Allozaur/mcp mvp

.github/workflows/build.yml

@@ -79,7 +79,8 @@ jobs:
           cmake -B build \
             -DCMAKE_BUILD_RPATH="@loader_path" \
             -DLLAMA_FATAL_WARNINGS=ON \
-            -DLLAMA_BUILD_BORINGSSL=ON \
+            -DLLAMA_CURL=OFF \
+            -DLLAMA_BORINGSSL=ON \
             -DGGML_METAL_USE_BF16=ON \
             -DGGML_METAL_EMBED_LIBRARY=OFF \
             -DGGML_METAL_SHADER_DEBUG=ON \
@@ -117,7 +118,8 @@ jobs:
           cmake -B build \
             -DCMAKE_BUILD_RPATH="@loader_path" \
             -DLLAMA_FATAL_WARNINGS=ON \
-            -DLLAMA_BUILD_BORINGSSL=ON \
+            -DLLAMA_CURL=OFF \
+            -DLLAMA_BORINGSSL=ON \
             -DGGML_METAL=OFF \
             -DGGML_RPC=ON \
             -DCMAKE_OSX_DEPLOYMENT_TARGET=13.3
@@ -1015,7 +1017,7 @@ jobs:
         id: cmake_build
         run: |
           cmake -S . -B build ${{ matrix.defines }} `
-            -DLLAMA_BUILD_BORINGSSL=ON
+            -DLLAMA_CURL=OFF -DLLAMA_BORINGSSL=ON
           cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS}
 
       - name: Add libopenblas.dll
@@ -1120,7 +1122,8 @@ jobs:
           call "C:\Program Files\Microsoft Visual Studio\2022\Enterprise\VC\Auxiliary\Build\vcvarsall.bat" x64
           cmake -S . -B build -G "Ninja Multi-Config" ^
             -DLLAMA_BUILD_SERVER=ON ^
-            -DLLAMA_BUILD_BORINGSSL=ON ^
+            -DLLAMA_CURL=OFF ^
+            -DLLAMA_BORINGSSL=ON ^
             -DGGML_NATIVE=OFF ^
             -DGGML_BACKEND_DL=ON ^
             -DGGML_CPU_ALL_VARIANTS=ON ^
@@ -1227,7 +1230,8 @@ jobs:
             -DCMAKE_CXX_COMPILER="${env:HIP_PATH}\bin\clang++.exe" `
             -DCMAKE_CXX_FLAGS="-I$($PWD.Path.Replace('\', '/'))/opt/rocm-${{ env.ROCM_VERSION }}/include/" `
             -DCMAKE_BUILD_TYPE=Release `
-            -DLLAMA_BUILD_BORINGSSL=ON `
+            -DLLAMA_CURL=OFF `
+            -DLLAMA_BORINGSSL=ON `
             -DROCM_DIR="${env:HIP_PATH}" `
             -DGGML_HIP=ON `
             -DGGML_HIP_ROCWMMA_FATTN=ON `

.github/workflows/server.yml

@@ -72,7 +72,7 @@ jobs:
       - name: Build
         id: cmake_build
         run: |
-          cmake -B build -DLLAMA_BUILD_BORINGSSL=ON -DGGML_SCHED_NO_REALLOC=ON
+          cmake -B build -DLLAMA_BORINGSSL=ON -DGGML_SCHED_NO_REALLOC=ON
           cmake --build build --config ${{ matrix.build_type }} -j ${env:NUMBER_OF_PROCESSORS} --target llama-server
 
       - name: Python setup
@@ -108,7 +108,7 @@ jobs:
       - name: Build
         id: cmake_build
         run: |
-          cmake -B build -DLLAMA_BUILD_BORINGSSL=ON -DGGML_SCHED_NO_REALLOC=ON
+          cmake -B build -DLLAMA_BORINGSSL=ON -DGGML_SCHED_NO_REALLOC=ON
           cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS} --target llama-server
 
