Tools & Plugins
Osaurus includes a powerful plugin system for extending AI agent capabilities. Tools are exposed via the Model Context Protocol (MCP), allowing any MCP-compatible client to use them.
Why Native Tools?
Osaurus tools are pure native Swift and Rust implementations—not Python scripts running through interpreters. This matters for production AI agents:
| Aspect | Python/uv MCPs | Native Swift Tools |
|---|---|---|
| CPU Speed | Interpreter overhead + GIL limits parallelism | Compiled machine code, true multi-threading |
| Memory | Higher baseline (~50MB+) + garbage collector pauses | ARC provides precise, predictable memory control |
| Startup | Virtual environment + interpreter load (~200ms) | Binary loads in under 10ms |
| Dependencies | Requires Python runtime, pip packages | Self-contained binary, zero dependencies |
For AI agents executing dozens of tool calls per session, these differences compound significantly.
Official System Tools
These tools are maintained by the Osaurus team and available from the central registry:
| Plugin ID | Description | Tools |
|---|---|---|
osaurus.filesystem | File system operations | read_file, write_file, list_directory, create_directory, delete_file, move_file, search_files, get_file_info |
osaurus.browser | Headless WebKit browser | browser_navigate, browser_get_content, browser_get_html, browser_execute_script, browser_click, browser_type, browser_screenshot, browser_wait |
osaurus.git | Git repository utilities | git_status, git_log, git_diff, git_branch |
osaurus.search | Web search via DuckDuckGo | search, search_news, search_images |
osaurus.fetch | HTTP client for web requests | fetch, fetch_json, fetch_html, download |
osaurus.time | Time and date utilities | current_time, format_date |
Installing Tools
Use the Osaurus CLI to manage tools:
# Install a tool from the registry
osaurus tools install osaurus.browser
osaurus tools install osaurus.filesystem
# Install multiple tools
osaurus tools install osaurus.git osaurus.search
# List installed tools
osaurus tools list
# Search available tools
osaurus tools search browser
# Uninstall a tool
osaurus tools uninstall osaurus.time
Tools are installed to:
~/Library/Application Support/com.dinoki.osaurus/Tools/<plugin_id>/<version>/
Using Tools
Via MCP Clients
Once installed, tools are automatically available to any connected MCP client. Configure your client to connect to Osaurus:
Cursor / Claude Desktop:
{
"mcpServers": {
"osaurus": {
"command": "osaurus",
"args": ["mcp"]
}
}
}
The CLI proxies MCP over stdio to the running Osaurus server. If Osaurus isn't running, it auto-launches.
Via HTTP API
Tools are also accessible via HTTP endpoints:
| Endpoint | Method | Description |
|---|---|---|
/mcp/health | GET | Check MCP availability |
/mcp/tools | GET | List active tools |
/mcp/call | POST | Execute a tool |
Example: List available tools
curl http://127.0.0.1:1337/mcp/tools | jq
Example: Execute a tool
curl -X POST http://127.0.0.1:1337/mcp/call \
-H "Content-Type: application/json" \
-d '{
"name": "read_file",
"arguments": {"path": "/etc/hosts"}
}'
Via OpenAI Function Calling
Tools can also be used through the standard OpenAI function calling interface:
from openai import OpenAI
client = OpenAI(base_url="http://127.0.0.1:1337/v1", api_key="osaurus")
response = client.chat.completions.create(
model="llama-3.2-3b-instruct-4bit",
messages=[{"role": "user", "content": "What files are in my home directory?"}],
tools=[{
"type": "function",
"function": {
"name": "list_directory",
"description": "List contents of a directory",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string", "description": "Directory path"}
},
"required": ["path"]
}
}
}]
)
Tool Permissions
Each tool can specify a permission policy:
ask(default) — Prompts user for approval before each executionauto— Executes automatically if requirements are metdeny— Blocks execution entirely
Some tools require macOS system permissions:
| Permission | How to Grant | Use Case |
|---|---|---|
| Automation | System Settings → Privacy & Security → Automation | AppleScript, controlling other apps |
| Accessibility | System Settings → Privacy & Security → Accessibility | UI automation, input simulation |
The Tools UI shows which permissions are needed and provides one-click buttons to grant them.
