@h1deya/langchain-mcp-tools 0.3.8 → 0.3.9

package/README.md

@@ -14,7 +14,7 @@ However, it only supports text results of tool calls and does not support MCP fe
 
 [LangChain's **official LangChain.js MCP Adapters** library](https://www.npmjs.com/package/@langchain/mcp-adapters),
 which supports comprehensive integration with LangChain, has been released.
-You may want to consider using it if you don't have specific needs for this library.
+You might want to consider using it if the extra features that this library supports are not necessary.
 
 ## Prerequisites
 
@@ -44,6 +44,11 @@ const mcpServers: McpServersConfig = {
     command: "uvx",
     args: ["mcp-server-fetch"]
   },
+  "brave-search": {
+    command: "npx",
+    args: [ "-y", "@modelcontextprotocol/server-brave-search"],
+    env: { "BRAVE_API_KEY": `${process.env.BRAVE_API_KEY}` }
+  },
   github: {
     type: "http",
     url: "https://api.githubcopilot.com/mcp/",
@@ -86,16 +91,35 @@ to be invoked to close all MCP server sessions when finished.
 The returned tools can be used with LangChain, e.g.:
 
 ```ts
-// import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
-const llm = new ChatGoogleGenerativeAI({ model: "gemini-2.5-flash" });
+// import { createAgent } from "langchain";
+const model = new ChatGoogleGenerativeAI({ model: "gemini-2.5-flash" });
 
 // import { createReactAgent } from "@langchain/langgraph/prebuilt";
-const agent = createReactAgent({
-  llm,
+const agent = createAgent({
+  model,
   tools
 });
 ```
 
+The returned `cleanup` function properly handles resource cleanup:
+
+- Closes all MCP server connections concurrently and logs any cleanup failures
+- Continues cleanup of remaining servers even if some fail
+- Should always be called when done using the tools
+
+It is typically invoked in a finally block:
+
+```ts
+const { tools, cleanup } = await convertMcpToLangchainTools(mcpServers);
+
+try {
+  // Use tools with your LLM
+} finally {
+  // Always cleanup, even if errors occur
+  await cleanup();
+}
+```
+
 A minimal but complete working usage example can be found
 [in this example in the langchain-mcp-tools-ts-usage repo](https://github.com/hideya/langchain-mcp-tools-ts-usage/blob/main/src/index.ts)
 
@@ -145,14 +169,6 @@ While MCP tools can return multiple content types (text, images, etc.), this lib
   [See below](https://github.com/hideya/langchain-mcp-tools-ts/blob/main/README.md#llm-provider-schema-compatibility) for details.
 - **Passing PATH Env Variable**: The library automatically adds the `PATH` environment variable to stdio server configrations if not explicitly provided to ensure servers can find required executables.
 
-## API docs
-
-Can be found [here](https://hideya.github.io/langchain-mcp-tools-ts/modules.html)
-
-## Building from Source
-
-See [README_DEV.md](https://github.com/hideya/langchain-mcp-tools-ts/blob/main/README_DEV.md) for details.
-
 ## Features
 
 ### `stderr` Redirection for Local MCP Server 
@@ -260,10 +276,10 @@ Streamable HTTP is the modern MCP transport that replaces the older HTTP+SSE tra
 