       - name: Python setup

CMakeLists.txt

@@ -111,8 +111,11 @@ option(LLAMA_BUILD_SERVER   "llama: build server example" ${LLAMA_STANDALONE})
 option(LLAMA_TOOLS_INSTALL  "llama: install tools"        ${LLAMA_TOOLS_INSTALL_DEFAULT})
 
 # 3rd party libs
-option(LLAMA_HTTPLIB    "llama: httplib for downloading functionality" ON)
-option(LLAMA_OPENSSL    "llama: use openssl to support HTTPS" ON)
+option(LLAMA_CURL       "llama: use libcurl to download model from an URL" OFF)
+option(LLAMA_HTTPLIB    "llama: if libcurl is disabled, use httplib to download model from an URL" ON)
+option(LLAMA_BORINGSSL  "llama: use boringssl to support HTTPS" ON)
+option(LLAMA_LIBRESSL   "llama: use libressl to support HTTPS"  OFF)
+option(LLAMA_OPENSSL    "llama: use openssl to support HTTPS"   OFF)
 option(LLAMA_LLGUIDANCE "llama-common: include LLGuidance library for structured output in common utils" OFF)
 
 # deprecated

tools/server/server-models.cpp

@@ -1000,11 +1000,20 @@ server_http_proxy::server_http_proxy(
         int32_t timeout_write
         ) {
     // shared between reader and writer threads
-    auto cli  = std::make_shared<httplib::Client>(host, port);
+    auto cli  = std::make_shared<httplib::ClientImpl>(host, port);
     auto pipe = std::make_shared<pipe_t<msg_t>>();
 
+    if (port == 443) {
+#ifdef CPPHTTPLIB_OPENSSL_SUPPORT
+        cli.reset(new httplib::SSLClient(host, port));
+#else
+        throw std::runtime_error("HTTPS requested but CPPHTTPLIB_OPENSSL_SUPPORT is not defined");
+#endif
+    }
+
     // setup Client
-    cli->set_connection_timeout(0, 200000); // 200 milliseconds
+    cli->set_follow_location(true);
+    cli->set_connection_timeout(5, 0); // 5 seconds
     cli->set_write_timeout(timeout_read, 0); // reversed for cli (client) vs srv (server)
     cli->set_read_timeout(timeout_write, 0);
     this->status = 500; // to be overwritten upon response
@@ -1053,7 +1062,15 @@ server_http_proxy::server_http_proxy(
         req.method = method;
         req.path = path;
         for (const auto & [key, value] : headers) {
-            req.set_header(key, value);
+            if (key == "Accept-Encoding") {
+                // disable Accept-Encoding to avoid compressed responses
+                continue;
+            }
+            if (key == "Host" || key == "host") {
+                req.set_header(key, host);
+            } else {
+                req.set_header(key, value);
+            }
         }
         req.body = body;
         req.response_handler = response_handler;

tools/server/server-models.h

@@ -2,6 +2,7 @@
 
 #include "common.h"
 #include "preset.h"
+#include "http.h"
 #include "server-common.h"
 #include "server-http.h"
 
@@ -184,8 +185,8 @@ struct server_http_proxy : server_http_res {
                       const std::map<std::string, std::string> & headers,
                       const std::string & body,
                       const std::function<bool()> should_stop,
-                      int32_t timeout_read,
-                      int32_t timeout_write
+                      int32_t timeout_read = 600,
+                      int32_t timeout_write = 600
                       );
     ~server_http_proxy() {
         if (cleanup) {
@@ -201,3 +202,48 @@ struct server_http_proxy : server_http_res {
         std::string content_type;
     };
 };
+
+// BELOW IS DEMO CODE FOR PROXY HANDLERS
+// DO NOT MERGE IT AS-IS
+
+static server_http_res_ptr proxy_request(const server_http_req & req, std::string method) {
+    std::string target_url = req.get_param("url");
+    common_http_url parsed_url = common_http_parse_url(target_url);
+
+    if (parsed_url.host.empty()) {
+        throw std::runtime_error("invalid target URL: missing host");
+    }
+
+    if (parsed_url.path.empty()) {
+        parsed_url.path = "/";
+    }
+
+    if (!parsed_url.password.empty()) {
+        throw std::runtime_error("authentication in target URL is not supported");
+    }
+
+    if (parsed_url.scheme != "http" && parsed_url.scheme != "https") {
+        throw std::runtime_error("unsupported URL scheme in target URL: " + parsed_url.scheme);
+    }
+
+    SRV_INF("proxying %s request to %s://%s%s\n", method.c_str(), parsed_url.scheme.c_str(), parsed_url.host.c_str(), parsed_url.path.c_str());
+
+    auto proxy = std::make_unique<server_http_proxy>(
+            method,
+            parsed_url.host,
+            parsed_url.scheme == "http" ? 80 : 443,
+            parsed_url.path,
+            req.headers,
+            req.body,
+            req.should_stop);
+
+    return proxy;
+}
+
+static server_http_context::handler_t proxy_handler_post = [](const server_http_req & req) -> server_http_res_ptr {
+    return proxy_request(req, "POST");
+};
+
+static server_http_context::handler_t proxy_handler_get = [](const server_http_req & req) -> server_http_res_ptr {
+    return proxy_request(req, "GET");
+};

