firecrawl-mcp 3.32.0 → 3.33.0

package/README.md

@@ -8,7 +8,7 @@
 
 # Firecrawl MCP Server
 
-A Model Context Protocol (MCP) server that brings [Firecrawl](https://github.com/firecrawl/firecrawl) to MCP-compatible AI agents — search, scrape, and interact with the live web for clean, agent-ready context.
+A Model Context Protocol (MCP) server that brings [Firecrawl](https://github.com/firecrawl/firecrawl), the context API for AI agents, to MCP-compatible clients: search, scrape, and interact with the live web and get back clean Markdown or structured data.
 
 > Big thanks to [@vrknetha](https://github.com/vrknetha), [@knacklabs](https://www.knacklabs.ai) for the initial implementation!
 

package/dist/index.js

@@ -2637,25 +2637,64 @@ function initializeClientSlug(name2) {
   const slug = slugOf(name2);
   return isOwnSlug(slug) || GENERIC_CLIENT_NAMES.has(slug) ? "" : slug;
 }
-function referrerSlug(referrer) {
-  let host;
+function publicHost(url) {
+  let parsed;
   try {
-    host = new URL(referrer ?? "").hostname.toLowerCase().replace(/\.$/, "");
+    parsed = new URL(url ?? "");
   } catch {
     return "";
   }
+  const host = parsed.hostname.toLowerCase().replace(/\.$/, "");
   if (!host.includes(".") || host.endsWith(".localhost") || host.endsWith(".local") || /^[\d.]+$/.test(host) || host.startsWith("[")) {
     return "";
   }
-  return slugOf(host.replace(/^www\./, ""));
+  return host.replace(/^www\./, "");
+}
+function referrerSlug(referrer) {
+  return slugOf(publicHost(referrer));
+}
+var SHARED_STATIC_HOSTS = [
+  "github.io",
+  "gitlab.io",
+  "pages.dev",
+  "netlify.app",
+  "vercel.app"
+];
+function isHttpUrl(value) {
+  try {
+    return /^https?:$/.test(new URL(value ?? "").protocol);
+  } catch {
+    return false;
+  }
+}
+function oauthClientSlug(clientId, clientName) {
+  if (!isHttpUrl(clientId)) return initializeClientSlug(clientName);
+  const host = publicHost(clientId);
+  if (!host || host === "firecrawl.dev" || host.endsWith(".firecrawl.dev")) {
+    return "";
+  }
+  if (!SHARED_STATIC_HOSTS.some(
+    (shared) => host === shared || host.endsWith(`.${shared}`)
+  )) {
+    return slugOf(host);
+  }
+  const [first = ""] = new URL(clientId ?? "").pathname.split("/").filter(Boolean);
+  const segment = slugOf(first).slice(0, NAME_MAX / 2);
+  if (!segment) return slugOf(host);
+  const room = NAME_MAX - segment.length - 1;
+  return slugOf(`${slugOf(host).slice(0, room)}-${segment}`);
 }
 function originForClient(client, serverVersion2, userAgent, signals = {}) {
   const declared = slugOf(signals.declaredOrigin);
   const slug = slugOf(client?.name);
   const product = userAgentProduct(userAgent);
   const remembered = initializeClientSlug(signals.initializeClient?.name);
+  const oauthClient = oauthClientSlug(
+    signals.oauthClientId,
+    signals.oauthClientName
+  );
   const referrer = referrerSlug(signals.referrer);
-  const base = !isOwnSlug(declared) ? `mcp-${declared}` : !isOwnSlug(slug) ? `mcp-${slug}` : product && !RUNTIME_PRODUCTS.has(product) ? `mcp-ua-${product}` : remembered ? `mcp-${remembered}` : referrer ? `mcp-ref-${referrer}` : product ? `mcp-ua-${product}` : ORIGIN_SERVER;
+  const base = !isOwnSlug(declared) ? `mcp-${declared}` : !isOwnSlug(slug) ? `mcp-${slug}` : product && !RUNTIME_PRODUCTS.has(product) ? `mcp-ua-${product}` : remembered ? `mcp-${remembered}` : oauthClient ? `mcp-oauth-${oauthClient}` : referrer ? `mcp-ref-${referrer}` : product ? `mcp-ua-${product}` : ORIGIN_SERVER;
   return serverVersion2 ? `${base}@${serverVersion2}` : base;
 }
 function originHeaders(origin) {
@@ -2672,6 +2711,8 @@ function requestOrigin(client, session) {
     {
       declaredOrigin: session?.clientOrigin,
       initializeClient: session?.initializeClient,
+      oauthClientId: session?.oauthClientId,
+      oauthClientName: session?.oauthClientName,
       referrer: session?.clientReferrer
     }
   );
@@ -6222,6 +6263,7 @@ function credentialMetadata(data) {
     userId: typeof data.sub === "string" ? data.sub : void 0,
     apiKeyId: typeof data.api_key_id === "string" ? data.api_key_id : void 0,
     oauthClientId: typeof data.client_id === "string" ? data.client_id : void 0,
+    oauthClientName: typeof data.client_name === "string" ? data.client_name : void 0,
     resource: typeof data.aud === "string" ? data.aud : void 0
   };
 }

