RationalBloks

RationalBloks MCP Server

Deploy production APIs in minutes. 48 tools for projects, schemas, deployments, object storage, and graph data — delivered on infrastructure you own (self-host or your own BYOC cluster).

What Is This?

RationalBloks MCP lets AI agents (Claude, Cursor, etc.) deploy production APIs from a JSON schema. No backend code to write. No infrastructure to manage.

"Create a task management API with tasks, projects, and users"
→ 2 minutes later: Production API running on Kubernetes

Installation

# recommended — no install step, always the latest release
uvx rationalbloks-mcp@latest

# or install into an environment
pip install rationalbloks-mcp

Quick Start

1. Get Your API Key

Visit rationalbloks.com/settings and create an API key.

2. Configure Your AI Agent

VS Code - Add to .vscode/mcp.json (Cursor: .cursor/mcp.json with a mcpServers key):

{
  "servers": {
    "rationalbloks": {
      "command": "uvx",
      "args": ["rationalbloks-mcp@latest"],
      "env": {
        "RATIONALBLOKS_API_KEY": "rb_sk_your_key_here"
      }
    }
  }
}

Claude Desktop - Add to claude_desktop_config.json:

{
  "mcpServers": {
    "rationalbloks": {
      "command": "uvx",
      "args": ["rationalbloks-mcp@latest"],
      "env": {
        "RATIONALBLOKS_API_KEY": "rb_sk_your_key_here"
      }
    }
  }
}

---

Remote (no install): point any MCP client at https://mcp.rationalbloks.com/mcp (Streamable HTTP) with Authorization: Bearer rb_sk_....

---

48 Tools

Relational Read Operations (15 tools)

Tool	Description
list_projects	List all your projects
get_project	Get project details
get_schema	Get current JSON schema
get_user_info	Get authenticated user info
get_job_status	Check deployment job status
get_project_info	Detailed project info with K8s status
get_version_history	Git commit history
get_template_schemas	Pre-built schema templates
get_schema_reference	Advanced schema features reference (__policy__, computed, __constraints__, __audit__)
get_subscription_status	Plan and usage limits
get_project_usage	CPU/memory metrics
get_project_storage_usage	Object-storage file count and bytes used vs limits
list_project_files	List uploaded files (metadata + public URLs)
get_schema_at_version	Schema at specific commit
list_clusters	List your BYOC resource pools (client-owned clusters)

Relational Write Operations (7 tools)

Tool	Description
create_project	Create new project from schema (cluster_id of one of your BYOC pools is required; backend_type python or rust)
update_schema	Update project schema (dry_run: true previews the migration plan without saving)
deploy_staging	Deploy to staging environment
deploy_production	Deploy to production
delete_project	Delete project permanently
rollback_project	Rollback to previous version
rename_project	Rename project

Graph Schema Operations (11 tools)

Tool	Description
get_graph_schema	Get graph project schema
get_graph_template_schemas	Pre-built graph schema templates
get_graph_version_history	Graph schema version history
get_graph_schema_at_version	Schema at specific version
get_graph_project_info	Graph project info with K8s/Neo4j status
create_graph_project	Create Neo4j graph project
update_graph_schema	Update graph schema
deploy_graph_staging	Deploy graph to staging
deploy_graph_production	Deploy graph to production
delete_graph_project	Delete graph project
rollback_graph_project	Rollback graph to previous version

Graph Data Operations (15 tools)

Tool	Description
create_graph_node	Create a single node
get_graph_node	Get node by ID
list_graph_nodes	List nodes by entity type
update_graph_node	Update node properties
delete_graph_node	Delete a node
create_graph_relationship	Create a relationship
get_node_relationships	Get node's relationships
delete_graph_relationship	Delete a relationship
bulk_create_graph_nodes	Bulk create nodes
bulk_create_graph_relationships	Bulk create relationships
search_graph_nodes	Search nodes by property filters
fulltext_search_graph	Full-text search across all fields
traverse_graph	Traverse graph from a node
get_graph_statistics	Get graph statistics (counts)
get_graph_data_schema	Get deployed data schema

---

Schema Format

Schemas must be in FLAT format:

{
  "tasks": {
    "title": {"type": "string", "max_length": 200, "required": true},
    "status": {"type": "string", "max_length": 50, "enum": ["pending", "done"]},
    "due_date": {"type": "date", "required": false}
  },
  "projects": {
    "name": {"type": "string", "max_length": 100, "required": true}
  }
}

Field Types

Type	Required Properties
string	max_length
text	None
integer	None
decimal	precision, scale
boolean	None
uuid	None
date	None
datetime	None
json	None

Auto-Generated Fields

These are automatic - don't define them:

• id (UUID primary key)
• created_at (datetime)
• updated_at (datetime)

User Authentication

Use the built-in app_users table:

{
  "employee_profiles": {
    "user_id": {"type": "uuid", "foreign_key": "app_users.id", "required": true},
    "department": {"type": "string", "max_length": 100}
  }
}

---

Frontend

For frontend development, use our NPM packages:

npm install @rationalbloks/frontblok-auth @rationalbloks/frontblok-crud

These provide:

• frontblok-auth: Authentication, login, tokens, user context
• frontblok-crud: Generic CRUD via getApi().getAll(), getApi().create(), etc.

---

Environment Variables

Variable	Description	Default
RATIONALBLOKS_API_KEY	Your API key (required for stdio; HTTP clients send it as a Bearer token per request)	-
TRANSPORT	stdio or http	stdio
HOST / PORT	Bind address for TRANSPORT=http	0.0.0.0 / 8000
LOGICBLOK_URL	LogicBlok gateway base URL	https://logicblok.rationalbloks.com
RATIONALBLOKS_DEBUG	Print full tracebacks on startup errors	unset

---

Support

• Documentation: rationalbloks.com/documentation
• Email: support@rationalbloks.com

License

Proprietary - Copyright 2026 RationalBloks. All Rights Reserved.