Hide Alexandria capability prices by default; add includeCosts to find_tools

CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## [3.30.1] - 2026-10-14
+
+### Added
+
+- `firecrawl_find_tools` accepts `includeCosts`. When it is `true`, tool results carry per-capability credit prices as before, and `nextTool` arguments keep the flag. The server handles it locally and does not send it upstream.
+
+### Changed
+
+- Alexandria output omits per-capability credit prices by default. `creditsCost`, `perRecord`, `billing`, `recordsPerUnit` and `zeroDataRetentionCreditsCost` are dropped from `firecrawl_find_tools` items and related tools, from `data.tools` in `firecrawl_search` and URL-mode `firecrawl_scrape`, and from each Alexandria result entry. Execution request totals such as `data.creditsCost` are unchanged; the free `firecrawl_find_tools` response omits its zero total.
+- Hosted instructions say Alexandria execution is billed per capability, replacing "billed at the capability's listed price".
+
 ## [3.30.0] - 2026-10-14
 
 ### Added

README.md

@@ -1112,14 +1112,16 @@ Start with no arguments for categories, then progressively narrow the catalogue:
 | --- | --- |
 | `{}` | Categories and short descriptions |
 | `{"categories":["podcasts"]}` | Providers in that category |
-| `{"categories":["podcasts"],"providers":["particle"]}` | Compact tool names, descriptions, and prices |
+| `{"categories":["podcasts"],"providers":["particle"]}` | Compact tool names and descriptions |
 | `{"providers":["particle"],"capabilities":["podcasts/episodes/search"]}` | Complete selected inputs, constraints, response, and examples |
 
 No group hop is required. Explicit `level` supports `categories`, `providers`,
 `groups`, or `tools`; explicit `expand` selects contract sections. `expand: []`
 keeps results compact even when selecting a capability. For broad full contracts,
 explicitly request `level: "tools"` and `expand: ["options", "response", "examples"]`.
-URLs provide contextual discovery without fetching the page.
+URLs provide contextual discovery without fetching the page. Tool results omit
+per-capability credit prices unless `includeCosts: true` is set; follow-up
+`nextTool` arguments keep it.
 
 Results are in `data.alexandria[0].data`. Follow an item's `nextTool` by calling
 its `name` with its `arguments`; the page's `nextTool` advances pagination.
@@ -1146,7 +1148,7 @@ These controls require the matching Alexandria API deployment.
 }
 ```
 
-**Returns:** `{ success, scrape_id, requestId, data: { alexandria: [...], creditsCost } }`. Each item is either a result (`provider`, `capability`, `creditsCost`, `data`, `records`, `upstreamStatus`) or an `error` with a `code`; the batch never fails as a whole for a provider error and `data.creditsCost` sums the successful items. Alexandria error bodies (403 without Alexandria access, and 402/409 billing statuses) are relayed in-band with their `code`.
+**Returns:** `{ success, scrape_id, requestId, data: { alexandria: [...], creditsCost } }`. Each item is either a result (`provider`, `capability`, `data`, `records`, `upstreamStatus`) or an `error` with a `code`; the batch never fails as a whole for a provider error and `data.creditsCost` is the total charged for the request. Alexandria error bodies (403 without Alexandria access, and 402/409 billing statuses) are relayed in-band with their `code`.
