mcp-use 1.3.11__tar.gz → 1.3.12__tar.gz

mcp_use-1.3.12/.github/workflows/docs.yml

@@ -0,0 +1,108 @@
+name: Documentation
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  docs:
+    runs-on: ubuntu-latest
+    name: Generate and validate API documentation
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v4
+
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.11'
+
+    - name: Install uv
+      run: pip install uv
+
+    - name: Create virtual environment
+      run: uv venv
+
+    - name: Install dependencies
+      run: uv pip install -e .
+
+    - name: Install Mintlify CLI
+      run: npm install -g mint
+
+    - name: Generate API documentation
+      run: cd docs && uv run python generate_docs.py ../mcp_use api-reference docs.json
+
+    - name: Check for broken links
+      run: |
+        cd docs
+        mint broken-links
+
+    - name: Check for documentation changes
+      id: check_docs
+      run: |
+        if [ -n "$(git status --porcelain docs/)" ]; then
+          echo "docs_outdated=true" >> $GITHUB_OUTPUT
+          echo "❌ API documentation is out of date!"
+          echo ""
+          echo "The following files have been modified:"
+          MODIFIED=$(git status --porcelain docs/)
+          echo "$MODIFIED"
+          echo "modified_files<<EOF" >> $GITHUB_OUTPUT
+          echo "$MODIFIED" >> $GITHUB_OUTPUT
+          echo "EOF" >> $GITHUB_OUTPUT
+        else
+          echo "docs_outdated=false" >> $GITHUB_OUTPUT
+          echo "✅ API documentation is up to date"
+        fi
+
+    - name: Comment on PR
+      if: steps.check_docs.outputs.docs_outdated == 'true' && github.event_name == 'pull_request'
+      uses: actions/github-script@v7
+      with:
+        script: |
+          const comment = `## ❌ API Documentation Out of Date
+
+          The API documentation needs to be regenerated. Please run the following commands:
+
+          \`\`\`bash
+          cd docs
+          uv run python generate_docs.py ../mcp_use api-reference docs.json
+          \`\`\`
+
+          Then commit the changes:
+
+          \`\`\`bash
+          git add docs/api-reference/ docs/docs.json
+          git commit -m "docs: update API documentation"
+          \`\`\`
+
+          <details>
+          <summary>Modified files</summary>
+
+          \`\`\`
+          ${process.env.MODIFIED_FILES}
+          \`\`\`
+          </details>`;
+
+          github.rest.issues.createComment({
+            issue_number: context.issue.number,
+            owner: context.repo.owner,
+            repo: context.repo.repo,
+            body: comment
+          });
+      env:
+        MODIFIED_FILES: ${{ steps.check_docs.outputs.modified_files }}
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+    - name: Fail if docs are outdated
+      if: steps.check_docs.outputs.docs_outdated == 'true'
+      run: |
+        echo "Please update the API documentation and commit the changes."
+        exit 1

{mcp_use-1.3.11 → mcp_use-1.3.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mcp-use
-Version: 1.3.11
+Version: 1.3.12
 Summary: MCP Library for LLMs
 Author-email: Pietro Zullo <pietro.zullo@gmail.com>
 License: MIT
@@ -20,7 +20,8 @@ Requires-Dist: jsonschema-pydantic>=0.1.0
 Requires-Dist: langchain>=0.1.0
 Requires-Dist: mcp>=1.10.0
 Requires-Dist: posthog>=4.8.0
-Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pydantic-core==2.33.2
+Requires-Dist: pydantic==2.11.10
 Requires-Dist: python-dotenv>=1.0.0
 Requires-Dist: scarf-sdk>=0.1.0
 Requires-Dist: websockets>=15.0
@@ -833,23 +834,23 @@ Thanks to all our amazing contributors!
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/38653995?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/patchy631/ai-engineering-hub"><strong>patchy631/ai-engineering-hub</strong></a></td>
-    <td>⭐ 17917</td>
+    <td>⭐ 18021</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/164294848?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/buildfastwithai/gen-ai-experiments"><strong>buildfastwithai/gen-ai-experiments</strong></a></td>
-    <td>⭐ 178</td>
+    <td>⭐ 202</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/187057607?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/hud-evals/hud-python"><strong>hud-evals/hud-python</strong></a></td>
-    <td>⭐ 159</td>
+    <td>⭐ 168</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/170207473?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/tavily-ai/meeting-prep-agent"><strong>tavily-ai/meeting-prep-agent</strong></a></td>
-    <td>⭐ 136</td>
+    <td>⭐ 138</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/20041231?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/krishnaik06/MCP-CRASH-Course"><strong>krishnaik06/MCP-CRASH-Course</strong></a></td>
-    <td>⭐ 72</td>
+    <td>⭐ 74</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/54944174?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/larksuite/lark-samples"><strong>larksuite/lark-samples</strong></a></td>

