@pipeworx/mcp-data360 0.1.2 → 0.1.4

package/README.md

@@ -2,7 +2,7 @@
 
 World Bank Data360 MCP — the World Bank's modern unified data platform.
 
-Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1683+ live data sources.
+Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1854+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
 
 ## Tools
 
@@ -56,7 +56,7 @@ directly, instead of just this one's:
 }
 ```
 
-Both URLs reach the same gateway and the same 1683+ data sources. The
+Both URLs reach the same gateway and the same 1854+ data sources. The
 only difference is which pack's tools are listed **directly**; `ask_pipeworx`
 reaches all of them from either one.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pipeworx/mcp-data360",
-  "version": "0.1.2",
+  "version": "0.1.4",
   "description": "World Bank Data360 MCP — the World Bank's modern unified data platform.",
   "type": "module",
   "main": "src/index.ts",
@@ -26,7 +26,7 @@
     "@cloudflare/workers-types": "^4.20260405.1"
   },
   "pipeworx": {
-    "sourceHash": "v1-61d39d1cf7fa43ecbd2836e19c734b143647b67ff511a68979ea6f88a8a0de97",
-    "sourceCommit": "56d3c46c09bb3078ffdbdbca992a93f406bcd382"
+    "sourceHash": "v1-1511cd1832ee85fadcceee3343e69d08d9d9cd3b0ba78476982edcd1ebdfd01c",
+    "sourceCommit": "8355bf3d1eece256a62a89dba2278e7a77bebe07"
   }
 }

package/server.json

@@ -3,7 +3,7 @@
   "name": "io.github.pipeworx-io/data360",
   "title": "Data360",
   "description": "World Bank Data360 MCP — the World Bank's modern unified data platform.",
-  "version": "0.1.2",
+  "version": "0.1.4",
   "websiteUrl": "https://pipeworx.io/packs/data360",
   "repository": {
     "url": "https://github.com/pipeworx-io/mcp-data360",

package/src/index.ts

@@ -670,6 +670,254 @@ function pickMessage(node: unknown, depth: number): string | null {
 function collapse(s: string): string {
   return s.replace(/\s+/g, ' ').trim();
 }
+
+// ── Bounded readers — peak memory, not just wall time (fleet #3322) ──────
+//
+// `parseJson` above does `await res.text()` then `JSON.parse(raw)`, so a
+// multi-megabyte upstream body is held TWICE at peak: once as the raw string
+// and once as the object graph (which for an array of small objects runs
+// several times the byte size). Nothing in `workers/gateway` can see that
+// peak — it happens inside the pack, before any gateway code holds a payload —
+// which is why the gateway-side payload caps of #3293 and #3320 did not move
+// the 503/1102 rate at all.
+//
+// Measured on the live gateway, 2026-10-19, sha fa5de5c34, direct tools/call:
+//   statcan_list_cubes  8,049,566 B   <- one upstream array, no limit argument
+//   gnomad_gene BRCA1   2,732,706 B
+// Five of those in flight at the quality runner's width is ~40 MB of parse
+// peak against a 128 MB isolate; Cloudflare kills the isolate and every
+// request in flight returns 503/1102, which is why the victims look random.
+//
+// `readJsonArrayPrefix` is the fix for the dominant shape: an upstream that
+// returns one enormous top-level JSON array with no server-side paging. It
+// parses elements off the stream and DISCARDS the consumed bytes, so peak
+// retained memory is one element plus one chunk rather than the whole body,
+// and it cancels the body as soon as it has what it was asked for.
+
+/** Default ceiling for a single upstream JSON body read into an isolate.
+ *  Chosen so the known tail (statcan 8.0 MB, gnomad 2.7 MB) is bounded well
+ *  below the point where a handful of concurrent reads exhausts 128 MB. */
+const DEFAULT_MAX_JSON_BYTES = 1_500_000;
+
+interface JsonArrayPrefix<T> {
+  /** The decoded elements, at most `maxItems` of them. */
+  items: T[];
+  /** True when the upstream array had more elements than we read. */
+  truncated: boolean;
+  /** Bytes actually pulled off the socket — the number that bounds memory. */
+  bytesRead: number;
+  /** `Content-Length` if the upstream declared one, else null. */
+  declaredBytes: number | null;
+}
+
+/**
+ * Read the FIRST `maxItems` elements of a top-level JSON array off a response
+ * stream without ever materialising the whole body.