 ### Accessing Remote MCP Servers with OAuth Quickly
 
-If you need to use MCP servers that require OAuth quickly, consider using **"[mcp-remote](https://www.npmjs.com/package/mcp-remote)"**.
+If you need to use MCP servers that require OAuth, consider using **"[mcp-remote](https://www.npmjs.com/package/mcp-remote)"**.
 
 ```ts
-    notionMCP: {
+    notion: {
       command: "npx",
       args: ["-y", "mcp-remote", "https://mcp.notion.com/mcp"],
     },
@@ -313,10 +329,18 @@ Test implementations are provided:
   - MCP client uses this library: [streamable-http-auth-test-client.ts](https://github.com/hideya/langchain-mcp-tools-ts/tree/main/testfiles/streamable-http-auth-test-client.ts)
   - Test MCP Server:  [streamable-http-auth-test-server.ts](https://github.com/hideya/langchain-mcp-tools-ts/tree/main/testfiles/streamable-http-auth-test-server.ts)
 
+## API docs
+
+Can be found [here](https://hideya.github.io/langchain-mcp-tools-ts/modules.html)
+
 ## Change Log
 
 Can be found [here](https://github.com/hideya/langchain-mcp-tools-ts/blob/main/CHANGELOG.md)
 
+## Building from Source
+
+See [README_DEV.md](https://github.com/hideya/langchain-mcp-tools-ts/blob/main/README_DEV.md) for details.
+
 ## Appendix
 
 ### Troubleshooting
@@ -408,27 +432,6 @@ const { tools, cleanup } = await convertMcpToLangchainTools(
 - [Gemini API Schema Requirements](https://ai.google.dev/api/caching#Schema)
 - [Anthropic Tool Use](https://docs.anthropic.com/en/docs/agents-and-tools/tool-use/overview)
 
-
-### Resource Management
-
-The returned `cleanup` function properly handles resource cleanup:
-
-- Closes all MCP server connections concurrently
-- Logs any cleanup failures
-- Continues cleanup of remaining servers even if some fail
-- Should always be called when done using the tools
-
-```ts
-const { tools, cleanup } = await convertMcpToLangchainTools(mcpServers);
-
-try {
-  // Use tools with your LLM
-} finally {
-  // Always cleanup, even if errors occur
-  await cleanup();
-}
-```
-
 ### Debugging and Logging
 
 The library provides configurable logging to help debug connection and tool execution issues:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@h1deya/langchain-mcp-tools",
-  "version": "0.3.8",
+  "version": "0.3.9",
   "description": "MCP To LangChain Tools Conversion Utility",
   "license": "MIT",
   "keywords": [
@@ -51,6 +51,8 @@
     "test:coverage": "vitest run --coverage",
     "_comment_examples": "# Basic usage examples",
     "example:simple": "tsx testfiles/simple-usage.ts",
+    "_comment_sse_ws": "# SSE and WS transport tests",
+    "test:sse-and-ws": "tsx testfiles/sse-and-ws-test.ts",
     "_comment_streamable": "# Streamable HTTP transport tests",
     "test:streamable:auth:server": "tsx testfiles/streamable-http-auth-test-server.ts",
     "test:streamable:auth:client": "tsx testfiles/streamable-http-auth-test-client.ts",
@@ -68,33 +70,36 @@
   },
   "dependencies": {
     "@h1deya/json-schema-to-zod": "^0.1.1",
-    "@langchain/core": "^0.3.62",
-    "@modelcontextprotocol/sdk": "^1.15.0",
+    "@langchain/core": ">=0.3.62",
+    "@modelcontextprotocol/sdk": ">=1.15.0",
     "zod": "^3.25.74"
   },
   "devDependencies": {
     "@eslint/js": "^9.17.0",
-    "@langchain/anthropic": "^0.3.11",
-    "@langchain/cerebras": "^0.0.3",
-    "@langchain/google-genai": "^0.2.12",
-    "@langchain/groq": "^0.2.3",
-    "@langchain/langgraph": "^0.2.36",
-    "@langchain/openai": "^0.3.16",
-    "@langchain/xai": "^0.1.0",
+    "@langchain/anthropic": "^1.3.17",
+    "@langchain/cerebras": "^1.0.1",
+    "@langchain/google-genai": "^2.1.18",
+    "@langchain/groq": "^1.1.0",
+    "@langchain/openai": "^1.2.7",
+    "@langchain/xai": "^1.3.3",
+    "@modelcontextprotocol/sdk": "^1.26.0",
+    "@types/cors": "^2.8.19",
+    "@types/express": "^5.0.6",
     "@types/node": "^22.10.5",
     "@types/ws": "^8.18.1",
     "@typescript-eslint/eslint-plugin": "^8.19.0",
     "@typescript-eslint/parser": "^8.19.0",
-    "@vitest/coverage-v8": "^3.0.9",
+    "@vitest/coverage-v8": "^3.2.4",
     "cors": "^2.8.5",
     "dotenv": "^16.4.7",
     "eslint": "^9.17.0",
     "express": "^4.19.2",
+    "langchain": "^1.2.23",
     "tsx": "^4.19.3",
     "typedoc": "^0.28.3",
     "typescript": "^5.7.2",
     "typescript-eslint": "^8.19.0",
-    "vitest": "^3.0.9",
+    "vitest": "^3.2.4",
     "ws": "^8.18.1"
   }
 }