feat: Add alt transports (#5)

* feat: Add HTTP transport support to TIM-MCP server

- Add HTTP transport mode alongside existing STDIO mode
- STDIO remains default mode for backward compatibility
- Add Click-based CLI with --http, --host, --port options
- Create transport configuration module with validation
- Add comprehensive test coverage (152 tests passing)
- Update documentation with deployment examples
- Align ruff configuration with pre-commit settings

* fix: Replace regex with glob patterns in file filtering

- Replace regex-based file pattern matching with intuitive glob patterns
- Remove include_readme flag - README.md now follows same filtering rules
- Simplify get_content tool implementation and documentation
- Update all tests to use glob patterns instead of regex
- Fix file filtering bug where invalid patterns included all files

* fix: reduce search results to 5

* fix: update search to filter non archived and core-team modules

* docs: add claude code instructions for test

* fix: resolve file filtering issue in get_content tool

- Remove automatic glob-to-regex conversion in _sanitize_list_parameter()
- Fix cache warning by removing invalid ttl parameter
- Update docstrings to reflect glob pattern usage
- Add regression test for the specific bug scenario

Author: daniel-butler-irl

.secrets.baseline

@@ -3,7 +3,7 @@
     "files": "go.sum|^.secrets.baseline$",
     "lines": null
   },
-  "generated_at": "2025-09-24T11:38:27Z",
+  "generated_at": "2025-09-25T11:22:38Z",
   "plugins_used": [
     {
       "name": "AWSKeyDetector"
@@ -82,87 +82,87 @@
         "hashed_secret": "887c04fb792699ceb6b29d9d4cb017d2854f8314",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 44,
+        "line_number": 43,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "f2fc748e82e02ed29053ddbb52f241a7e10e9a4f",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 45,
+        "line_number": 44,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "52a3342b7890ccda14efd7f947fa9ee6fda62529",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 62,
+        "line_number": 61,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "67e1c41f7a21c2c3e818b0192a161092ab074b69",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 63,
+        "line_number": 62,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "5eb844612e49e7ae88d1297b833d1057f4dddcb8",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 80,
+        "line_number": 79,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "462c772756a6e7e0f4c042b643072166fe491e80",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 232,
+        "line_number": 256,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "6aee17ecbbef021e3e8e9529facc4fa044180b64",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 284,
+        "line_number": 309,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "f10ba892b2ef72888d523de9812f53860cb752b5",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 300,
+        "line_number": 325,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "8744edae886af9ba92b6394b0b8820c228fecbcf",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 687,
+        "line_number": 726,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "ccd9fa3711ccbf21e2951d7443fcb0c53b651eb9",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 695,
+        "line_number": 734,
         "type": "Base64 High Entropy String",
         "verified_result": null
       },
       {
         "hashed_secret": "0de58b3d996020b8925e18e91bd571cf25cb7fd8",
         "is_secret": false,
         "is_verified": false,
-        "line_number": 703,
+        "line_number": 742,
         "type": "Base64 High Entropy String",
         "verified_result": null
       }