+ *
+ * Use this instead of `parseJson` when the upstream returns one big array and
+ * offers no `limit`/`offset` of its own. Peak retained memory is one element
+ * plus the current chunk; the body is cancelled as soon as `maxItems` is
+ * reached, so the remaining megabytes are never transferred at all.
+ *
+ *     const { items, truncated } = await readJsonArrayPrefix<Cube>(
+ *       res, 'StatCan WDS', { maxItems: limit + offset });
+ *
+ * `maxBytes` is a second, independent backstop for a pathological element (a
+ * single 50 MB object): hitting it stops the read and sets `truncated`, rather
+ * than throwing, because a partial answer plus an explicit truncated flag is
+ * more useful to a caller than an error.
+ */
+async function readJsonArrayPrefix<T>(
+  res: Response,
+  name: string,
+  opts: { maxItems: number; maxBytes?: number },
+): Promise<JsonArrayPrefix<T>> {
+  const maxBytes = opts.maxBytes ?? DEFAULT_MAX_JSON_BYTES;
+  const declaredRaw = Number(res.headers.get('content-length'));
+  const declaredBytes = Number.isFinite(declaredRaw) && declaredRaw > 0 ? declaredRaw : null;
+
+  // No streaming body available (a mock, or an already-buffered response):
+  // fall back to the whole-text path so behaviour stays correct, just unbounded.
+  if (!res.body) {
+    const all = await parseJson<T[]>(res, name);
+    if (!Array.isArray(all)) throw new Error(`upstream_down: ${name} returned ${typeof all} where a JSON array was expected.`);
+    return {
+      items: all.slice(0, opts.maxItems),
+      truncated: all.length > opts.maxItems,
+      bytesRead: declaredBytes ?? 0,
+      declaredBytes,
+    };
+  }
+
+  const reader = res.body.getReader();
+  const decoder = new TextDecoder();
+  const items: T[] = [];
+
+  let buf = '';
+  let scan = 0;
+  let bytesRead = 0;
+  let started = false; // consumed the opening '['
+  let arrayEnded = false;
+  let depth = 0;
+  let inStr = false;
+  let esc = false;
+  let elemStart = -1;
+  let truncated = false;
+
+  const push = (text: string) => {
+    const t = text.trim();
+    if (!t) return;
+    items.push(JSON.parse(t) as T);
+  };
+
+  try {
+    outer: while (items.length < opts.maxItems && !arrayEnded) {
+      const { value, done } = await reader.read();
+      if (done) break;
+      bytesRead += value.byteLength;
+      buf += decoder.decode(value, { stream: true });
+      if (bytesRead > maxBytes) { truncated = true; break; }
+
+      for (; scan < buf.length; scan++) {
+        const ch = buf[scan];
+
+        if (inStr) {
+          if (esc) { esc = false; continue; }
+          if (ch === '\\') { esc = true; continue; }
+          if (ch === '"') inStr = false;
+          continue;
+        }
+
+        if (!started) {
+          if (ch === '[') { started = true; continue; }
+          if (ch.trim() === '') continue;
+          throw new Error(
+            `upstream_down: ${name} returned a body that does not begin with a JSON array (saw ${JSON.stringify(ch)}). ` +
+              'This reader is only for upstreams that answer with one top-level array.',
+          );
+        }
+
+        if (ch === '"') { if (depth === 0 && elemStart < 0) elemStart = scan; inStr = true; continue; }
+
+        if (ch === '{' || ch === '[') {
+          if (depth === 0 && elemStart < 0) elemStart = scan;
+          depth++;
+          continue;
+        }
+
+        if (ch === '}' || ch === ']') {
+          if (depth > 0) {
+            depth--;
+            if (depth === 0 && elemStart >= 0) {
+              push(buf.slice(elemStart, scan + 1));
+              elemStart = -1;
+              if (items.length >= opts.maxItems) { truncated = true; scan++; break outer; }
+            }
+            continue;
+          }
+          // depth 0 and a closing bracket: the end of the top-level array.