Community Tools
The Osaurus Tools Registry hosts community-contributed plugins. Browse available tools:
osaurus tools search <keyword>
Example: osaurus-emacs
The osaurus-emacs plugin demonstrates a community tool that executes Emacs Lisp code:
osaurus tools install osaurus.emacs
Once installed, AI agents can interact with your Emacs instance:
{
"id": "execute_emacs_lisp_code",
"description": "Execute Emacs Lisp code in a running Emacs instance",
"parameters": {
"code": "(buffer-name)"
}
}
Remote MCP Providers
Osaurus can connect to external MCP servers and aggregate their tools into your local instance. This lets you use tools from remote MCP endpoints alongside your locally installed plugins.
Adding a Remote MCP Provider
- Open the Management window (⌘⇧M)
- Navigate to MCP Providers
- Click Add Provider
- Enter the provider details
Configuration Options
| Field | Description |
|---|---|
| Name | Display name for the provider |
| Endpoint | MCP server URL or command |
| Token | Authentication token (stored securely in Keychain) |
| Timeout | Request timeout in seconds |
| Streaming | Enable/disable streaming responses |
How It Works
- Tool Discovery — Osaurus queries the remote MCP server for available tools
- Namespacing — Remote tools are prefixed with the provider name (e.g.,
provider_toolname) to avoid conflicts - Unified Access — All tools—local and remote—appear in the same tools list
- Secure Storage — Authentication tokens are stored in macOS Keychain
Using Remote Tools
Once connected, remote tools appear alongside local tools:
# List all tools (local and remote)
curl http://127.0.0.1:1337/mcp/tools | jq
# Call a remote tool (namespaced)
curl -X POST http://127.0.0.1:1337/mcp/call \
-H "Content-Type: application/json" \
-d '{
"name": "provider_remote_tool",
"arguments": {"param": "value"}
}'
Remote tools are also available to MCP clients like Cursor and Claude Desktop through the standard osaurus mcp command.
Best Practices
- Use descriptive provider names — Makes it easy to identify tool origins
- Set appropriate timeouts — Remote tools may have higher latency than local ones
- Monitor connection health — Check the Management window for provider status
Creating Your Own Tools
Want to build a tool? See the Plugin Authoring Guide for complete instructions.
Quick start:
# Scaffold a new Swift plugin
osaurus tools create MyPlugin --language swift
# Build and install locally
cd MyPlugin
swift build -c release
osaurus tools install .
Central Registry
All official and community tools are indexed in the osaurus-tools repository:
- Browse plugins: See what's available
- Submit your plugin: Open a PR to add your tool
- Automatic CI: Your plugin JSON is validated on submission
Registry Structure
osaurus-tools/
├── plugins/ # Plugin specifications
│ ├── osaurus.browser.json
│ ├── osaurus.filesystem.json
│ └── ...
├── tools/ # Source code for official tools
└── scripts/ # Build and release automation
Troubleshooting
Tool not appearing in MCP clients
- Verify the tool is installed:
osaurus tools list - Check Osaurus is running:
osaurus status - Restart the MCP client to refresh the tool list
Permission denied errors
- Check which permissions the tool requires in the UI
- Grant permissions via System Settings → Privacy & Security
- No restart required—permissions take effect immediately
Tool execution fails
- Check Osaurus logs: Click the menu bar icon → View Logs
- Verify the tool's requirements are met
- Try reinstalling:
osaurus tools uninstall <id> && osaurus tools install <id>
To contribute a tool, see the Plugin Authoring Guide or browse the tools registry.