MCP Tools Reference
Bootspring exposes 40+ MCP (Model Context Protocol) tools that your AI assistant can use. These tools provide the core functionality for agents, skills, workflows, intelligence, and more.
What Are MCP Tools?
MCP tools are capabilities that Bootspring makes available to AI assistants through the Model Context Protocol. When you ask your AI assistant to use Bootspring, it invokes these tools behind the scenes.
You: "Use the frontend-expert agent to build a login form"
│
▼
AI Assistant invokes: bootspring_agent
│
▼
Bootspring returns: Expert guidance + code
Available Tools
Core Tools
| Tool | Description |
|---|---|
bootspring_assist | Natural language assistant with recommendations |
bootspring_context | Query and manage project context |
bootspring_agent | Invoke specialized expert agents |
bootspring_skill | Search and use code patterns |
bootspring_generate | Generate or regenerate CLAUDE.md |
Task Management
| Tool | Description |
|---|---|
bootspring_todo | Manage development tasks |
bootspring_prd | Product requirement document management |
bootspring_memory | Access project memory and learnings |
Automation
| Tool | Description |
|---|---|
bootspring_orchestrator | Workflow orchestration and phases |
bootspring_loop | Autonomous task execution loops |
bootspring_autopilot | Git event-driven automation |
bootspring_seed | Project seeding and scaffolding |
bootspring_mvp | MVP code import and analysis |
Intelligence
| Tool | Description |
|---|---|
observer-session-metrics | Current session token/cost/tool metrics |
observer-cost-tracker | Cost tracking across time windows |
observer-summary | Aggregate stats and tool rankings |
observer-intelligence | Full 12-module intelligence report |
observer-efficiency | 6-dimension efficiency scoring |
observer-patterns | Anti-pattern detection (thrashing, retry storms, etc.) |
observer-alerts | Smart alerts with dynamic thresholds |
observer-trends | Time series analysis |
observer-compare | Side-by-side session comparison |
observer-optimize | Cost optimization recommendations |
observer-replay | Session timeline replay |
autopilot-status | Autopilot mode and feature status |
autopilot-config | Autopilot configuration |
autopilot-suggestions | Get prescriptive suggestions |
autopilot-learning | Suggestion effectiveness data |
Configuration & System
| Tool | Description |
|---|---|
bootspring_plugin | Plugin management |
bootspring_capabilities | Discover available capabilities |
bootspring_dashboard | Dashboard control and status |
bootspring_quality | Quality gates and checks |
bootspring_telemetry | Usage telemetry management |
bootspring_content | Content generation |
How to Use MCP Tools
Through Natural Language
Most of the time, you'll use tools implicitly through natural language:
"Generate a new context file for this project"
→ AI uses bootspring_generate
"Search for authentication patterns"
→ AI uses bootspring_skill
"Use the security-expert to review this code"
→ AI uses bootspring_agent
Explicit Tool Invocation
You can also explicitly request a tool:
Use the bootspring_agent tool with agent="database-expert" to design a schema.
Use the bootspring_skill tool with query="stripe subscriptions" to find patterns.
Tool Parameters
Each tool accepts specific parameters. For example:
bootspring_agent
bootspring_skill
bootspring_orchestrator
Tool Categories
Intelligence Tools
Tools that provide AI-powered assistance:
- bootspring_assist - General assistance with recommendations
- bootspring_agent - Specialized expert guidance
- bootspring_skill - Code pattern discovery
- bootspring_memory - Historical learnings
Automation Tools
Tools that automate development workflows:
- bootspring_orchestrator - Multi-phase workflows
- bootspring_loop - Autonomous execution
- bootspring_autopilot - Git-triggered automation
- bootspring_quality - Automated quality checks
Intelligence Tools (Observer + Autopilot)
Always-on session analytics and prescriptive recommendations:
- observer-session-metrics - Token usage, tool analytics, costs
- observer-intelligence - Full 12-module analysis report
- observer-efficiency - 6-dimension efficiency scoring (0-100)
- observer-patterns - 8 anti-pattern detectors
- observer-optimize - Cost optimization with model comparison
- autopilot-suggestions - Context-aware prescriptive recommendations
- autopilot-learning - Suggestion effectiveness tracking
Management Tools
Tools for project and task management:
- bootspring_todo - Task tracking
- bootspring_prd - Requirements management
- bootspring_context - Context management
- bootspring_generate - Context generation
System Tools
Tools for configuration and discovery:
- bootspring_plugin - Plugin management
- bootspring_capabilities - Feature discovery
- bootspring_dashboard - Dashboard control
- bootspring_telemetry - Usage tracking
Tool Response Format
All tools return structured responses:
Error responses:
Tool Permissions
Some tools require specific tiers:
| Tool | Free | Pro | Team |
|---|---|---|---|
| bootspring_assist | ✓ | ✓ | ✓ |
| bootspring_agent | Limited | Full | Full |
| bootspring_skill | Built-in | All | All + Custom |
| bootspring_orchestrator | Basic | Full | Full |
| bootspring_loop | ✗ | ✓ | ✓ |
| bootspring_autopilot | ✗ | ✓ | ✓ |
| bootspring_prd | ✓ | ✓ | ✓ |
| bootspring_quality | ✓ | ✓ | ✓ |
Debugging Tools
Verbose Mode
Enable verbose tool output:
Tool Logs
View tool invocation logs:
Best Practices
1. Let the AI Choose
Usually, let your AI assistant choose the right tool:
Help me set up authentication
The AI will automatically use bootspring_skill and bootspring_agent as needed.
2. Be Specific for Complex Tasks
For complex tasks, specify the tool:
Use the bootspring_orchestrator tool to start the launch workflow
3. Chain Tools
Tools can be chained together:
First use bootspring_skill to find the auth pattern,
then use bootspring_agent with security-expert to review it.
4. Check Capabilities First
Discover what's available:
Use bootspring_capabilities to show what tools I have access to.
Complete Tool Reference
Quick Reference Table
| Tool | Primary Use | Key Parameters |
|---|---|---|
bootspring_assist | General help | query, context, format |
bootspring_context | Context queries | action, query |
bootspring_agent | Expert guidance | agent, task, context |
bootspring_skill | Code patterns | query, category, limit |
bootspring_generate | Context gen | force, sections |
bootspring_todo | Task management | action, task, id |
bootspring_prd | Requirements | action, feature |
bootspring_memory | Learnings | query, type |
bootspring_orchestrator | Workflows | action, workflow, phase |
bootspring_loop | Autonomous | task, maxIterations |
bootspring_autopilot | Git automation | event, config |
bootspring_seed | Scaffolding | action, template |
bootspring_mvp | MVP import | source, analyze |
bootspring_plugin | Plugins | action, plugin |
bootspring_capabilities | Discovery | category |
bootspring_dashboard | Dashboard | action |
bootspring_quality | Quality gates | gate, files |
bootspring_telemetry | Telemetry | action, event |
bootspring_content | Content gen | type, topic |
observer-session-metrics | Session analytics | sessionId |
observer-intelligence | Full analysis | sessionId |
observer-efficiency | Efficiency score | sessionId |
observer-patterns | Anti-patterns | sessionId |
observer-optimize | Cost optimization | — |
autopilot-status | Autopilot status | — |
autopilot-suggestions | Suggestions | limit |
autopilot-config | Config | mode, key, value |
Next Steps
- bootspring_assist - Start with the main assistant tool
- bootspring_agent - Learn about agent invocation
- bootspring_skill - Discover code patterns
- bootspring_orchestrator - Automate workflows