@aborruso/ckan-mcp-server 0.4.130 → 0.4.131

package/LOG.md

@@ -1,7 +1,21 @@
 # LOG
 
+## 2026-10-22
+
+### v0.4.131
+
+Ships #563: Anubis challenge retry with an honest User-Agent (#7). Tests 595 passed, smoke 17/17.
+
+### Anubis-fronted portals: retry once with an honest User-Agent (#7)
+
+Reported by @umlwbin: our Chrome-impersonating headers (needed by dati.anticorruzione.it's WAF) trip Anubis anti-bot gates, which answer with an HTML proof-of-work page that axios cannot solve. Anubis challenges any UA containing `Mozilla`, including `Mozilla/5.0 (compatible; ...)`, so no fixed UA serves both portals. `makeCkanRequest` now detects the challenge page (`anubis_challenge` marker, `isAnubisChallenge`) and retries once with `CKAN-MCP-Server/1.0` and no `Sec-CH-UA*` headers, on both the axios and fetch/Workers paths. The retry acquires its own rate-limit token (Greptile review). +6 tests (fail without the fix). Tests 595 passed; e2e `package_search` OK on canwin-datahub.ad.umanitoba.ca/data (48,947), dati.anticorruzione.it (70), dati.gov.it.
+
 ## 2026-10-19
 
+### Advisory GHSA-w3gp-3hrh-v465 published
+
+Reported by @olevasseur, accepted and published as Medium (CVSS 6.5): affected `>= 0.4.114, <= 0.4.129`, patched `0.4.130`. CVE requested, not yet assigned. v0.4.130 is live on npm (with provenance), the MCP Registry and the Worker. `SECURITY.md` table updated.
+
 ### v0.4.130
 
 Ships #561: linear shrink in `truncateJson` (GHSA-w3gp-3hrh-v465). Tests 589 passed, smoke 17/17.

