MCP Integration

Bootspring uses the Model Context Protocol (MCP) to communicate with AI assistants. This open standard enables secure, standardized tool access across different AI platforms.

What is MCP?#

The Model Context Protocol (MCP) is an open protocol developed by Anthropic that enables AI assistants to securely access external tools and data sources.

┌─────────────────────────────────────────────────────────────────────────┐ │ MCP Architecture │ ├─────────────────────────────────────────────────────────────────────────┤ │ │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │ │ AI │ MCP │ MCP │ Tools │ Bootspring │ │ │ │ Assistant │◄──────►│ Server │◄──────►│ Features │ │ │ │ (Claude) │Protocol │ (Bootspring)│ │ │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ │ │ │ │ The AI assistant uses MCP to access Bootspring tools without │ │ direct integration - the protocol handles all communication. │ │ │ └─────────────────────────────────────────────────────────────────────────┘

Why MCP?#

BenefitDescription
StandardizedWorks with any MCP-compatible AI assistant
SecureControlled capability exposure
ExtensibleEasy to add new tools
PortableWorks across platforms (Claude, Cursor, etc.)

Bootspring MCP Server#

Bootspring runs as an MCP server, exposing 19 tools for AI assistants:

Core Tools#

ToolPurpose
bootspring_assistGeneral development assistance
bootspring_contextProject context access
bootspring_agentSpecialized agent invocation
bootspring_skillCode pattern generation
bootspring_qualityQuality gate execution

Generation Tools#

ToolPurpose
bootspring_generateContext file generation
bootspring_seedProject seeding/scaffolding
bootspring_prdPRD document generation
bootspring_mvpMVP planning
bootspring_contentContent generation

Workflow Tools#

ToolPurpose
bootspring_orchestratorWorkflow management
bootspring_loopAutonomous execution
bootspring_todoTask tracking
bootspring_dashboardDashboard integration

Configuration Tools#

ToolPurpose
bootspring_pluginPlugin management
bootspring_capabilitiesFeature discovery
bootspring_telemetryUsage analytics
bootspring_memoryPersistent memory
bootspring_autopilotAutopilot mode

Setting Up MCP#

Configuration File#

Create .mcp.json in your project root:

Loading code block...

Environment Variables#

Set your API key:

Loading code block...

Verifying Connection#

Test the MCP connection:

Loading code block...

Expected output:

✓ MCP server running ✓ 19 tools registered ✓ Authentication valid ✓ Ready for connections

How Tools Work#

Tool Invocation Flow#

┌─────────────────────────────────────────────────────────────────────────┐ │ Tool Invocation Flow │ ├─────────────────────────────────────────────────────────────────────────┤ │ │ │ 1. User Request │ │ "Help me add authentication" │ │ │ │ │ ▼ │ │ 2. AI Determines Tool │ │ → bootspring_agent with auth-expert │ │ │ │ │ ▼ │ │ 3. MCP Protocol │ │ AI ──► MCP Server ──► Bootspring │ │ │ │ │ ▼ │ │ 4. Tool Execution │ │ Bootspring processes request │ │ │ │ │ ▼ │ │ 5. Response │ │ Bootspring ──► MCP Server ──► AI ──► User │ │ │ └─────────────────────────────────────────────────────────────────────────┘

Tool Schema#

Each tool has a defined schema:

Loading code block...

Tool Responses#

Tools return structured responses:

Loading code block...

Compatible Platforms#

Claude Desktop#

Native MCP support:

Loading code block...

Claude Code (CLI)#

Automatic detection via .mcp.json:

Loading code block...

Cursor IDE#

Configure in settings:

Loading code block...

VS Code (Copilot Chat)#

Coming soon with MCP support in Copilot.

Security Model#

Capability Exposure#

Bootspring only exposes safe operations:

┌─────────────────────────────────────────────────────────────────────────┐ │ Security Model │ ├─────────────────────────────────────────────────────────────────────────┤ │ │ │ Exposed (Safe) │ Not Exposed (Protected) │ │ ───────────────────── │ ──────────────────────── │ │ • Read project context │ • Direct file system access │ │ • Generate code │ • Shell command execution │ │ • Run quality checks │ • Network requests │ │ • Access documentation │ • Environment variables │ │ • Invoke agents │ • Sensitive credentials │ │ │ │ └─────────────────────────────────────────────────────────────────────────┘

API Key Scoping#

API keys have scoped permissions:

Key TypePermissions
DevelopmentFull access in local environment
CI/CDQuality checks only
Read-onlyContext and documentation

Request Validation#

All tool requests are validated:

  1. Schema validation: Input matches expected format
  2. Permission check: API key has required access
  3. Rate limiting: Prevents abuse
  4. Audit logging: All requests logged

Advanced Configuration#

Custom Tool Parameters#

Override default tool behavior:

Loading code block...

Tool Filtering#

Enable/disable specific tools:

Loading code block...

Custom Server Port#

Run on a specific port:

Loading code block...

Debugging#

Enable Debug Logging#

Loading code block...

View Tool Calls#

Loading code block...

Output:

[MCP] Tool call: bootspring_agent [MCP] Input: { agent: "frontend-expert", task: "..." } [MCP] Duration: 1234ms [MCP] Output: { success: true, data: {...} }

Test Individual Tools#

Loading code block...

Troubleshooting#

Connection Issues#

Symptom: AI assistant can't connect to Bootspring

Solutions:

  1. Verify .mcp.json exists and is valid JSON
  2. Check BOOTSPRING_API_KEY is set
  3. Run bootspring mcp --test
  4. Restart the AI assistant

Tool Not Found#

Symptom: "Tool bootspring_xyz not found"

Solutions:

  1. Check tool name spelling
  2. Verify tool is enabled in config
  3. Check tier access (some tools require Pro/Team)

Slow Responses#

Symptom: Tools take a long time to respond

Solutions:

  1. Check network connectivity
  2. Reduce context size
  3. Use more specific queries
  4. Check server status at status.bootspring.com

Authentication Errors#

Symptom: "Invalid API key" errors

Solutions:

  1. Verify API key is correct
  2. Check key hasn't expired
  3. Ensure key has required permissions
  4. Regenerate key in dashboard

Protocol Details#

Message Format#

MCP uses JSON-RPC 2.0:

Loading code block...

Transport#

Bootspring MCP supports:

  • stdio: Default for local development
  • HTTP: For remote/CI environments
Loading code block...