package/dist/origin.js

@@ -59,25 +59,64 @@ function initializeClientSlug(name) {
   const slug = slugOf(name);
   return isOwnSlug(slug) || GENERIC_CLIENT_NAMES.has(slug) ? "" : slug;
 }
-function referrerSlug(referrer) {
-  let host;
+function publicHost(url) {
+  let parsed;
   try {
-    host = new URL(referrer ?? "").hostname.toLowerCase().replace(/\.$/, "");
+    parsed = new URL(url ?? "");
   } catch {
     return "";
   }
+  const host = parsed.hostname.toLowerCase().replace(/\.$/, "");
   if (!host.includes(".") || host.endsWith(".localhost") || host.endsWith(".local") || /^[\d.]+$/.test(host) || host.startsWith("[")) {
     return "";
   }
-  return slugOf(host.replace(/^www\./, ""));
+  return host.replace(/^www\./, "");
+}
+function referrerSlug(referrer) {
+  return slugOf(publicHost(referrer));
+}
+var SHARED_STATIC_HOSTS = [
+  "github.io",
+  "gitlab.io",
+  "pages.dev",
+  "netlify.app",
+  "vercel.app"
+];
+function isHttpUrl(value) {
+  try {
+    return /^https?:$/.test(new URL(value ?? "").protocol);
+  } catch {
+    return false;
+  }
+}
+function oauthClientSlug(clientId, clientName) {
+  if (!isHttpUrl(clientId)) return initializeClientSlug(clientName);
+  const host = publicHost(clientId);
+  if (!host || host === "firecrawl.dev" || host.endsWith(".firecrawl.dev")) {
+    return "";
+  }
+  if (!SHARED_STATIC_HOSTS.some(
+    (shared) => host === shared || host.endsWith(`.${shared}`)
+  )) {
+    return slugOf(host);
+  }
+  const [first = ""] = new URL(clientId ?? "").pathname.split("/").filter(Boolean);
+  const segment = slugOf(first).slice(0, NAME_MAX / 2);
+  if (!segment) return slugOf(host);
+  const room = NAME_MAX - segment.length - 1;
+  return slugOf(`${slugOf(host).slice(0, room)}-${segment}`);
 }
 function originForClient(client, serverVersion2, userAgent, signals = {}) {
   const declared = slugOf(signals.declaredOrigin);
   const slug = slugOf(client?.name);
   const product = userAgentProduct(userAgent);
   const remembered = initializeClientSlug(signals.initializeClient?.name);
+  const oauthClient = oauthClientSlug(
+    signals.oauthClientId,
+    signals.oauthClientName
+  );
   const referrer = referrerSlug(signals.referrer);
-  const base = !isOwnSlug(declared) ? `mcp-${declared}` : !isOwnSlug(slug) ? `mcp-${slug}` : product && !RUNTIME_PRODUCTS.has(product) ? `mcp-ua-${product}` : remembered ? `mcp-${remembered}` : referrer ? `mcp-ref-${referrer}` : product ? `mcp-ua-${product}` : ORIGIN_SERVER;
+  const base = !isOwnSlug(declared) ? `mcp-${declared}` : !isOwnSlug(slug) ? `mcp-${slug}` : product && !RUNTIME_PRODUCTS.has(product) ? `mcp-ua-${product}` : remembered ? `mcp-${remembered}` : oauthClient ? `mcp-oauth-${oauthClient}` : referrer ? `mcp-ref-${referrer}` : product ? `mcp-ua-${product}` : ORIGIN_SERVER;
   return serverVersion2 ? `${base}@${serverVersion2}` : base;
 }
 function originHeaders(origin) {
@@ -94,6 +133,8 @@ function requestOrigin(client, session) {
     {
       declaredOrigin: session?.clientOrigin,
       initializeClient: session?.initializeClient,
+      oauthClientId: session?.oauthClientId,
+      oauthClientName: session?.oauthClientName,
       referrer: session?.clientReferrer
     }
   );

package/dist/server.d.ts

@@ -35,6 +35,8 @@ type OriginSession = {
     clientOrigin?: string;
     clientReferrer?: string;
     initializeClient?: ClientImplementation;
+    oauthClientId?: string;
+    oauthClientName?: string;
 };
 /**
  * The origin of every request a tool call makes: the call's client, the
@@ -241,6 +243,13 @@ interface SessionData {
         name?: string;
         version?: string;
     };
+    /**
+     * The OAuth client id the access token was issued to. A metadata URL id
+     * names the product; read only when the User-Agent names a runtime.
+     */
+    oauthClientId?: string;
+    /** The registered name of that client; read when the id is not a URL. */
+    oauthClientName?: string;
     authType?: 'api-key' | 'oauth' | 'env' | 'keyless' | 'none';
     /** Admitted, but the supplied credential cannot be used. */
     credentialError?: 'CREDENTIAL_INVALID';

