@yawlabs/mcp-compliance 0.9.1 → 0.9.2

package/dist/{chunk-CH2E27X5.js → chunk-FKTEFLK5.js}

@@ -1228,14 +1228,20 @@ var STDIO_INCOMPATIBLE_IDS = /* @__PURE__ */ new Set([
   "error-parse-code",
   "error-invalid-request-code",
   // Security tests that are inherently HTTP-layer (auth headers,
-  // sessions, CORS, TLS, rate limits, RFC 9728 metadata).
+  // sessions, CORS, TLS, rate limits, RFC 9728 metadata). For stdio
+  // servers these don't apply — the parent process owns the trust
+  // boundary, not the server.
   "security-tls-required",
   "security-oauth-metadata",
   "security-token-in-uri",
   "security-rate-limiting",
   "security-cors-headers",
   "security-origin-validation",
-  "security-session-not-auth"
+  "security-session-not-auth",
+  "security-auth-required",
+  "security-auth-malformed",
+  "security-www-authenticate",
+  "security-session-entropy"
 ]);
 function supportsTransport(def, kind) {
   if (!def) return true;
@@ -1299,8 +1305,11 @@ async function runComplianceSuite(target, options = {}) {
         return !options.skip.includes(category) && !options.skip.includes(id);
       }
       return true;
+    }, looksRejected2 = function(text, isErrorFlag) {
+      if (isErrorFlag) return true;
+      return REJECTION_PATTERNS.some((p) => p.test(text));
     };
-    var buildHeaders = buildHeaders2, shouldRun = shouldRun2;
+    var buildHeaders = buildHeaders2, shouldRun = shouldRun2, looksRejected = looksRejected2;
     const backendUrl = resolvedTarget.type === "http" ? resolvedTarget.url : "";
     const userHeaders = resolvedTarget.type === "http" ? resolvedTarget.headers ?? options.headers ?? {} : {};
     const displayUrl = resolvedTarget.type === "http" ? resolvedTarget.url : `stdio:${resolvedTarget.command}${resolvedTarget.args?.length ? ` ${resolvedTarget.args.join(" ")}` : ""}`;
@@ -3284,25 +3293,50 @@ async function runComplianceSuite(target, options = {}) {
         }
       }
     );
+    const REJECTION_PATTERNS = [
+      /access denied/i,
+      /permission denied/i,
+      /not allowed/i,
+      /not permitted/i,
+      /outside (allowed|permitted)/i,
+      /forbidden/i,
+      /unauthorized/i,
+      /invalid (path|input|argument|parameter|request)/i,
+      /(payload|request) (rejected|blocked|refused)/i,
+      /enoent|eacces|eperm/i,
+      /sandbox(ed)?/i,
+      /(no such file|file not found)/i,
+      /\binvalid\b.*\b(input|json|argument|parameter|character)/i
+    ];
     async function runInjectionTest(toolName, paramName, payloads, detectPattern, label) {
       const issues = [];
+      let defended = 0;
       for (const payload of payloads) {
         try {
           const res = await rpc("tools/call", { name: toolName, arguments: { [paramName]: payload } });
-          const content = res.body?.result?.content;
+          const result = res.body?.result;
+          const content = result?.content;
+          const isErrorFlag = result?.isError === true;
           if (Array.isArray(content)) {
             const text = content.map((c) => c.text || "").join(" ");
             if (detectPattern.test(text)) {
-              issues.push(`Payload "${payload}" ${label} (output: ${text.substring(0, 100)})`);
+              if (looksRejected2(text, isErrorFlag)) {
+                defended++;
+              } else {
+                issues.push(`Payload "${payload}" ${label} (output: ${text.substring(0, 100)})`);
+              }
+            } else {
+              defended++;
             }
           }
         } catch {
+          defended++;
         }
       }
       if (issues.length > 0) return { passed: false, details: issues.join("; ") };
       return {
         passed: true,
-        details: `Tested ${payloads.length} payloads against ${toolName}.${paramName} \u2014 no ${label.split(" ")[0]} detected`
+        details: defended === payloads.length ? `Tested ${payloads.length} payloads against ${toolName}.${paramName} \u2014 server defended (rejected or sanitized)` : `Tested ${payloads.length} payloads against ${toolName}.${paramName} \u2014 no ${label.split(" ")[0]} detected`
       };
     }
     if (toolNames.length > 0) {

