# RationalBloks > RationalBloks, an MCP server by rationalbloks.com, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Deploy production REST and Neo4j Graph APIs from JSON schemas in seconds. - Canonical: https://www.anchorterminal.com/tools/rationalbloks-mcp - Markdown: https://www.anchorterminal.com/tools/rationalbloks-mcp.md (~3,100 tokens) - Slim: https://www.anchorterminal.com/tools/rationalbloks-mcp.min.md (~3,030 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/rationalbloks-mcp.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-10 # RationalBloks > Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/ - Kind: MCP server, by rationalbloks.com (https://rationalbloks.com) - Category: Cloud & infrastructure (https://www.anchorterminal.com/categories/infrastructure.md) - Listed because: It's published in the registry under rationalbloks.com, a namespace the registry only gives to whoever proves they control that domain. - What the official MCP registry says: Deploy production REST and Neo4j Graph APIs from JSON schemas in seconds. ## Facts - MCP registry: `com.rationalbloks/mcp` 0.16.0 - Endpoint: https://mcp.rationalbloks.com/ (streamable HTTP) - Package: pypi `rationalbloks-mcp` (stdio) - Source: https://github.com/rationalbloks/rationalbloks-mcp - PyPI downloads a week: 213 - GitHub stars: 1 - Registry entry updated: 2026-10-07 ## Tools - Tools it lists (50, about 13,624 tokens of context, `tools/list` without credentials over MCP 2026-07-28, checked 2026-10-03 22:16 UTC): - `list_projects` (read-only): List all your RationalBloks projects with their status and URLs - `get_project` (read-only): Get detailed information about a specific project - `get_schema` (read-only): Get the JSON schema definition of a project in FLAT format. Returns the schema structure where each table name maps directly to field definitions. This is the… - `get_user_info` (read-only): Get information about the authenticated user - `list_clusters` (read-only): List your registered BYOC resource pools (client-owned Kubernetes clusters). Each returned cluster has an 'id' you MUST pass as create_project's cluster_id to… - `get_job_status` (read-only): Check the status of a job (a create, deploy, promotion, rollback or deletion). STATUS VALUES: pending (queued), processing (in progress), completed (success),… - `list_project_jobs` (read-only): List a project's jobs, newest first: every create, deploy, promotion, rollback, resource change and module operation, each with its status, error, failure_side… - `get_project_info` (read-only): Get detailed project info including deployment status and resource usage. DEPLOYMENT STATUS: Running (healthy), Pending (starting), CrashLoopBackOff (init… - `get_version_history` (read-only): Get the deployment and version history (git commits) for a project. Shows all schema changes with commit SHA, timestamp, and message. USE CASES: Review what… - `get_template_schemas` (read-only): Get pre-built template schemas for common use cases. ⭐ USE THIS FIRST when creating a new project! Templates show the CORRECT schema format with: proper FLAT… - `get_schema_reference` (read-only): Get the reference for ADVANCED schema features the templates do not show — read this before adding authorization or derived fields to a schema. Covers:… - `get_subscription_status` (read-only): Get your subscription tier, limits, and usage - `get_project_usage` (read-only): Get resource usage metrics (CPU, memory) for a project - `get_project_storage_usage` (read-only): Get object-storage usage for a project: file count and bytes used against the plan limits. - `list_project_files` (read-only): List a project's uploaded files (metadata + public URLs), most recent first. Inspection only — files are not streamed through MCP. - `get_schema_at_version` (read-only): Get the schema as it was at a specific version/commit - `create_project` (writes): Create a new RationalBloks project from a JSON schema. ⚠️ CRITICAL RULES - READ BEFORE CREATING SCHEMA: 1. FLAT FORMAT (REQUIRED): ✅ CORRECT: {users: {email:… - `update_schema` (writes): Update a project's schema (saves to database, does NOT deploy). ⚠️ CRITICAL: Follow ALL rules from create_project: • FLAT format (no 'fields' nesting) •… - `patch_schema` (writes): Change PART of a project's schema (saves to database, does NOT deploy). Send only the change. The server applies it to the saved schema, in order and all… - `deploy_staging` (writes): Deploy a project to the staging environment. This triggers: (1) Schema validation, (2) Docker image build, (3) GitHub commit, (4) Kubernetes deployment, (5)… - `deploy_production` (writes): Promote staging to production (requires paid plan) A deploy that drops data is refused until you pass confirm_destructive=true after reviewing the plan. One… - `delete_project` (writes): Delete a project (removes GitHub repo, K8s deployments, and database). It runs as a job: poll the returned job_id with get_job_status until it is completed.