package/dist/index.js

@@ -932,6 +932,11 @@ function auditLog(serverUrl, action, params, cacheHit) {
   } catch {
   }
 }
+var BROWSER_USER_AGENT = "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36";
+var HONEST_USER_AGENT = "CKAN-MCP-Server/1.0";
+function isAnubisChallenge(body) {
+  return typeof body === "string" && body.includes("anubis_challenge");
+}
 async function makeCkanRequest(serverUrl, action, params = {}, opts = {}) {
   const isNode = typeof process !== "undefined" && !!process.versions?.node;
   validateServerUrl(serverUrl);
@@ -963,95 +968,106 @@ async function makeCkanRequest(serverUrl, action, params = {}, opts = {}) {
   _lastCacheHit = false;
   const rateLimitConfig = getRateLimitConfig();
   const rateLimitEnabled = rateLimitConfig.enabled && opts.rateLimit !== false;
-  if (rateLimitEnabled) {
-    const hostname = new URL(resolvedServerUrl).hostname;
-    await getRateLimiter().acquire(hostname);
-  }
+  const acquireRateToken = async () => {
+    if (rateLimitEnabled) {
+      const hostname = new URL(resolvedServerUrl).hostname;
+      await getRateLimiter().acquire(hostname);
+    }
+  };
+  await acquireRateToken();
   try {
-    let decodedData;
-    if (isNode) {
-      const safeAgents = await getSafeAgents();
-      const response = await axios.get(url, {
-        params,
-        timeout: 3e4,
-        responseType: "arraybuffer",
-        maxRedirects: 5,
-        // Re-validate every redirect hop: Node skips the agent's `lookup` for IP
-        // literals, so a public host 302-ing to e.g. 169.254.169.254 would otherwise
-        // be followed. Also enforces CKAN_ALLOWED_DOMAINS on redirect targets.
-        beforeRedirect: (redirectOptions) => {
-          validateServerUrl(redirectOptions.href);
-        },
-        // Never route through HTTP_PROXY/HTTPS_PROXY: a proxy would connect to the
-        // target itself, bypassing the SSRF-safe lookup pinned in the agents below.
-        proxy: false,
-        maxContentLength: MAX_RESPONSE_BYTES,
-        maxBodyLength: MAX_RESPONSE_BYTES,
-        ...safeAgents ? { httpAgent: safeAgents.httpAgent, httpsAgent: safeAgents.httpsAgent } : {},
-        headers: {
-          Accept: "application/json, text/plain, */*",
-          "Accept-Language": "en-US,en;q=0.9,it;q=0.8",
-          "Accept-Encoding": "gzip, deflate, br",
-          Connection: "keep-alive",
-          "Sec-CH-UA": '"Chromium";v="120", "Not?A_Brand";v="24", "Google Chrome";v="120"',
-          "Sec-CH-UA-Mobile": "?0",
-          "Sec-CH-UA-Platform": '"Linux"',
-          "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
-        }
-      });
-      decodedData = await decodePossiblyCompressed(
-        response.data,
-        response.headers
-      );
-    } else {
-      const searchParams = new URLSearchParams();
-      for (const [key, value] of Object.entries(params)) {
-        if (value === void 0 || value === null) {
-          continue;
-        }
-        searchParams.set(key, String(value));
-      }
-      const fetchUrl = searchParams.toString() ? `${url}?${searchParams.toString()}` : url;
-      const controller = new AbortController();
-      const timeoutId = setTimeout(() => controller.abort(), 3e4);
-      let response;
-      try {
-        response = await safeFetch(fetchUrl, {
-          method: "GET",
-          signal: controller.signal,
+    const fetchDecoded = async (honest) => {
+      if (isNode) {
+        const safeAgents = await getSafeAgents();
+        const response = await axios.get(url, {
+          params,
+          timeout: 3e4,
+          responseType: "arraybuffer",
+          maxRedirects: 5,
+          // Re-validate every redirect hop: Node skips the agent's `lookup` for IP
+          // literals, so a public host 302-ing to e.g. 169.254.169.254 would otherwise
+          // be followed. Also enforces CKAN_ALLOWED_DOMAINS on redirect targets.
+          beforeRedirect: (redirectOptions) => {
+            validateServerUrl(redirectOptions.href);
+          },
+          // Never route through HTTP_PROXY/HTTPS_PROXY: a proxy would connect to the
+          // target itself, bypassing the SSRF-safe lookup pinned in the agents below.
+          proxy: false,
+          maxContentLength: MAX_RESPONSE_BYTES,
+          maxBodyLength: MAX_RESPONSE_BYTES,
+          ...safeAgents ? { httpAgent: safeAgents.httpAgent, httpsAgent: safeAgents.httpsAgent } : {},
           headers: {
             Accept: "application/json, text/plain, */*",
-            "Accept-Encoding": "identity",
-            "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+            "Accept-Language": "en-US,en;q=0.9,it;q=0.8",
+            "Accept-Encoding": "gzip, deflate, br",
+            Connection: "keep-alive",
