tony/hive
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Major WHOOSH system refactoring and feature enhancements

Browse Source 
- Migrated from HIVE branding to WHOOSH across all components
- Enhanced backend API with new services: AI models, BZZZ integration, templates, members
- Added comprehensive testing suite with security, performance, and integration tests
- Improved frontend with new components for project setup, AI models, and team management
- Updated MCP server implementation with WHOOSH-specific tools and resources
- Enhanced deployment configurations with production-ready Docker setups
- Added comprehensive documentation and setup guides
- Implemented age encryption service and UCXL integration

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
anthonyrawlins
2025-08-27 08:34:48 +10:00
parent 0e9844ef13
commit 268214d971
399 changed files with 57390 additions and 2045 deletions
Download Patch File Download Diff File Expand all files Collapse all files

84
mcp-server/README.md
View File

@@ -1,6 +1,6 @@
# 🐝 Hive MCP Server
# 🐝 WHOOSH MCP Server
Model Context Protocol (MCP) server that exposes the Hive Distributed AI Orchestration Platform to AI assistants like Claude.
Model Context Protocol (MCP) server that exposes the WHOOSH Distributed AI Orchestration Platform to AI assistants like Claude.
## Overview
@@ -34,12 +34,12 @@ Add to your Claude Desktop configuration (`~/Library/Application Support/Claude/
```json
{
"mcpServers": {
"hive": {
"whoosh": {
"command": "node",
"args": ["/path/to/hive/mcp-server/dist/index.js"],
"args": ["/path/to/whoosh/mcp-server/dist/index.js"],
"env": {
"HIVE_API_URL": "https://hive.home.deepblack.cloud",
"HIVE_WS_URL": "wss://hive.home.deepblack.cloud"
"WHOOSH_API_URL": "https://whoosh.home.deepblack.cloud",
"WHOOSH_WS_URL": "wss://whoosh.home.deepblack.cloud"
}
}
}
@@ -50,12 +50,12 @@ Add to your Claude Desktop configuration (`~/Library/Application Support/Claude/
```json
{
"mcpServers": {
"hive": {
"whoosh": {
"command": "node",
"args": ["/path/to/hive/mcp-server/dist/index.js"],
"args": ["/path/to/whoosh/mcp-server/dist/index.js"],
"env": {
"HIVE_API_URL": "http://localhost:8087",
"HIVE_WS_URL": "ws://localhost:8087"
"WHOOSH_API_URL": "http://localhost:8087",
"WHOOSH_WS_URL": "ws://localhost:8087"
}
}
}
@@ -64,53 +64,53 @@ Add to your Claude Desktop configuration (`~/Library/Application Support/Claude/
### 4. Restart Claude Desktop
The Hive MCP server will automatically connect to your running Hive cluster.
The WHOOSH MCP server will automatically connect to your running WHOOSH cluster.
## Available Tools
### Agent Management
- **`hive_get_agents`** - List all registered agents with status
- **`hive_register_agent`** - Register new agents in the cluster
- **`whoosh_get_agents`** - List all registered agents with status
- **`whoosh_register_agent`** - Register new agents in the cluster
### Task Management
- **`hive_create_task`** - Create development tasks for specialized agents
- **`hive_get_task`** - Get details of specific tasks
- **`hive_get_tasks`** - List tasks with filtering options
- **`whoosh_create_task`** - Create development tasks for specialized agents
- **`whoosh_get_task`** - Get details of specific tasks
- **`whoosh_get_tasks`** - List tasks with filtering options
### Workflow Management
- **`hive_get_workflows`** - List available workflows
- **`hive_create_workflow`** - Create new distributed workflows
- **`hive_execute_workflow`** - Execute workflows with inputs
- **`whoosh_get_workflows`** - List available workflows
- **`whoosh_create_workflow`** - Create new distributed workflows
- **`whoosh_execute_workflow`** - Execute workflows with inputs
### Monitoring
- **`hive_get_cluster_status`** - Get comprehensive cluster status
- **`hive_get_metrics`** - Retrieve Prometheus metrics
- **`hive_get_executions`** - View workflow execution history