{mcp_use-1.3.11 → mcp_use-1.3.12}/README.md

@@ -787,23 +787,23 @@ Thanks to all our amazing contributors!
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/38653995?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/patchy631/ai-engineering-hub"><strong>patchy631/ai-engineering-hub</strong></a></td>
-    <td>⭐ 17917</td>
+    <td>⭐ 18021</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/164294848?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/buildfastwithai/gen-ai-experiments"><strong>buildfastwithai/gen-ai-experiments</strong></a></td>
-    <td>⭐ 178</td>
+    <td>⭐ 202</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/187057607?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/hud-evals/hud-python"><strong>hud-evals/hud-python</strong></a></td>
-    <td>⭐ 159</td>
+    <td>⭐ 168</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/170207473?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/tavily-ai/meeting-prep-agent"><strong>tavily-ai/meeting-prep-agent</strong></a></td>
-    <td>⭐ 136</td>
+    <td>⭐ 138</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/20041231?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/krishnaik06/MCP-CRASH-Course"><strong>krishnaik06/MCP-CRASH-Course</strong></a></td>
-    <td>⭐ 72</td>
+    <td>⭐ 74</td>
   </tr>
   <tr>
     <td><img src="https://avatars.githubusercontent.com/u/54944174?s=40&v=4" width="20" height="20" style="vertical-align: middle; margin-right: 8px;"> <a href="https://github.com/larksuite/lark-samples"><strong>larksuite/lark-samples</strong></a></td>

{mcp_use-1.3.11 → mcp_use-1.3.12}/docs/advanced/building-custom-agents.mdx

@@ -40,7 +40,8 @@ The `LangChainAdapter` is a powerful component that converts MCP tools to LangCh
 
 Here's a simple example of creating a custom agent using the LangChain adapter:
 
-```python
+<CodeGroup>
+```python Python
 import asyncio
 from langchain_openai import ChatOpenAI
 from langchain.agents import AgentExecutor, create_tool_calling_agent
@@ -84,14 +85,66 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
+```typescript TypeScript
+import { ChatOpenAI } from '@langchain/openai'
+import { AgentExecutor, createToolCallingAgent } from 'langchain/agents'
+import { ChatPromptTemplate, MessagesPlaceholder } from '@langchain/core/prompts'
+import { MCPClient, LangChainAdapter, loadConfigFile } from 'mcp-use'
+
+async function main() {
+    // Initialize the MCP client
+    const config = await loadConfigFile('path/to/config.json')
+    const client = new MCPClient(config)
+
+    // Create adapter instance
+    const adapter = new LangChainAdapter()
+
+    // Get LangChain tools directly from the client with a single line
+    const tools = await adapter.createTools(client)
+
+    // Initialize your language model
+    const llm = new ChatOpenAI({ model: 'gpt-4o' })
+
+    // Create a prompt template
+    const prompt = ChatPromptTemplate.fromMessages([
+        ['system', 'You are a helpful assistant with access to powerful tools.'],
+        new MessagesPlaceholder('chat_history'),
+        ['human', '{input}'],
+        new MessagesPlaceholder('agent_scratchpad'),
+    ])
+
+    // Create the agent
+    const agent = createToolCallingAgent({ llm, tools, prompt })
+
+    // Create the agent executor
+    const agentExecutor = new AgentExecutor({ agent, tools, verbose: true })
+
+    // Run the agent
+    const result = await agentExecutor.invoke({ input: 'What can you do?' })
+    console.log(result.output)
+
+    await client.closeAllSessions()
+}
+
+main().catch(console.error)
+```
+</CodeGroup>
+
 <Tip>
 **One-Line Tool Creation**: The API simplifies tool creation - all you need is to create an adapter instance and call its `create_tools` method:
 
-```python
+<CodeGroup>
+```python Python
 adapter = LangChainAdapter()
 tools = await adapter.create_tools(client)
 ```
 
+```typescript TypeScript
+const adapter = new LangChainAdapter()
+const tools = await adapter.createTools(client)
+```
+</CodeGroup>
+
 You don't need to worry about sessions, connectors, or initialization. The adapter handles everything for you.
 </Tip>
 
@@ -163,7 +216,8 @@ class YourFrameworkAdapter(BaseAdapter):
 
 Once you've implemented your adapter, you can use it with the simplified API:
 
-```python
+<CodeGroup>
+```python Python
 from your_module import YourFrameworkAdapter
 from mcp_use.client import MCPClient
 
@@ -180,37 +234,56 @@ tools = await adapter.create_tools(client)
 agent = your_framework.create_agent(tools=tools)
 ```
 