+            ...honest ? {} : {
+              "Sec-CH-UA": '"Chromium";v="120", "Not?A_Brand";v="24", "Google Chrome";v="120"',
+              "Sec-CH-UA-Mobile": "?0",
+              "Sec-CH-UA-Platform": '"Linux"'
+            },
+            "User-Agent": honest ? HONEST_USER_AGENT : BROWSER_USER_AGENT
           }
-        }, { maxHops: 5 });
-      } catch (error) {
-        if (controller.signal.aborted) {
-          throw new CkanTransportError(`Request timeout connecting to ${serverUrl}`, serverUrl);
+        });
+        return decodePossiblyCompressed(
+          response.data,
+          response.headers
+        );
+      } else {
+        const searchParams = new URLSearchParams();
+        for (const [key, value] of Object.entries(params)) {
+          if (value === void 0 || value === null) {
+            continue;
+          }
+          searchParams.set(key, String(value));
         }
-        if (error instanceof TypeError) {
-          throw new CkanTransportError(`Network error: ${error.message}`, serverUrl);
+        const fetchUrl = searchParams.toString() ? `${url}?${searchParams.toString()}` : url;
+        const controller = new AbortController();
+        const timeoutId = setTimeout(() => controller.abort(), 3e4);
+        let response;
+        try {
+          response = await safeFetch(fetchUrl, {
+            method: "GET",
+            signal: controller.signal,
+            headers: {
+              Accept: "application/json, text/plain, */*",
+              "Accept-Encoding": "identity",
+              "User-Agent": honest ? HONEST_USER_AGENT : BROWSER_USER_AGENT
+            }
+          }, { maxHops: 5 });
+        } catch (error) {
+          if (controller.signal.aborted) {
+            throw new CkanTransportError(`Request timeout connecting to ${serverUrl}`, serverUrl);
+          }
+          if (error instanceof TypeError) {
+            throw new CkanTransportError(`Network error: ${error.message}`, serverUrl);
+          }
+          throw error;
+        } finally {
+          clearTimeout(timeoutId);
         }
-        throw error;
-      } finally {
-        clearTimeout(timeoutId);
-      }
-      if (!response.ok) {
-        throw new CkanApiError(`CKAN API error (${response.status}): ${response.statusText}`, response.status, action, serverUrl);
-      }
-      const declaredLength = Number(response.headers.get("content-length"));
-      if (Number.isFinite(declaredLength) && declaredLength > MAX_RESPONSE_BYTES) {
-        throw new CkanApiError(`Response too large (${declaredLength} bytes)`, void 0, action, serverUrl);
-      }
-      const buffer = await response.arrayBuffer();
-      if (buffer.byteLength > MAX_RESPONSE_BYTES) {
-        throw new CkanApiError(`Response too large (${buffer.byteLength} bytes)`, void 0, action, serverUrl);
+        if (!response.ok) {
+          throw new CkanApiError(`CKAN API error (${response.status}): ${response.statusText}`, response.status, action, serverUrl);
+        }
+        const declaredLength = Number(response.headers.get("content-length"));
+        if (Number.isFinite(declaredLength) && declaredLength > MAX_RESPONSE_BYTES) {
+          throw new CkanApiError(`Response too large (${declaredLength} bytes)`, void 0, action, serverUrl);
+        }
+        const buffer = await response.arrayBuffer();
+        if (buffer.byteLength > MAX_RESPONSE_BYTES) {
+          throw new CkanApiError(`Response too large (${buffer.byteLength} bytes)`, void 0, action, serverUrl);
+        }
+        const headers = {};
+        response.headers.forEach((headerValue, headerKey) => {
+          headers[headerKey] = headerValue;
+        });
+        return decodePossiblyCompressed(buffer, headers);
       }
-      const headers = {};
-      response.headers.forEach((headerValue, headerKey) => {
-        headers[headerKey] = headerValue;
-      });
-      decodedData = await decodePossiblyCompressed(buffer, headers);
+    };
+    let decodedData = await fetchDecoded(false);
+    if (isAnubisChallenge(decodedData)) {
+      await acquireRateToken();
+      decodedData = await fetchDecoded(true);
     }
     if (decodedData && decodedData.success === true) {
       const result = decodedData.result;
@@ -6101,7 +6117,7 @@ var registerAllPrompts = (server) => {
 function createServer() {
   return new McpServer({
     name: "ckan-mcp-server",
-    version: "0.4.130"
+    version: "0.4.131"
   });
 }
 function registerAll(server) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aborruso/ckan-mcp-server",
-  "version": "0.4.130",
+  "version": "0.4.131",
   "mcpName": "io.github.aborruso/ckan-mcp-server",
   "description": "MCP server for interacting with CKAN open data portals",
   "repository": {