 
 Execution generates one `x-request-id` and returns it on success or failure. Retry
 the identical payload with that `requestId`; do not create a new ID after an

gemini-extension.json

@@ -1,6 +1,6 @@
 {
   "name": "firecrawl",
-  "version": "3.30.0",
+  "version": "3.30.1",
   "description": "Official Firecrawl MCP for web search, scraping, crawling, and structured data extraction.",
   "mcpServers": {
     "firecrawl": {

package.json

@@ -1,6 +1,6 @@
 {
   "name": "firecrawl-mcp",
-  "version": "3.30.0",
+  "version": "3.30.1",
   "description": "MCP server for Firecrawl — search, scrape, and interact with the web, and search scientific papers. Supports both cloud and self-hosted instances. Features include web search, scraping, page interaction, batch processing, LLM-powered content analysis, and research paper search over biomedical and arXiv literature (PubMed, bioRxiv, medRxiv, arXiv) with citation-graph expansion and full-text reading.",
   "type": "module",
   "mcpName": "io.github.firecrawl/firecrawl-mcp-server",

server.json

@@ -3,7 +3,7 @@
   "name": "io.github.firecrawl/firecrawl-mcp-server",
   "title": "Firecrawl MCP Server",
   "description": "MCP server for Firecrawl — web search, scraping, and biomedical/arXiv paper search.",
-  "version": "3.30.0",
+  "version": "3.30.1",
   "repository": {
     "url": "https://github.com/firecrawl/firecrawl-mcp-server.git",
     "source": "github"
@@ -12,7 +12,7 @@
     {
       "registryType": "npm",
       "identifier": "firecrawl-mcp",
-      "version": "3.30.0",
+      "version": "3.30.1",
       "transport": {
         "type": "stdio"
       },

src/alexandria.ts

@@ -58,6 +58,7 @@ export const findToolsSchema = z
     expand: z.array(z.enum(['options', 'response', 'examples'])).optional().describe('Use ["options", "response"] for inputs and output shape without example payloads; [] keeps results compact. Omit for full contracts on selected capabilities.'),
     limit: z.number().int().min(1).max(100).optional(),
     offset: z.number().int().nonnegative().optional(),
+    includeCosts: z.boolean().optional().describe('Include per-capability credit prices (creditsCost, perRecord) in tool results.'),
   })
   .strict();
 
@@ -81,17 +82,18 @@ export function findToolsOptions(args: z.infer<typeof findToolsSchema>) {
   if (level === 'categories' && (args.query || args.providers?.length || args.categories?.length || args.groups?.length || args.capabilities?.length || args.urls?.length || args.expand !== undefined)) {
     throw new Error('Category index accepts only level, limit and offset. Select a category to browse providers.');
   }
-  const { expand, ...selectors } = args;
+  // eslint-disable-next-line @typescript-eslint/no-unused-vars
+  const { expand, includeCosts, ...selectors } = args;
   return { ...selectors, ...(expand !== undefined ? { expand } : {}), level, limit: args.limit ?? 20,
     ...(args.expand === undefined && level === 'tools' && args.capabilities?.length ? { expand: ['options', 'response', 'examples'] as const } : {}),
   };
 }
 
-export function withFindToolsNavigation(envelope: any) {
+export function withFindToolsNavigation(envelope: any, carry: Record<string, unknown> = {}) {
   const page = envelope?.data?.alexandria?.[0]?.data;
   if (!page || !Array.isArray(page.items)) return envelope;
   const link = (next: any) => next?.provider === 'firecrawl' && next?.capability === 'find-tools' && next.options
-    ? { name: 'firecrawl_find_tools', arguments: next.options } : undefined;
+    ? { name: 'firecrawl_find_tools', arguments: { ...next.options, ...carry } } : undefined;
   for (const item of page.items) {
     if (page.level === 'providers' && link(item.next)) {
       const selectors = { ...item.next.options };
@@ -107,3 +109,62 @@ export function withFindToolsNavigation(envelope: any) {
 
 export const ALEXANDRIA_SEARCH_INSTRUCTIONS =
