Add expanded tools and in-memory document cache

.env.example

@@ -0,0 +1,32 @@
+# MCP Summary Server - Environment Variables
+
+# Server Configuration
+PORT=8080
+
+# Authentication (optional)
+# If set, requests must include: Authorization: Bearer <API_KEY>
+API_KEY=
+
+# LLM Configuration
+OPENAPI_URL=http://localhost:8080/v1
+OPENAPI_API_KEY=
+MODEL_NAME=gpt-4o
+
+# LLM Call Timeout in seconds (increase for large documents)
+LLM_TIMEOUT=120
+
+# Summarization Configuration
+# Characters per chunk when splitting long text
+CHUNK_SIZE=4000
+
+# Characters of overlap between chunks to maintain context
+OVERLAP=200
+
+# Target length for intermediate chunk summaries (words)
+TARGET_INTERMEDIATE_SUMMARY_LENGTH=150
+
+# Maximum length for final synthesized summary (words)
+MAX_DIRECT_SUMMARY_LENGTH=100
+
+# Maximum text length (characters) before chunking is triggered
+MAX_DIRECT_TEXT_LENGTH=8000

Dockerfile

@@ -0,0 +1,37 @@
+# Dockerfile for MCP Summary Server
+#
+# Usage (from directory containing this Dockerfile and mcp_summary_server.py):
+#
+#   docker build -t mcp-summary .
+#   docker run -p 8080:8080 --env-file .env mcp-summary
+#
+
+FROM python:3.12-slim
+
+WORKDIR /app
+
+# Install runtime dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt && rm requirements.txt
+
+# Copy the server script
+COPY mcp_summary_server.py /app/mcp_summary_server.py
+
+# Expose HTTP port
+EXPOSE 8080
+
+# Environment variables
+ENV PORT=8080
+ENV OPENAPI_URL=http://localhost:8080/v1
+ENV OPENAPI_API_KEY=
+ENV MODEL_NAME=gpt-4o
+ENV CHUNK_SIZE=4000
+ENV OVERLAP=200
+ENV TARGET_INTERMEDIATE_SUMMARY_LENGTH=150
+ENV MAX_DIRECT_SUMMARY_LENGTH=100
+ENV MAX_DIRECT_TEXT_LENGTH=8000
+ENV LLM_TIMEOUT=120
+ENV API_KEY=
+
+# Start the MCP summary server
+ENTRYPOINT ["python", "-u", "/app/mcp_summary_server.py"]