+          if (elemStart >= 0) { push(buf.slice(elemStart, scan)); elemStart = -1; }
+          arrayEnded = true;
+          break outer;
+        }
+
+        if (ch === ',' && depth === 0) {
+          if (elemStart >= 0) {
+            push(buf.slice(elemStart, scan));
+            elemStart = -1;
+            if (items.length >= opts.maxItems) { truncated = true; scan++; break outer; }
+          }
+          continue;
+        }
+
+        // A bare scalar element (number / true / false / null).
+        if (depth === 0 && elemStart < 0 && ch.trim() !== '') elemStart = scan;
+      }
+
+      // Drop everything already consumed. THIS is what bounds memory: without
+      // it `buf` grows to the full body and the reader is streaming in name only.
+      if (elemStart >= 0) {
+        buf = buf.slice(elemStart);
+        scan -= elemStart;
+        elemStart = 0;
+      } else {
+        buf = buf.slice(scan);
+        scan = 0;
+      }
+    }
+  } finally {
+    // Cancel rather than drain: the point is that the remaining megabytes are
+    // never transferred. A cancel on an already-finished body is a no-op.
+    await reader.cancel().catch(() => {});
+  }
+
+  return { items, truncated, bytesRead, declaredBytes };
+}
+
+/**
+ * `parseJson`, with a hard ceiling on how many bytes are read.
+ *
+ * For an upstream whose body is not a single array (so `readJsonArrayPrefix`
+ * does not apply) but which can still answer with megabytes. Unlike the array
+ * reader this one THROWS when the cap is hit, because a truncated prefix of an
+ * arbitrary JSON document is not parseable and there is no partial answer to
+ * hand back. A declared `Content-Length` over the cap is refused before a
+ * single chunk is read.
+ */
+async function parseJsonBounded<T>(
+  res: Response,
+  name: string,
+  maxBytes: number = DEFAULT_MAX_JSON_BYTES,
+): Promise<T> {
+  const declaredRaw = Number(res.headers.get('content-length'));
+  const declared = Number.isFinite(declaredRaw) && declaredRaw > 0 ? declaredRaw : null;
+
+  const tooBig = (n: number) =>
+    new Error(
+      `upstream_down: ${name} answered with ${n.toLocaleString()} bytes, over this pack's ${maxBytes.toLocaleString()}-byte ceiling. ` +
+        'The body is not read past the ceiling on purpose — a few concurrent reads of a body that size exhaust the ' +
+        'Worker isolate and take every other in-flight request down with them. Narrow the request (a smaller range, ' +
+        'a specific id, or a lower limit) and retry.',
+    );
+
+  if (declared !== null && declared > maxBytes) {
+    await res.body?.cancel().catch(() => {});
+    throw tooBig(declared);
+  }
+  if (!res.body) return parseJson<T>(res, name);
+
+  const reader = res.body.getReader();
+  const decoder = new TextDecoder();
+  let raw = '';
+  let bytesRead = 0;
+  try {
+    for (;;) {
+      const { value, done } = await reader.read();
+      if (done) break;
+      bytesRead += value.byteLength;
+      if (bytesRead > maxBytes) throw tooBig(bytesRead);
+      raw += decoder.decode(value, { stream: true });
+    }
+    raw += decoder.decode();
+  } finally {
+    await reader.cancel().catch(() => {});
+  }
+
+  if (!raw.trim()) {
+    throw new Error(
+      `upstream_down: ${name} answered HTTP ${res.status} with an EMPTY body where JSON was expected. ` +
+        'Nothing about the request can cause this — it is an upstream fault, and the same call may well work on retry.',
+    );
+  }
+  try {
+    return JSON.parse(raw) as T;
+  } catch {
+    throw new Error(
+      `upstream_down: ${name} answered HTTP ${res.status} with a body that is not valid JSON. ` +
+        `It begins: ${stripMarkup(raw).slice(0, 120) || '(unreadable)'}`,
+    );
+  }
+}
 /**
  * World Bank Data360 MCP — the World Bank's modern unified data platform.