   'Authenticated search combines web results, semantic tool summaries and domain matches. Use sources: ["alexandria"] for semantic tools only. ' + ALEXANDRIA_SOURCES_OPT_OUT + ' Tool matches describe available structured-data capabilities, not executed data. toolDetail: "compact" (default) returns only provider, capability and description; "summary" adds metadata; "full" includes their input and output contracts. firecrawl_scrape with an alexandria body executes a selected capability; firecrawl_find_tools provides catalogue browsing and full contracts.';
+
+const TOOL_PRICE_KEYS = ['creditsCost', 'perRecord', 'billing', 'recordsPerUnit', 'zeroDataRetentionCreditsCost'];
+
+/** Drops per-capability price metadata from a discovered tool or an execution result entry. */
+export function withoutToolPrice(tool: any) {
+  if (!tool || typeof tool !== 'object' || Array.isArray(tool)) return tool;
+  const copy = { ...tool };
+  for (const key of TOOL_PRICE_KEYS) delete copy[key];
+  return copy;
+}
+
+/** Strips per-capability prices from `data.tools` in a search or URL scrape response. */
+export function withoutDiscoveredToolPrices(body: any) {
+  const tools = body?.data?.tools ?? body?.tools;
+  if (!Array.isArray(tools)) return body;
+  return body?.data?.tools
+    ? { ...body, data: { ...body.data, tools: tools.map(withoutToolPrice) } }
+    : { ...body, tools: tools.map(withoutToolPrice) };
+}
+
+function withoutPagePrices(page: any) {
+  if (!page || typeof page !== 'object') return page;
+  return {
+    ...page,
+    ...(Array.isArray(page.items) ? { items: page.items.map(withoutToolPrice) } : {}),
+    ...(Array.isArray(page.relatedTools) ? {
+      relatedTools: page.relatedTools.map((group: any) => Array.isArray(group?.tools)
+        ? { ...group, tools: group.tools.map((entry: any) => entry?.tool ? { ...entry, tool: withoutToolPrice(entry.tool) } : withoutToolPrice(entry)) }
+        : group),
+    } : {}),
+  };
+}
+
+/** Strips the per-capability cost from each Alexandria result entry, and tool prices from Find Tools pages. */
+export function withoutResultPrices(body: any) {
+  const results = body?.data?.alexandria;
+  if (!Array.isArray(results)) return body;
+  return {
+    ...body,
+    data: {
+      ...body.data,
+      alexandria: results.map((entry: any) => {
+        const stripped = withoutToolPrice(entry);
+        return entry?.provider === 'firecrawl' && entry?.capability === 'find-tools' && stripped && typeof stripped === 'object'
+          ? { ...stripped, data: withoutPagePrices(entry.data) }
+          : stripped;
+      }),
+    },
+  };
+}
+
+/** Find Tools is free; its envelope drops the zero total along with tool prices. */
+export function withoutFindToolsPrices(envelope: any) {
+  const stripped = withoutResultPrices(envelope);
+  if (!stripped?.data || typeof stripped.data !== 'object') return stripped;
+  const data = { ...stripped.data };
+  delete data.creditsCost;
+  return { ...stripped, data };
+}

src/server.ts

@@ -41,6 +41,9 @@ import {
   findToolsSchema,
   findToolsOptions,
   withFindToolsNavigation,
+  withoutDiscoveredToolPrices,
+  withoutFindToolsPrices,
+  withoutResultPrices,
   hasAlexandria,
   defaultDomainTools,
   normalizeSearchSources,
@@ -1487,7 +1490,7 @@ Alexandria mode, on an authenticated session with Alexandria access: \`alexandri
           },
           session
         );
-        return structuredText(json?.data ?? json);
+        return structuredText(withoutDiscoveredToolPrices(json?.data ?? json));
       }
       const client = getClient(session);
       const res = await relayTermsRequired(
@@ -1498,7 +1501,7 @@ Alexandria mode, on an authenticated session with Alexandria access: \`alexandri
           } as any),
         { tool: 'firecrawl_scrape' }
       );
-      return structuredText(res);
+      return structuredText(withoutDiscoveredToolPrices(res));
     },
   };
   server.addTool({
@@ -1616,7 +1619,7 @@ For a programming question, add \`categories: ["developer"]\`; its hits return i
         // identifier to keyless clients, where it would invite an unusable call.