README.md

@@ -85,10 +85,70 @@ uv sync
 # Run tests
 uv run pytest
 
-# Run the server locally
+# Run the server locally (STDIO mode - default)
 uv run tim-mcp
 ```
 
+## Transport Modes
+
+TIM-MCP supports two transport modes for different deployment scenarios:
+
+### STDIO Mode (Default)
+
+STDIO is the default transport mode, perfect for MCP clients like Claude Desktop that spawn server processes on-demand.
+
+```bash
+# STDIO mode (default)
+tim-mcp
+
+# Explicit STDIO mode (same as default)
+tim-mcp --log-level DEBUG
+```
+
+### HTTP Mode
+
+HTTP mode runs the server as a web service, ideal for network deployments and multiple concurrent clients.
+
+```bash
+# HTTP mode with defaults (127.0.0.1:8000)
+tim-mcp --http
+
+# HTTP mode with custom port
+tim-mcp --http --port 8080
+
+# HTTP mode with custom host and port
+tim-mcp --http --host 0.0.0.0 --port 9000
+
+# HTTP mode with debug logging
+tim-mcp --http --log-level DEBUG
+```
+
+**HTTP Server URLs:**
+- Server runs at: `http://host:port/`
+- MCP endpoint: `http://host:port/mcp`
+
+**Production HTTPS:**
+For production deployments requiring HTTPS, use nginx as a reverse proxy:
+
+```nginx
+server {
+    listen 443 ssl;
+    server_name your-domain.com;
+
+    # SSL configuration
+    ssl_certificate /path/to/your/cert.pem;
+    ssl_certificate_key /path/to/your/key.pem;
+
+    location / {
+        proxy_pass http://127.0.0.1:8000;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+    }
+}
+```
+
 ### Environment Variables
 
 - `GITHUB_TOKEN` (optional): GitHub personal access token
@@ -171,6 +231,8 @@ This method downloads and runs TIM-MCP directly from the GitHub repository witho
 
 This method is ideal for development and testing, using your local clone of the repository.
 
+#### For Claude Desktop
+
 **Basic Configuration:**
 ```json
 {
@@ -213,6 +275,30 @@ This method is ideal for development and testing, using your local clone of the
 4. Update the `cwd` path in the configuration above to match your local repository path
 5. Add the configuration to your Claude Desktop settings
 
+#### For Claude Code
+
+For local development with Claude Code:
+
+```bash
+# Navigate to your tim-mcp directory first
+cd /path/to/your/tim-mcp
+
+# Add the local MCP server with GitHub token
+claude mcp add tim-mcp --env GITHUB_TOKEN=your_github_token_here \
+  -- uv run tim-mcp
+
+# Or without GitHub token (may hit rate limits)
+claude mcp add tim-mcp -- uv run tim-mcp
+
+# List configured MCP servers
+claude mcp list
+
+# Remove if needed
+claude mcp remove tim-mcp
+```
+
+**Important:** Run these commands from within your local tim-mcp repository directory, as Claude Code will use the current working directory when executing the MCP server.
+
 
 ## Verification
 
@@ -241,7 +327,7 @@ Once configured, TIM-MCP provides these tools to Claude for comprehensive Terraf
 
 **Usage Examples:**
 - Quick reference: `limit=3` for "I need a VPC module"
-- Exploring options: `limit=10-15` (default) for comparing alternatives
+- Exploring options: `limit=5-15` (default=5) for comparing alternatives
 - Comprehensive research: `limit=20+` for thorough analysis
 
 ### 2. `get_module_details`
@@ -287,20 +373,22 @@ Once configured, TIM-MCP provides these tools to Claude for comprehensive Terraf
 **Inputs:**
 - `module_id` (string, required): Full module identifier (e.g., "terraform-ibm-modules/vpc/ibm")
 - `path` (string, optional): Specific path - "" (root), "examples/basic", "modules/vpc", etc.
-- `include_files` (list[string], optional): Regex patterns for files to include
-- `exclude_files` (list[string], optional): Regex patterns for files to exclude
-- `include_readme` (boolean, optional): Include README.md for context (default: true)
+- `include_files` (list[string], optional): Glob patterns for files to include
+- `exclude_files` (list[string], optional): Glob patterns for files to exclude
 - `version` (string, optional): Git tag/branch to fetch from (default: "latest")
 
 **Output:** Markdown formatted content with file contents, organized by:
-- File paths and content
+- File paths and content with appropriate syntax highlighting
 - File sizes for reference
-- Context from README files when requested
-
-**Common Patterns:**
-- Input variables only: `include_files=["variables\\.tf$"]`
-- Basic example: `path="examples/basic", include_files=["main\\.tf$", "variables\\.tf$"]`
-- Complete module: `include_files=[".*\\.tf$"]`
+- README files are included if they match the patterns (like any other file)
+
+**Common Glob Patterns:**
+- Input variables only: `include_files=["variables.tf"]`
+- Basic example: `path="examples/basic", include_files=["*.tf"]`
+- Complete module: `include_files=["*.tf"]`
+- Documentation: `include_files=["*.md"]`
+- README only: `include_files=["README.md"]`
+- Everything: `include_files=["*"]` (or omit entirely)
 
 ## Tool Workflow