README.md

@@ -0,0 +1,137 @@
+# MCP Summary Server
+
+An MCP (Model Context Protocol) server for document summarization that keeps full text out of the chat context window.
+
+## Features
+
+- Automatically determines whether to summarize directly or use chunked summarization
+- All processing happens server-side
+- Returns only the summary to the client
+- Configurable chunking parameters
+- Bearer token authentication (optional)
+
+## Setup
+
+### Environment Variables
+
+Copy `.env.example` to `.env` and configure:
+
+```bash
+cp .env.example .env
+```
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| PORT | 8080 | HTTP server port |
+| API_KEY | (empty) | Bearer token for authentication |
+| OPENAPI_URL | http://localhost:8080/v1 | LLM API endpoint |
+| OPENAPI_API_KEY | (empty) | LLM API key |
+| MODEL_NAME | gpt-4o | LLM model to use |
+| LLM_TIMEOUT | 120 | LLM call timeout in seconds |
+| CHUNK_SIZE | 4000 | Characters per chunk |
+| OVERLAP | 200 | Characters of overlap between chunks |
+| TARGET_INTERMEDIATE_SUMMARY_LENGTH | 150 | Words per chunk summary |
+| MAX_DIRECT_SUMMARY_LENGTH | 100 | Max final summary length |
+| MAX_DIRECT_TEXT_LENGTH | 8000 | Max text length before chunking |
+
+## Running
+
+### Docker
+
+```bash
+# Build
+docker build -t mcp-summary .
+
+# Run with environment file
+docker run -p 8080:8080 --env-file .env mcp-summary
+
+# Run with inline environment variables
+docker run -p 8080:8080 \
+  -e OPENAPI_URL=http://localhost:8080/v1 \
+  -e OPENAPI_API_KEY=your-key \
+  -e MODEL_NAME=gpt-4o \
+  mcp-summary
+```
+
+### Python
+
+```bash
+pip install -r requirements.txt
+python mcp_summary_server.py
+```
+
+## Connecting to OpenWebUI
+
+### In OpenWebUI Admin Settings
+
+1. Go to **Admin Settings → External Tools**
+2. Click **+ (Add Server)**
+3. Set **Type** to **MCP (Streamable HTTP)**
+4. Enter your **Server URL**
+5. Set **Authentication**:
+   - **None** if no API key is configured
+   - **Bearer** if API_KEY is set (provide the key)
+6. Save
+
+### Docker Networking
+
+If running both OpenWebUI and MCP Summary in Docker:
+
+```bash
+# Use host.docker.internal to reach host machine
+docker run -p 8080:8080 \
+  -e OPENAPI_URL=http://host.docker.internal:3000/v1 \
+  -e OPENAPI_API_KEY=your-key \
+  mcp-summary
+```
+
+If both containers are on the same Docker network, use the container name directly:
+
+```bash
+docker run --network mynetwork -p 8080:8080 \
+  -e OPENAPI_URL=http://openwebui-container:8080/v1 \
+  -e OPENAPI_API_KEY=your-key \
+  mcp-summary
+```
+
+## MCP Tool
+
+### summarize_document
+
+Summarizes a document, automatically handling chunking for long text.
+
+**Parameters:**
+- `text` (string, required): The document text to summarize
+- `max_length` (integer, optional): Maximum summary length in words (default: 100)
+
+**Returns:**
+```json
+{
+  "summary": "The summarized text...",
+  "original_length": 12345,
+  "method": "direct",  // or "chunked"
+  "chunks": 1  // number of chunks used
+}
+```
+
+## Troubleshooting
+
+### "Failed to connect to MCP server"
+
+1. **Check authentication**: Ensure you haven't selected `Bearer` without a key. Switch to `None` if no token is needed.
+2. **Check network connectivity**: Ensure OpenWebUI can reach the MCP server URL
+3. **Check LLM connectivity**: Ensure the MCP server can reach the LLM at OPENAPI_URL
+4. **Check timeouts**: Increase LLM_TIMEOUT if summarization takes too long
+
+### Infinite loading screen
+
+This may occur if you configured the server as OpenAPI instead of MCP. Fix by:
+
+1. Opening Admin Settings → External Tools
+2. Disabling/deleting the problematic connection
+3. Re-adding with **Type** set to **MCP (Streamable HTTP)**
+
+### Slow initialization
+
+If the server takes longer than 10 seconds to initialize:
+- Increase `MCP_INITIALIZE_TIMEOUT` in OpenWebUI (default: 10 seconds)

diagnose.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+# Diagnostic script for MCP Summary Server
+
+echo "================================"
+echo "MCP Summary Server Diagnostics"
+echo "================================"
+
+# Check if server is running
+echo -e "\n1. Checking if server process is running..."
+ps aux | grep mcp_summary_server || echo "Server process not found"
+
+# Check if port is listening
+echo -e "\n2. Checking if port is listening..."
+netstat -tlnp 2>/dev/null | grep 8080 || echo "Port 8080 not listening"
+
+# Test basic connectivity
+echo -e "\n3. Testing basic connectivity..."
+curl -s http://localhost:8080/ || echo "Cannot connect to localhost:8080"
+
+# Test MCP initialize
+echo -e "\n4. Testing MCP initialize..."
+curl -s -X POST http://localhost:8080/ \
+  -H "Content-Type: application/json" \
+  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-11-25","capabilities":{},"clientInfo":{"name":"test","version":"1.0.0"}}}' | jq .
+
+# Test tools list
+echo -e "\n5. Testing tools list..."
+curl -s -X POST http://localhost:8080/ \
+  -H "Content-Type: application/json" \
+  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}' | jq .
+
+echo -e "\n================================"
+echo "Diagnostics complete"
+echo "================================"

requirements.txt

@@ -0,0 +1,4 @@
+# requirements.txt for MCP Summary Server
+
+# HTTP requests for LLM communication
+requests>=2.31.0