package/dist/server.js

@@ -2636,25 +2636,64 @@ function initializeClientSlug(name2) {
   const slug = slugOf(name2);
   return isOwnSlug(slug) || GENERIC_CLIENT_NAMES.has(slug) ? "" : slug;
 }
-function referrerSlug(referrer) {
-  let host;
+function publicHost(url) {
+  let parsed;
   try {
-    host = new URL(referrer ?? "").hostname.toLowerCase().replace(/\.$/, "");
+    parsed = new URL(url ?? "");
   } catch {
     return "";
   }
+  const host = parsed.hostname.toLowerCase().replace(/\.$/, "");
   if (!host.includes(".") || host.endsWith(".localhost") || host.endsWith(".local") || /^[\d.]+$/.test(host) || host.startsWith("[")) {
     return "";
   }
-  return slugOf(host.replace(/^www\./, ""));
+  return host.replace(/^www\./, "");
+}
+function referrerSlug(referrer) {
+  return slugOf(publicHost(referrer));
+}
+var SHARED_STATIC_HOSTS = [
+  "github.io",
+  "gitlab.io",
+  "pages.dev",
+  "netlify.app",
+  "vercel.app"
+];
+function isHttpUrl(value) {
+  try {
+    return /^https?:$/.test(new URL(value ?? "").protocol);
+  } catch {
+    return false;
+  }
+}
+function oauthClientSlug(clientId, clientName) {
+  if (!isHttpUrl(clientId)) return initializeClientSlug(clientName);
+  const host = publicHost(clientId);
+  if (!host || host === "firecrawl.dev" || host.endsWith(".firecrawl.dev")) {
+    return "";
+  }
+  if (!SHARED_STATIC_HOSTS.some(
+    (shared) => host === shared || host.endsWith(`.${shared}`)
+  )) {
+    return slugOf(host);
+  }
+  const [first = ""] = new URL(clientId ?? "").pathname.split("/").filter(Boolean);
+  const segment = slugOf(first).slice(0, NAME_MAX / 2);
+  if (!segment) return slugOf(host);
+  const room = NAME_MAX - segment.length - 1;
+  return slugOf(`${slugOf(host).slice(0, room)}-${segment}`);
 }
 function originForClient(client, serverVersion2, userAgent, signals = {}) {
   const declared = slugOf(signals.declaredOrigin);
   const slug = slugOf(client?.name);
   const product = userAgentProduct(userAgent);
   const remembered = initializeClientSlug(signals.initializeClient?.name);
+  const oauthClient = oauthClientSlug(
+    signals.oauthClientId,
+    signals.oauthClientName
+  );
   const referrer = referrerSlug(signals.referrer);
-  const base = !isOwnSlug(declared) ? `mcp-${declared}` : !isOwnSlug(slug) ? `mcp-${slug}` : product && !RUNTIME_PRODUCTS.has(product) ? `mcp-ua-${product}` : remembered ? `mcp-${remembered}` : referrer ? `mcp-ref-${referrer}` : product ? `mcp-ua-${product}` : ORIGIN_SERVER;
+  const base = !isOwnSlug(declared) ? `mcp-${declared}` : !isOwnSlug(slug) ? `mcp-${slug}` : product && !RUNTIME_PRODUCTS.has(product) ? `mcp-ua-${product}` : remembered ? `mcp-${remembered}` : oauthClient ? `mcp-oauth-${oauthClient}` : referrer ? `mcp-ref-${referrer}` : product ? `mcp-ua-${product}` : ORIGIN_SERVER;
   return serverVersion2 ? `${base}@${serverVersion2}` : base;
 }
 function originHeaders(origin) {
@@ -2671,6 +2710,8 @@ function requestOrigin(client, session) {
     {
       declaredOrigin: session?.clientOrigin,
       initializeClient: session?.initializeClient,
+      oauthClientId: session?.oauthClientId,
+      oauthClientName: session?.oauthClientName,
       referrer: session?.clientReferrer
     }
   );

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "firecrawl-mcp",
-  "version": "3.32.0",
-  "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.",
+  "version": "3.33.0",
+  "description": "Firecrawl MCP server, the context API for AI agents: search, scrape, parse, crawl, map, and interact with the web, run Agent and Monitor jobs, and search scientific papers (PubMed, bioRxiv, medRxiv, arXiv). Works with Firecrawl cloud or a self-hosted instance.",
   "type": "module",
   "mcpName": "io.github.firecrawl/firecrawl-mcp-server",
   "bin": {