tools/server/server.cpp

@@ -197,6 +197,9 @@ int main(int argc, char ** argv) {
     // Save & load slots
     ctx_http.get ("/slots",               ex_wrapper(routes.get_slots));
     ctx_http.post("/slots/:id_slot",      ex_wrapper(routes.post_slots));
+    // CORS proxy
+    ctx_http.get ("/cors-proxy",          ex_wrapper(proxy_handler_get));
+    ctx_http.post("/cors-proxy",          ex_wrapper(proxy_handler_post));
 
     //
     // Start the server

tools/server/webui/.storybook/main.ts

@@ -1,17 +1,24 @@
 import type { StorybookConfig } from '@storybook/sveltekit';
+import { dirname, resolve } from 'path';
+import { fileURLToPath } from 'url';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
 
 const config: StorybookConfig = {
 	stories: ['../tests/stories/**/*.mdx', '../tests/stories/**/*.stories.@(js|ts|svelte)'],
 	addons: [
 		'@storybook/addon-svelte-csf',
 		'@chromatic-com/storybook',
-		'@storybook/addon-docs',
+		'@storybook/addon-vitest',
 		'@storybook/addon-a11y',
-		'@storybook/addon-vitest'
+		'@storybook/addon-docs'
 	],
-	framework: {
-		name: '@storybook/sveltekit',
-		options: {}
+	framework: '@storybook/sveltekit',
+	viteFinal: async (config) => {
+		config.server = config.server || {};
+		config.server.fs = config.server.fs || {};
+		config.server.fs.allow = [...(config.server.fs.allow || []), resolve(__dirname, '../tests')];
+		return config;
 	}
 };
 export default config;

tools/server/webui/.storybook/preview.ts

@@ -13,7 +13,7 @@ const preview: Preview = {
 		},
 
 		backgrounds: {
-			disable: true
+			disabled: true
 		},
 
 		a11y: {

tools/server/webui/docs/architecture/high-level-architecture-simplified.md

@@ -12,9 +12,11 @@ flowchart TB
         C_Form["ChatForm"]
         C_Messages["ChatMessages"]
         C_Message["ChatMessage"]
+        C_AgenticContent["AgenticContent"]
         C_MessageEditForm["ChatMessageEditForm"]
         C_ModelsSelector["ModelsSelector"]
         C_Settings["ChatSettings"]
+        C_McpSettings["McpSettingsSection"]
     end
 
     subgraph Hooks["🪝 Hooks"]
@@ -27,20 +29,26 @@ flowchart TB
         S2["conversationsStore<br/><i>Conversation data & messages</i>"]
         S3["modelsStore<br/><i>Model selection & loading</i>"]
         S4["serverStore<br/><i>Server props & role detection</i>"]
-        S5["settingsStore<br/><i>User configuration</i>"]
+        S5["settingsStore<br/><i>User configuration incl. MCP</i>"]
     end
 
     subgraph Services["⚙️ Services"]
-        SV1["ChatService"]
+        SV1["ChatService<br/><i>incl. agentic loop</i>"]
         SV2["ModelsService"]
         SV3["PropsService"]
         SV4["DatabaseService"]
         SV5["ParameterSyncService"]
     end
 
