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

ToolDescription
bootspring_assistNatural language assistant with recommendations
bootspring_contextQuery and manage project context
bootspring_agentInvoke specialized expert agents
bootspring_skillSearch and use code patterns
bootspring_generateGenerate or regenerate CLAUDE.md

Task Management

ToolDescription
bootspring_todoManage development tasks
bootspring_prdProduct requirement document management
bootspring_memoryAccess project memory and learnings

Automation

ToolDescription
bootspring_orchestratorWorkflow orchestration and phases
bootspring_loopAutonomous task execution loops
bootspring_autopilotGit event-driven automation
bootspring_seedProject seeding and scaffolding
bootspring_mvpMVP code import and analysis

Intelligence

ToolDescription
observer-session-metricsCurrent session token/cost/tool metrics
observer-cost-trackerCost tracking across time windows
observer-summaryAggregate stats and tool rankings
observer-intelligenceFull 12-module intelligence report
observer-efficiency6-dimension efficiency scoring
observer-patternsAnti-pattern detection (thrashing, retry storms, etc.)
observer-alertsSmart alerts with dynamic thresholds
observer-trendsTime series analysis
observer-compareSide-by-side session comparison
observer-optimizeCost optimization recommendations
observer-replaySession timeline replay
autopilot-statusAutopilot mode and feature status
autopilot-configAutopilot configuration
autopilot-suggestionsGet prescriptive suggestions
autopilot-learningSuggestion effectiveness data

Configuration & System

ToolDescription
bootspring_pluginPlugin management
bootspring_capabilitiesDiscover available capabilities
bootspring_dashboardDashboard control and status
bootspring_qualityQuality gates and checks
bootspring_telemetryUsage telemetry management
bootspring_contentContent 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

Loading code block...

bootspring_skill

Loading code block...

bootspring_orchestrator

Loading code block...

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:

Loading code block...

Error responses:

Loading code block...

Tool Permissions

Some tools require specific tiers:

ToolFreeProTeam
bootspring_assist
bootspring_agentLimitedFullFull
bootspring_skillBuilt-inAllAll + Custom
bootspring_orchestratorBasicFullFull
bootspring_loop
bootspring_autopilot
bootspring_prd
bootspring_quality

Debugging Tools

Verbose Mode

Enable verbose tool output:

Loading code block...

Tool Logs

View tool invocation logs:

Loading code block...

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

ToolPrimary UseKey Parameters
bootspring_assistGeneral helpquery, context, format
bootspring_contextContext queriesaction, query
bootspring_agentExpert guidanceagent, task, context
bootspring_skillCode patternsquery, category, limit
bootspring_generateContext genforce, sections
bootspring_todoTask managementaction, task, id
bootspring_prdRequirementsaction, feature
bootspring_memoryLearningsquery, type
bootspring_orchestratorWorkflowsaction, workflow, phase
bootspring_loopAutonomoustask, maxIterations
bootspring_autopilotGit automationevent, config
bootspring_seedScaffoldingaction, template
bootspring_mvpMVP importsource, analyze
bootspring_pluginPluginsaction, plugin
bootspring_capabilitiesDiscoverycategory
bootspring_dashboardDashboardaction
bootspring_qualityQuality gatesgate, files
bootspring_telemetryTelemetryaction, event
bootspring_contentContent gentype, topic
observer-session-metricsSession analyticssessionId
observer-intelligenceFull analysissessionId
observer-efficiencyEfficiency scoresessionId
observer-patternsAnti-patternssessionId
observer-optimizeCost optimization
autopilot-statusAutopilot status
autopilot-suggestionsSuggestionslimit
autopilot-configConfigmode, key, value

Next Steps