  *
@@ -796,7 +1044,39 @@ async function callTool(name: string, args: Record<string, unknown>): Promise<un
       if (period) params.set('TIME_PERIOD', period);
       params.set('skip', String(numArg(args.skip, 0)));
       params.set('top', String(numArg(args.top, 100)));
-      return get(`/data?${params.toString()}`);
+      const res = await pwFetch(`${BASE}/data?${params.toString()}`, {
+        headers: { Accept: 'application/json', 'User-Agent': UA },
+      });
+      if (!res.ok) {
+        const text = await res.text();
+        // Data360 answers an unknown DATABASE_ID with 417 EA500001 "Data
+        // retrieval failed" -- the same body it sends on a real outage, so the
+        // body cannot tell them apart. Check the id against the database list
+        // and only call it not_found when it is genuinely absent (fleet #2497).
+        const dbId = params.get('DATABASE_ID')!;
+        const known = await databaseIds().catch(() => null);
+        if (known && !known.includes(dbId)) {
+          const near = known.find((k) => k.toLowerCase() === dbId.toLowerCase());
+          return {
+            error: 'not_found',
+            message: near
+              ? `Data360 has no database "${dbId}" -- ids are case-sensitive; did you mean "${near}"?`
+              : `Data360 has no database "${dbId}". Call data360_list_databases for valid DATABASE_IDs (e.g. "WB_WDI").`,
+            DATABASE_ID: dbId,
+          };
+        }
+        throw new Error(`Data360: ${res.status} ${text.slice(0, 200)}`);
+      }
+      const data = (await res.json()) as { count?: number; value?: unknown[] };
+      if ((data.count ?? data.value?.length ?? 0) === 0) {
+        // An unknown INDICATOR / REF_AREA pair is a 200 with zero rows, not an error.
+        return {
+          ...data,
+          empty_reason: 'no_match',
+          note: `No observations for INDICATOR "${params.get('INDICATOR')}" in ${params.get('DATABASE_ID')} for REF_AREA "${params.get('REF_AREA')}"${period ? ` in ${period}` : ''}. Check the code with data360_search_indicators (database_id: "${params.get('DATABASE_ID')}"), or drop TIME_PERIOD.`,
+        };
+      }
+      return data;
     }
 
     default:
@@ -814,10 +1094,16 @@ async function searchPost(body: unknown): Promise<unknown> {
   return res.json();
 }
 
-async function get(path: string): Promise<unknown> {
-  const res = await pwFetch(`${BASE}${path}`, { headers: { Accept: 'application/json', 'User-Agent': UA } });
-  if (!res.ok) throw new Error(`Data360: ${res.status} ${await res.text().then((t) => t.slice(0, 200))}`);
-  return res.json();
+async function databaseIds(): Promise<string[]> {
+  const res = (await searchPost({
+    count: true,
+    search: '*',
+    top: 0,
+    facets: ['series_description/database_id,count:1000'],
+  })) as any;
+  const ids: Array<{ value: string }> = res?.['@search.facets']?.['series_description/database_id'] ?? [];
+  if (ids.length === 0) throw new Error('Data360 database list came back empty');
+  return ids.map((d) => d.value);
 }
 
 function reqStr(args: Record<string, unknown>, key: string, example: string): string {

package/src/server.ts

@@ -8,8 +8,9 @@ import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
 import { CallToolRequestSchema, ListToolsRequestSchema } from '@modelcontextprotocol/sdk/types.js';
 import pack from './index.js';
 
+
 const server = new Server(
-  { name: '@pipeworx/mcp-data360', version: '0.1.2' },
+  { name: '@pipeworx/mcp-data360', version: '0.1.4' },
   { capabilities: { tools: {} } },
 );
 
@@ -24,7 +25,9 @@ server.setRequestHandler(ListToolsRequestSchema, async () => ({
 server.setRequestHandler(CallToolRequestSchema, async (request) => {
   const { name, arguments: args } = request.params;
   try {
-    const result = await pack.callTool(name, (args ?? {}) as Record<string, unknown>);
+    const callArgs = { ...((args ?? {}) as Record<string, unknown>) };
+    
+    const result = await pack.callTool(name, callArgs);
     return { content: [{ type: 'text', text: JSON.stringify(result, null, 2) }] };
   } catch (err) {
     return {