_error: executionPackSource ? void 0 : hostedFallbackError
       };
     }
@@ -3406,7 +3333,7 @@ async function handleLegacyTool(name, args) {
         const hosted = await loadHostedPageSelection();
         if (!hosted) {
           return {
-            error: "Execution pack manifest not found. Run `decantr refresh` or `decantr registry get-pack manifest --write-context` to generate compiled packs.",
+            error: "Execution pack manifest not found. Run `decantr refresh` or `decantr content get-pack manifest --write-context` to generate compiled packs.",
             hosted_fallback_error: hostedFallbackError
           };
         }
@@ -3651,6 +3578,7 @@ async function handleLegacyTool(name, args) {
         verifyCommand
       };
       return {
+        discovery: mcpDiscoverySummary(projectRoot),
         route: resolvedRoute,
         page_id: pageId,
         section_id: section.id,
@@ -3755,7 +3683,7 @@ async function handleLegacyTool(name, args) {
           hostedFallbackError = hosted.error;
           if (!hosted.bundle) {
             return {
-              error: "Execution pack manifest not found. Run `decantr refresh` or `decantr registry get-pack manifest --write-context` to generate compiled packs.",
+              error: "Execution pack manifest not found. Run `decantr refresh` or `decantr content get-pack manifest --write-context` to generate compiled packs.",
               hosted_fallback_error: hosted.error
             };
           }
@@ -3775,7 +3703,7 @@ async function handleLegacyTool(name, args) {
         hostedFallbackError = hosted.error;
         if (!hosted.selected) {
           return {
-            error: "Execution pack manifest not found. Run `decantr refresh` or `decantr registry get-pack manifest --write-context` to generate compiled packs.",
+            error: "Execution pack manifest not found. Run `decantr refresh` or `decantr content get-pack manifest --write-context` to generate compiled packs.",
             hosted_fallback_error: hosted.error
           };
         }
@@ -3930,12 +3858,6 @@ async function handleLegacyTool(name, args) {
       if (existsSync(localReviewPackPath)) {
         return critiqueFile(args.file_path, process.cwd());
       }
-      if (allowsHostedUpload(args)) {
-        const hosted = await loadHostedFileCritiqueFallback(args);
-        if (hosted.report) {
-          return hosted.report;
-        }
-      }
       return critiqueFile(args.file_path, process.cwd());
     }
     case "decantr_audit_project": {
@@ -3965,12 +3887,6 @@ async function handleLegacyTool(name, args) {
       if (hasReviewPack && hasPackManifest) {
         return auditProject(projectRoot);
       }
-      if (allowsHostedUpload(args)) {
-        const hosted = await loadHostedProjectAuditFallback(args);
-        if (hosted.report) {
-          return hosted.report;
-        }
-      }
       return auditProject(projectRoot);
     }
     case "decantr_get_findings": {
@@ -4072,7 +3988,10 @@ async function handleLegacyTool(name, args) {
       try {
         const projectRoot = resolveMcpProjectRoot(args.project_path);
         const state = await getMcpHealthState(projectRoot);
-        return state.evidence;
+        return {
+          ...state.evidence,
+          discovery: mcpDiscoverySummary(projectRoot)
+        };
       } catch (error) {
         return { error: error.message };
       }
@@ -4111,6 +4030,7 @@ async function handleLegacyTool(name, args) {
         }
         return {
           project: state.evidence.project,
+          discovery: mcpDiscoverySummary(projectRoot),
           health: state.evidence.health,
           finding: {
             id: finding.id,
@@ -4329,7 +4249,7 @@ function describeUpdate(operation, payload) {
 }
 
 // src/index.ts
-var VERSION = "3.6.2";
+var VERSION = "3.8.0";
 var server = new Server({ name: "decantr", version: VERSION }, { capabilities: { tools: {} } });
 server.setRequestHandler(ListToolsRequestSchema, async () => {
   return { tools: TOOLS };

package/dist/index.js

@@ -1 +1 @@
-import "./chunk-XCTAGWHI.js";
+import "./chunk-M45XVAPP.js";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@decantr/mcp-server",
-  "version": "3.6.2",
+  "version": "3.8.0",
   "mcpName": "io.github.decantr-ai/mcp-server",
   "description": "MCP server for Decantr — exposes Contract context, typed graph artifacts, and verification evidence to AI coding assistants",
   "keywords": [
@@ -41,7 +41,8 @@
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
   "files": [
-    "dist"
+    "dist",
+    "server.json"
   ],
   "engines": {
     "node": ">=20.19.0"
@@ -51,10 +52,10 @@
   },
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.29.0",
-    "@decantr/core": "3.6.0",
-    "@decantr/verifier": "3.6.1",
-    "@decantr/essence-spec": "3.4.0",
-    "@decantr/registry": "3.4.0"
+    "@decantr/core": "3.8.0",
+    "@decantr/verifier": "3.8.0",
+    "@decantr/essence-spec": "3.8.0",
+    "@decantr/registry": "3.8.0"
   },
   "scripts": {
     "build": "tsup",

package/server.json

@@ -0,0 +1,20 @@
+{
+  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
+  "name": "io.github.decantr-ai/mcp-server",
+  "description": "AI Frontend Governance for codebases touched by AI agents. Serves Contract context, typed graph artifacts, drift evidence, and repair prompts.",
+  "repository": {
+    "url": "https://github.com/decantr-ai/decantr",
+    "source": "github"
+  },
+  "version": "3.8.0",
+  "packages": [
+    {
+      "registryType": "npm",
+      "identifier": "@decantr/mcp-server",
+      "version": "3.8.0",
+      "transport": {
+        "type": "stdio"
+      }
+    }
+  ]
+}