package/dist/index.js

@@ -1372,14 +1372,20 @@ var STDIO_INCOMPATIBLE_IDS = /* @__PURE__ */ new Set([
   "error-parse-code",
   "error-invalid-request-code",
   // Security tests that are inherently HTTP-layer (auth headers,
-  // sessions, CORS, TLS, rate limits, RFC 9728 metadata).
+  // sessions, CORS, TLS, rate limits, RFC 9728 metadata). For stdio
+  // servers these don't apply — the parent process owns the trust
+  // boundary, not the server.
   "security-tls-required",
   "security-oauth-metadata",
   "security-token-in-uri",
   "security-rate-limiting",
   "security-cors-headers",
   "security-origin-validation",
-  "security-session-not-auth"
+  "security-session-not-auth",
+  "security-auth-required",
+  "security-auth-malformed",
+  "security-www-authenticate",
+  "security-session-entropy"
 ]);
 function supportsTransport(def, kind) {
   if (!def) return true;
@@ -1443,8 +1449,11 @@ async function runComplianceSuite(target, options = {}) {
         return !options.skip.includes(category) && !options.skip.includes(id);
       }
       return true;
+    }, looksRejected2 = function(text, isErrorFlag) {
+      if (isErrorFlag) return true;
+      return REJECTION_PATTERNS.some((p) => p.test(text));
     };
-    var buildHeaders = buildHeaders2, shouldRun = shouldRun2;
+    var buildHeaders = buildHeaders2, shouldRun = shouldRun2, looksRejected = looksRejected2;
     const backendUrl = resolvedTarget.type === "http" ? resolvedTarget.url : "";
     const userHeaders = resolvedTarget.type === "http" ? resolvedTarget.headers ?? options.headers ?? {} : {};
     const displayUrl = resolvedTarget.type === "http" ? resolvedTarget.url : `stdio:${resolvedTarget.command}${resolvedTarget.args?.length ? ` ${resolvedTarget.args.join(" ")}` : ""}`;
@@ -3428,25 +3437,50 @@ async function runComplianceSuite(target, options = {}) {
         }
       }
     );
+    const REJECTION_PATTERNS = [
+      /access denied/i,
+      /permission denied/i,
+      /not allowed/i,
+      /not permitted/i,
+      /outside (allowed|permitted)/i,
+      /forbidden/i,
+      /unauthorized/i,
+      /invalid (path|input|argument|parameter|request)/i,
+      /(payload|request) (rejected|blocked|refused)/i,
+      /enoent|eacces|eperm/i,
+      /sandbox(ed)?/i,
+      /(no such file|file not found)/i,
+      /\binvalid\b.*\b(input|json|argument|parameter|character)/i
+    ];
     async function runInjectionTest(toolName, paramName, payloads, detectPattern, label) {
       const issues = [];
+      let defended = 0;
       for (const payload of payloads) {
         try {
           const res = await rpc("tools/call", { name: toolName, arguments: { [paramName]: payload } });
-          const content = res.body?.result?.content;
+          const result = res.body?.result;
+          const content = result?.content;
+          const isErrorFlag = result?.isError === true;
           if (Array.isArray(content)) {
             const text = content.map((c) => c.text || "").join(" ");
             if (detectPattern.test(text)) {
-              issues.push(`Payload "${payload}" ${label} (output: ${text.substring(0, 100)})`);
+              if (looksRejected2(text, isErrorFlag)) {
+                defended++;
+              } else {
+                issues.push(`Payload "${payload}" ${label} (output: ${text.substring(0, 100)})`);
+              }
+            } else {
+              defended++;
             }
           }
         } catch {
+          defended++;
         }
       }
       if (issues.length > 0) return { passed: false, details: issues.join("; ") };
       return {
         passed: true,
-        details: `Tested ${payloads.length} payloads against ${toolName}.${paramName} \u2014 no ${label.split(" ")[0]} detected`
+        details: defended === payloads.length ? `Tested ${payloads.length} payloads against ${toolName}.${paramName} \u2014 server defended (rejected or sanitized)` : `Tested ${payloads.length} payloads against ${toolName}.${paramName} \u2014 no ${label.split(" ")[0]} detected`
       };
     }
     if (toolNames.length > 0) {

package/dist/mcp/server.js

@@ -2,7 +2,7 @@ import {
   SPEC_BASE,
   TEST_DEFINITIONS,
   runComplianceSuite
-} from "../chunk-CH2E27X5.js";
+} from "../chunk-FKTEFLK5.js";
 
 // src/mcp/server.ts
 import { existsSync, readFileSync } from "fs";

package/dist/runner.js

@@ -8,7 +8,7 @@ import {
   parseSSEResponse,
   previewTests,
   runComplianceSuite
-} from "./chunk-CH2E27X5.js";
+} from "./chunk-FKTEFLK5.js";
 export {
   SPEC_BASE,
   SPEC_VERSION,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yawlabs/mcp-compliance",
-  "version": "0.9.1",
+  "version": "0.9.2",
   "description": "CLI tool and MCP server that tests MCP servers for spec compliance",
   "license": "MIT",
   "author": "Yaw Labs <contact@yaw.sh> (https://yaw.sh)",