+    subgraph MCP["🔧 MCP (Model Context Protocol)"]
+        MCP1["MCPClient<br/><i>@modelcontextprotocol/sdk</i>"]
+        MCP2["mcpStore<br/><i>reactive state</i>"]
+        MCP3["OpenAISseClient"]
+    end
+
     subgraph Storage["💾 Storage"]
         ST1["IndexedDB<br/><i>conversations, messages</i>"]
-        ST2["LocalStorage<br/><i>config, userOverrides</i>"]
+        ST2["LocalStorage<br/><i>config, userOverrides, mcpServers</i>"]
     end
 
     subgraph APIs["🌐 llama-server API"]
@@ -50,15 +58,22 @@ flowchart TB
         API4["/v1/models"]
     end
 
+    subgraph ExternalMCP["🔌 External MCP Servers"]
+        EXT1["MCP Server 1"]
+        EXT2["MCP Server N"]
+    end
+
     %% Routes → Components
     R1 & R2 --> C_Screen
     RL --> C_Sidebar
 
     %% Component hierarchy
     C_Screen --> C_Form & C_Messages & C_Settings
     C_Messages --> C_Message
+    C_Message --> C_AgenticContent
     C_Message --> C_MessageEditForm
     C_Form & C_MessageEditForm --> C_ModelsSelector
+    C_Settings --> C_McpSettings
 
     %% Components → Hooks → Stores
     C_Form & C_Messages --> H1 & H2
@@ -70,6 +85,7 @@ flowchart TB
     C_Sidebar --> S2
     C_ModelsSelector --> S3 & S4
     C_Settings --> S5
+    C_McpSettings --> S5
 
     %% Stores → Services
     S1 --> SV1 & SV4
@@ -78,6 +94,12 @@ flowchart TB
     S4 --> SV3
     S5 --> SV5
 
+    %% ChatService → MCP (Agentic Mode)
+    SV1 --> MCP2
+    MCP2 --> MCP1
+    SV1 --> MCP3
+    MCP3 --> API1
+
     %% Services → Storage
     SV4 --> ST1
     SV5 --> ST2
@@ -87,6 +109,9 @@ flowchart TB
     SV2 --> API3 & API4
     SV3 --> API2
 
+    %% MCP → External Servers
+    MCP1 --> EXT1 & EXT2
+
     %% Styling
     classDef routeStyle fill:#e1f5fe,stroke:#01579b,stroke-width:2px
     classDef componentStyle fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
@@ -95,12 +120,16 @@ flowchart TB
     classDef serviceStyle fill:#e8f5e9,stroke:#2e7d32,stroke-width:2px
     classDef storageStyle fill:#fce4ec,stroke:#c2185b,stroke-width:2px
     classDef apiStyle fill:#e3f2fd,stroke:#1565c0,stroke-width:2px
+    classDef mcpStyle fill:#e0f2f1,stroke:#00695c,stroke-width:2px
+    classDef externalStyle fill:#f3e5f5,stroke:#6a1b9a,stroke-width:2px,stroke-dasharray: 5 5
 
     class R1,R2,RL routeStyle
-    class C_Sidebar,C_Screen,C_Form,C_Messages,C_Message,C_MessageEditForm,C_ModelsSelector,C_Settings componentStyle
+    class C_Sidebar,C_Screen,C_Form,C_Messages,C_Message,C_AgenticContent,C_MessageEditForm,C_ModelsSelector,C_Settings,C_McpSettings componentStyle
     class H1,H2 hookStyle
     class S1,S2,S3,S4,S5 storeStyle
     class SV1,SV2,SV3,SV4,SV5 serviceStyle
     class ST1,ST2 storageStyle
     class API1,API2,API3,API4 apiStyle
+    class MCP1,MCP2,MCP3 mcpStyle
+    class EXT1,EXT2 externalStyle
 ```