- **`whoosh_get_cluster_status`** - Get comprehensive cluster status
- **`whoosh_get_metrics`** - Retrieve Prometheus metrics
- **`whoosh_get_executions`** - View workflow execution history
### Coordination
- **`hive_coordinate_development`** - Orchestrate complex multi-agent development projects
- **`whoosh_coordinate_development`** - Orchestrate complex multi-agent development projects
## Available Resources
### Real-time Cluster Data
- **`hive://cluster/status`** - Live cluster status and health
- **`hive://agents/list`** - Agent registry with capabilities
- **`hive://tasks/active`** - Currently running and pending tasks
- **`hive://tasks/completed`** - Recent task results and metrics
- **`whoosh://cluster/status`** - Live cluster status and health
- **`whoosh://agents/list`** - Agent registry with capabilities
- **`whoosh://tasks/active`** - Currently running and pending tasks
- **`whoosh://tasks/completed`** - Recent task results and metrics
### Workflow Data
- **`hive://workflows/available`** - All configured workflows
- **`hive://executions/recent`** - Recent workflow executions
- **`whoosh://workflows/available`** - All configured workflows
- **`whoosh://executions/recent`** - Recent workflow executions
### Monitoring Data
- **`hive://metrics/prometheus`** - Raw Prometheus metrics
- **`hive://capabilities/overview`** - Cluster capabilities summary
- **`whoosh://metrics/prometheus`** - Raw Prometheus metrics
- **`whoosh://capabilities/overview`** - Cluster capabilities summary
## Example Usage with Claude
### Register an Agent
```
Please register a new agent in my Hive cluster:
Please register a new agent in my WHOOSH cluster:
- ID: walnut-kernel-dev
- Endpoint: http://walnut.local:11434
- Model: codellama:34b
@@ -137,23 +137,23 @@ Use parallel coordination where possible.
### Monitor Cluster Status
```
What's the current status of my Hive cluster? Show me agent utilization and recent task performance.
What's the current status of my WHOOSH cluster? Show me agent utilization and recent task performance.
```
## Configuration
The MCP server connects to the Hive backend using domain endpoints by default. You can customize this by setting environment variables:
The MCP server connects to the WHOOSH backend using domain endpoints by default. You can customize this by setting environment variables:
**Production (Default):**
- **`HIVE_API_URL`** - `https://hive.home.deepblack.cloud`
- **`HIVE_WS_URL`** - `wss://hive.home.deepblack.cloud`
- **`WHOOSH_API_URL`** - `https://whoosh.home.deepblack.cloud`
- **`WHOOSH_WS_URL`** - `wss://whoosh.home.deepblack.cloud`
**Development/Local Testing:**
- **`HIVE_API_URL`** - `http://localhost:8087`
- **`HIVE_WS_URL`** - `ws://localhost:8087`
- **`WHOOSH_API_URL`** - `http://localhost:8087`
- **`WHOOSH_WS_URL`** - `ws://localhost:8087`
**Additional Options:**
- **`HIVE_TIMEOUT`** - Request timeout in milliseconds (default: `30000`)
- **`WHOOSH_TIMEOUT`** - Request timeout in milliseconds (default: `30000`)
Copy `.env.example` to `.env` and modify as needed for your deployment.
@@ -169,9 +169,9 @@ npm run watch
npm run dev
```
## Integration with Hive
## Integration with WHOOSH
This MCP server connects to your running Hive platform and provides a standardized interface for AI assistants to:
This MCP server connects to your running WHOOSH platform and provides a standardized interface for AI assistants to:
1. **Understand** your cluster capabilities and current state
2. **Plan** complex development tasks across multiple agents
@@ -182,7 +182,7 @@ The server automatically handles task queuing, agent assignment, and result aggr
## Security Notes
- The MCP server connects to your local Hive cluster
- The MCP server connects to your local WHOOSH cluster
- No external network access required
- All communication stays within your development environment
- Agent endpoints should be on trusted networks only