+```typescript TypeScript
+import { YourFrameworkAdapter } from './your-module'
+import { MCPClient, loadConfigFile } from 'mcp-use'
+
+// Initialize the client
+const config = await loadConfigFile('config.json')
+const client = new MCPClient(config)
+
+// Create an adapter instance
+const adapter = new YourFrameworkAdapter()
+
+// Get tools with a single line
+const tools = await adapter.createTools(client)
+
+// Use the tools with your framework
+const agent = yourFramework.createAgent({ tools })
+```
+</CodeGroup>
+
 ### Tips for Implementing an Adapter
 
-<Accordion title="Implementation Guidelines">
-  <AccordionItem title="Schema Conversion">
+<AccordionGroup>
+  <Accordion title="Schema Conversion">
     Most frameworks have their own way of handling argument schemas. You'll need to convert the MCP tool's JSON Schema to your framework's format.
 
     <Tip>
     Look at the LangChain adapter implementation as a reference for handling schema conversion patterns.
     </Tip>
-  </AccordionItem>
+  </Accordion>
 
-  <AccordionItem title="Tool Execution">
+  <Accordion title="Tool Execution">
     When a tool is called in your framework, you'll need to pass the call to the connector's `call_tool` method and handle the result.
 
     <Warning>
     Always ensure proper async/await handling when calling MCP tools, as they are inherently asynchronous.
     </Warning>
-  </AccordionItem>
+  </Accordion>
 
-  <AccordionItem title="Result Parsing">
+  <Accordion title="Result Parsing">
     MCP tools return structured data with types like text, images, or embedded resources. Your adapter should parse these into a format your framework understands.
-  </AccordionItem>
+  </Accordion>
 
-  <AccordionItem title="Error Handling">
+  <Accordion title="Error Handling">
     Ensure your adapter handles errors gracefully, both during tool conversion and execution.
 
     <Note>
     The base adapter provides logging utilities to help with error reporting and debugging.
     </Note>
-  </AccordionItem>
-</Accordion>
+  </Accordion>
+</AccordionGroup>
 
 
 ## Conclusion

{mcp_use-1.3.11 → mcp_use-1.3.12}/docs/advanced/logging.mdx

@@ -57,7 +57,8 @@ There are two primary ways to enable debug mode:
 Programmatic control is useful for debugging specific parts of your application or conditionally enabling debug mode based on your application state.
 </Note>
 
-```python
+<CodeGroup>
+```python Python
 import mcp_use
 
 # Different debug levels
@@ -66,16 +67,36 @@ mcp_use.set_debug(2)  # DEBUG level (full verbose output)
 mcp_use.set_debug(0)  # Turn off debug (WARNING level)
 ```
 
+```typescript TypeScript
+import { logger } from 'mcp-use'
+
+// Set the logger level
+logger.level = 'info'   // INFO level
+logger.level = 'debug'  // DEBUG level (full verbose output)
+logger.level = 'warn'   // Turn off debug (WARNING level)
+```
+</CodeGroup>
+
 <Tip>
 You can conditionally enable debugging based on environment or configuration:
 
-```python
+<CodeGroup>
+```python Python
 import os
 import mcp_use
 
 if os.getenv("ENVIRONMENT") == "development":
     mcp_use.set_debug(2)
 ```
+
+```typescript TypeScript
+import { logger } from 'mcp-use'
+
+if (process.env.ENVIRONMENT === 'development') {
+    logger.level = 'debug'
+}
+```
+</CodeGroup>
 </Tip>
 
 ## Debug Levels
@@ -110,7 +131,8 @@ if os.getenv("ENVIRONMENT") == "development":
 
 If you only want to increase verbosity for the agent component without enabling full debug mode for the entire package, you can use the `verbose` parameter when creating an MCPAgent:
 
-```python
+<CodeGroup>
+```python Python
 from mcp_use import MCPAgent
 
 # Create agent with increased verbosity
@@ -121,6 +143,18 @@ agent = MCPAgent(
 )
 ```
 
+```typescript TypeScript
+import { MCPAgent } from 'mcp-use'
+
+// Create agent with increased verbosity
+const agent = new MCPAgent({
+    llm: yourLlm,
+    client: yourClient,
+    verbose: true  // Only shows debug messages from the agent
+})
+```
+</CodeGroup>
+
 This option is useful when you want to see the agent's steps and decision-making process without all the low-level debug information from other components.
 
 ## Debug Information