         const keylessResponse = { ...(json ?? {}) };
         delete keylessResponse.id;
-        return structuredCompact(keylessResponse);
+        return structuredCompact(withoutDiscoveredToolPrices(keylessResponse));
       }
       // Call /v2/search through the SDK's HTTP layer (auth + retries) instead
       // of `client.search()` so we preserve the full response envelope. The
@@ -1633,7 +1636,7 @@ For a programming question, add \`categories: ["developer"]\`; its hits return i
       const httpRes = exchangeSource
         ? await relayExchangeError(postSearch, context)
         : await relayTermsRequired(postSearch, context);
-      return structuredCompact(httpRes?.data ?? {});
+      return structuredCompact(withoutDiscoveredToolPrices(httpRes?.data ?? {}));
     },
   });
 
@@ -1644,7 +1647,8 @@ For a programming question, add \`categories: ["developer"]\`; its hits return i
       | z.infer<typeof exchangeCallsSchema>,
     suppliedRequestId?: string,
     timeout?: number,
-    origin = requestOrigin(undefined, session)
+    origin = requestOrigin(undefined, session),
+    includeCosts = false
   ): Promise<string> {
     assertExchangeCredential(session);
     const client = getClient(session);
@@ -1667,7 +1671,7 @@ For a programming question, add \`categories: ["developer"]\`; its hits return i
       );
       const calls = Array.isArray(alexandria) ? alexandria : [alexandria];
       return alexandriaOutput(
-        { ...(response?.data ?? {}), requestId },
+        { ...(includeCosts ? (response?.data ?? {}) : withoutResultPrices(response?.data ?? {})), requestId },
         calls,
         async (body, id) => {
           const result = await (client as any).http.post(
@@ -1709,6 +1713,7 @@ For a programming question, add \`categories: ["developer"]\`; its hits return i
       let options;
       try { options = findToolsOptions(args as Parameters<typeof findToolsOptions>[0]); }
       catch (error) { throw new UserError(error instanceof Error ? error.message : String(error)); }
+      const carry: { includeCosts?: true } = (args as { includeCosts?: boolean }).includeCosts ? { includeCosts: true } : {};
       if (options.level === 'categories') {
         assertExchangeCredential(session);
         const response = await relayExchangeError(
@@ -1725,11 +1730,12 @@ For a programming question, add \`categories: ["developer"]\`; its hits return i
           next: { provider: 'firecrawl', capability: 'find-tools', options: { categories: [row.cohort], level: 'providers', limit: options.limit } },
         }));
         const page: any = { level: 'categories', items, total: rows.length };
-        if (offset + options.limit < rows.length) page.nextTool = { name: 'firecrawl_find_tools', arguments: { level: 'categories', limit: options.limit, offset: offset + options.limit } };
-        return structuredCompact(withAlexandriaFeedbackHint(withFindToolsNavigation({ success: true, data: { creditsCost: 0, alexandria: [{ provider: 'firecrawl', capability: 'find-tools', creditsCost: 0, data: page }] } }), alexandriaFeedbackAvailable()));
+        if (offset + options.limit < rows.length) page.nextTool = { name: 'firecrawl_find_tools', arguments: { level: 'categories', limit: options.limit, offset: offset + options.limit, ...carry } };
+        return structuredCompact(withAlexandriaFeedbackHint(withFindToolsNavigation({ success: true, data: { alexandria: [{ provider: 'firecrawl', capability: 'find-tools', data: page }] } }, carry), alexandriaFeedbackAvailable()));
       }
-      const result = await executeExchangeCalls(session, { provider: 'firecrawl', capability: 'find-tools', options }, undefined, undefined, origin);
-      return structuredCompact(withFindToolsNavigation(JSON.parse(result)));
+      const result = await executeExchangeCalls(session, { provider: 'firecrawl', capability: 'find-tools', options }, undefined, undefined, origin, carry.includeCosts);
+      const envelope = JSON.parse(result);
+      return structuredCompact(withFindToolsNavigation(carry.includeCosts ? envelope : withoutFindToolsPrices(envelope), carry));
     },
   };
   server.addTool(findToolsTool);

src/service/profiles.ts

@@ -58,7 +58,7 @@ export function getOAuthIssuer(): string {
 // uses them.
