update README

Author: baryhuang

Diff for: Dockerfile

@@ -1,31 +1,65 @@
-# Use Python base image
-FROM python:3.10-slim-bookworm
+# --------
+# Builder stage
+# --------
+FROM python:3.11-slim AS builder
 
-# Install system dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
+# Install build tools and dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
     gcc \
     g++ \
+    libc6-dev \
+    libffi-dev \
+    libpq-dev \
+    make \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set working directory for builder
+WORKDIR /app
+
+# Copy the entire project first
+COPY . /app/
+
+# Upgrade pip and build wheels for all dependencies
+RUN pip install --upgrade pip \
+    && mkdir /wheels \
+    && pip wheel --wheel-dir=/wheels -r requirements.txt
+
+# --------
+# Final runtime stage
+# --------
+FROM python:3.11-slim
+
+# Install runtime dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libffi-dev \
+    libpq-dev \
     && rm -rf /var/lib/apt/lists/*
 
-# Install the project into `/app`
 WORKDIR /app
 
 # Copy the entire project
-COPY . /app
+COPY . /app/
+
+# Copy the wheels built in the builder stage
+COPY --from=builder /wheels /wheels
+
+# Install Python dependencies from the local wheel cache
+RUN pip install --upgrade pip \
+    && pip install --no-cache-dir --no-index --find-links=/wheels -r requirements.txt
+
+# Create models directory
+RUN mkdir -p /app/models
+
+# Pre-download models
+RUN python -c "from sentence_transformers import SentenceTransformer; \
+    model = SentenceTransformer('all-MiniLM-L6-v2'); \
+    model.save('/app/models/all-MiniLM-L6-v2')"
 
-# Install dependencies first for better caching
-RUN pip install --no-cache-dir \
-    mcp \
-    pydantic \
-    requests \
-    "numpy<2.0" \
-    fastapi \
-    uvicorn \
-    && pip install --no-cache-dir faiss-cpu sentence-transformers
+# Set environment variable for Sentence Transformers
+ENV SENTENCE_TRANSFORMERS_HOME=/app/models
 
-# Install the package in development mode
-RUN pip install -e .
+# Expose port
+EXPOSE 8000
 
 # Run the server
-ENTRYPOINT ["python", "-m", "mcp_server_any_openapi.server"]
+ENTRYPOINT ["python", "-m", "mcp_server_any_openapi.server"]

Diff for: README.md

@@ -13,7 +13,43 @@ query -> [Embedding] -> FAISS TopK -> OpenAPI docs -> MCP Client (Claude Desktop
 MCP Client -> Construct OpenAPI Request -> Execute Request -> Return Response
 ```
 
-## Usage Example
+## Multi-instance config example
+
+Here is the multi-instance config example. I design it so it can more flexibly used for multiple set of apis:
+```
+{
+  "mcpServers": {
+    "finance_openapi": {
+      "command": "docker",
+      "args": [
+        "run",
+        "-i",
+        "--rm",
+        "-e",
+        "OPENAPI_JSON_DOCS_URL=https://api.finance.com/openapi.json",
+        "-e",
+        "MCP_API_PREFIX=finance",
+        "buryhuang/mcp-server-any-openapi:latest"
+      ]
+    },
+    "healthcare_openapi": {
+      "command": "docker",
+      "args": [
+        "run",
+        "-i",
+        "--rm",
+        "-e",
+        "OPENAPI_JSON_DOCS_URL=https://api.healthcare.com/openapi.json",
+        "-e",
+        "MCP_API_PREFIX=healthcare",
+        "buryhuang/mcp-server-any-openapi:latest"
+      ]
+    }
+  }
+}
+```
+
+## Claude Desktop Usage Example
 Claude Desktop Project Prompt:
 ```
 You should get the api spec details from tools financial_api_request_schema
@@ -31,16 +67,15 @@ Get prices for all stocks
 
 ## Features
 
-- 🏗️ Multiple deployment options:
-  - Public Docker image (`buryhuang/mcp-server-any-openapi`)
-  - Local Python package (`pip install`)
+- 🧠 Use remote openapi json file as source, no local file system access, no updating required for API changes
 - 🔍 Semantic search using optimized MiniLM-L3 model (43MB vs original 90MB)
-- 📚 Comprehensive endpoint documentation including parameters, request bodies, and responses
 - 🚀 FastAPI-based server with async support
-- 🐳 Multi-platform Docker support
-- 🧠 Intelligent chunking for large OpenAPI specs (handles 100KB+ documents)
+- 🧠 Endpoint based chunking OpenAPI specs (handles 100KB+ documents), no loss of endpoint context
 - ⚡ In-memory FAISS vector search for instant endpoint discovery
-- 🐢 Cold start penalty (~15s for model loading)
+
+## Limitations
+- 🐢 Cold start penalty (~15s for model loading) if not using docker image
+- If using docker image, the size may be bigger
 
 ## Challenges Addressed
 
@@ -164,7 +199,7 @@ Official images support 3 platforms:
 ```bash
 # Build and push using buildx
 docker buildx create --use
-docker buildx build --platform linux/amd64,linux/arm64,linux/arm/v7 \
+docker buildx build --platform linux/amd64,linux/arm64 \
   -t buryhuang/mcp-server-any-openapi:latest \
   --push .
 ```

Diff for: pyproject.toml

@@ -17,7 +17,8 @@ dependencies = [
     "numpy",
     "sentence-transformers",
     "fastapi",
-    "uvicorn"
+    "uvicorn",
+    "huggingface-hub"
 ]
 
 [tool.hatch.build.targets.wheel]

Diff for: requirements.txt

@@ -0,0 +1,9 @@
+mcp==1.2.1
+pydantic>=2.10.1,<3.0.0
+requests==2.31.0
+numpy==1.24.3
+fastapi==0.115.8
+uvicorn==0.34.0
+faiss-cpu==1.7.4
+sentence-transformers==2.2.2
+huggingface-hub==0.14.1