 export const SEARCH_PROFILE_INSTRUCTIONS =
   ALEXANDRIA_SEARCH_INSTRUCTIONS +
-  ` Firecrawl provides web, developer, government, and research search, and executes catalogued Alexandria data providers. Use firecrawl_search to find relevant results across the web and specialized indexes; authenticated searches also return matching Alexandria providers in data.tools. firecrawl_find_tools provides catalogue browsing and provider contracts; firecrawl_scrape with an alexandria body executes a selected capability; firecrawl_scrape with a url retrieves one supplied page. For a programming question, firecrawl_developer_search searches indexed public repositories, GitHub issues, merged pull requests, READMEs, and code documentation and returns the matched passages, and skills: "only" narrows it to agent-skill files; firecrawl_search with categories: ["developer"] reaches the same index beside ordinary web results, returning the hits in the web group rather than as passages and offering no skills filter. For a legal or regulatory question, firecrawl_gov_search searches primary law and regulatory material from US federal, state, and local government sources: statutes, regulations, codes, court opinions, and other government publications; firecrawl_search with categories: ["gov"] reaches the same sources in the web group and cannot be combined with other categories. For a biomedical, life-science, clinical, or arXiv literature question, the firecrawl_research_* tools search the paper index, while categories: ["research"] on firecrawl_search filters ordinary web results to research-affiliated websites. Use the firecrawl_research_* tools to search academic and research literature, expand from anchor papers via the citation graph, and read full-text passages from a specific paper. Search and discovery tools are read-only and return ranked results. Billing: web, developer, and research search are billed per request; government search is free; Alexandria discovery (firecrawl_search with sources ["alexandria"] alone, and firecrawl_find_tools) is free; firecrawl_scrape is billed, as a page retrieval in url mode or at each executed capability's listed price in alexandria mode.`;
+  ` Firecrawl provides web, developer, government, and research search, and executes catalogued Alexandria data providers. Use firecrawl_search to find relevant results across the web and specialized indexes; authenticated searches also return matching Alexandria providers in data.tools. firecrawl_find_tools provides catalogue browsing and provider contracts; firecrawl_scrape with an alexandria body executes a selected capability; firecrawl_scrape with a url retrieves one supplied page. For a programming question, firecrawl_developer_search searches indexed public repositories, GitHub issues, merged pull requests, READMEs, and code documentation and returns the matched passages, and skills: "only" narrows it to agent-skill files; firecrawl_search with categories: ["developer"] reaches the same index beside ordinary web results, returning the hits in the web group rather than as passages and offering no skills filter. For a legal or regulatory question, firecrawl_gov_search searches primary law and regulatory material from US federal, state, and local government sources: statutes, regulations, codes, court opinions, and other government publications; firecrawl_search with categories: ["gov"] reaches the same sources in the web group and cannot be combined with other categories. For a biomedical, life-science, clinical, or arXiv literature question, the firecrawl_research_* tools search the paper index, while categories: ["research"] on firecrawl_search filters ordinary web results to research-affiliated websites. Use the firecrawl_research_* tools to search academic and research literature, expand from anchor papers via the citation graph, and read full-text passages from a specific paper. Search and discovery tools are read-only and return ranked results. Billing: web, developer, and research search are billed per request; government search is free; Alexandria discovery (firecrawl_search with sources ["alexandria"] alone, and firecrawl_find_tools) is free; firecrawl_scrape is billed, as a page retrieval in url mode or per executed capability in alexandria mode (pass includeCosts to firecrawl_find_tools to see prices).`;
 
 // The exact set of tools the search surface exposes. Registration is filtered
 // against this set, so anything not listed here can never appear on that