… - `rollback_project` (writes): Rollback a project to a previous version. ⚠️ WARNING: This reverts schema AND code to the specified commit. Database data is NOT rolled back. Use… - `rename_project` (writes): Rename a project (changes display name, not project_code) - `get_graph_schema` (read-only): Get the graph schema definition of a project. Returns the hierarchical schema with nodes (entities) and relationships. Graph schemas define entity hierarchies… - `get_graph_template_schemas` (read-only): Get pre-built graph template schemas for common use cases. ⭐ USE THIS FIRST when creating a new graph project! Templates show the CORRECT graph schema format… - `get_graph_version_history` (read-only): Get the deployment and version history for a graph project. Shows all schema changes with commit SHAs, timestamps, version numbers, and messages. Use this to… - `get_graph_schema_at_version` (read-only): Get the graph schema as it existed at a specific version/commit. Use get_graph_version_history to find commit SHAs. Useful for comparing schemas across… - `get_graph_project_info` (read-only): Get detailed graph project information including Kubernetes deployment status, Neo4j database health, pod status, and resource usage. Use this after deployment… - `create_graph_project` (writes): Create a new Neo4j graph database project from a hierarchical JSON schema. ⚠️ GRAPH SCHEMA FORMAT — READ BEFORE CREATING: Graph schemas define nodes (entities)… - `update_graph_schema` (writes): Update a graph project's schema (saves to database, does NOT deploy). ⚠️ Follow ALL rules from create_graph_project: • Must have "nodes" key with at least one… - `deploy_graph_staging` (writes): Deploy a graph project to the staging environment. This triggers: (1) Schema validation, (2) Neo4j entity code generation, (3) Docker image build, (4) GitHub… - `deploy_graph_production` (writes): Promote graph staging to production. Creates a separate production Neo4j instance with its own credentials and database. Requires paid plan. A deploy that… - `delete_graph_project` (writes): Delete a graph project (removes GitHub repo, K8s deployments, Neo4j database, and credentials). It runs as a job: poll the returned job_id with get_job_status… - `rollback_graph_project` (writes): Rollback a graph project to a previous version. ⚠️ WARNING: This reverts schema AND code to the specified commit. Neo4j data is NOT rolled back. Use… - `create_graph_node` (writes): Create a single node in a deployed graph project. REQUIRES: Project must be deployed (use deploy_graph_staging first). The entity_type must match an entity key… - `get_graph_node` (read-only): Get a specific node by its entity_id from a deployed graph project. Returns all node properties including created_at and updated_at timestamps. - `list_graph_nodes` (read-only): List nodes of a specific entity type from a deployed graph project. Supports pagination with limit/offset. Returns nodes ordered by creation date (newest… - `update_graph_node` (writes): Update properties of an existing node in a deployed graph project. Only send the fields you want to change — unspecified fields remain unchanged. - `delete_graph_node` (writes): Delete a node and all its relationships from a deployed graph project. ⚠️ This also removes all relationships connected to this node (DETACH DELETE). - `create_graph_relationship` (writes): Create a relationship between two nodes in a deployed graph project. The rel_type must match a relationship key from the project schema. Use… - `get_node_relationships` (read-only): Get all relationships connected to a specific node. Supports direction filtering (incoming, outgoing, both) and relationship type filtering. - `delete_graph_relationship` (writes): Delete a specific relationship by its internal ID. Use get_node_relationships to find relationship IDs. - `bulk_create_graph_nodes` (writes): Create multiple nodes at once (up to 500 per call). Uses Neo4j UNWIND for high performance. Essential for knowledge graph population — create hundreds of… - `bulk_create_graph_relationships` (writes): Create multiple relationships at once (up to 500 per call). Uses Neo4j UNWIND for high performance. Essential for connecting knowledge — link hundreds of… - `search_graph_nodes` (read-only): Search for nodes by property values in a deployed graph project. Supports exact match and contains search (prefix value with ~ for contains). Examples: Exact:… - `fulltext_search_graph` (read-only): Search across ALL string properties of ALL nodes in a deployed graph using free-text queries. Unlike search_graph_nodes (which filters by specific property),… - `traverse_graph` (read-only): Walk the graph from a starting node, discovering connected knowledge. Returns all nodes reachable within max_depth hops, with their distance from the start.… - `get_graph_statistics` (read-only): Get statistics about a deployed graph: total node count, total relationship count, counts per entity type, counts per relationship type. Essential for… - `get_graph_data_schema` (read-only): Get the runtime schema of a DEPLOYED graph project — shows the actual entity types and relationship types available for data operations. Returns: Available… - How its tools read to an agent (0 errors, 17 warnings, 1 note, about 13,624 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score): - warn TC07 create_graph_project: the description is about 648 tokens - warn TC07 create_project: the description is about 653 tokens - warn TC07 patch_schema: the description is about 505 tokens - warn TC13 bulk_create_graph_nodes: nodes[].data (object with no properties) - warn TC13 bulk_create_graph_relationships: relationships[].data (object with no properties) - warn TC13 create_graph_node: data (object with no properties) - warn TC13 create_graph_project: schema (object with no properties) - warn TC13 create_graph_relationship: data (object with no properties) - warn TC13 create_project: schema (object with no properties) - warn TC13 patch_schema: operations[] (object with no properties) - warn TC13 search_graph_nodes: filters (object with no properties) - warn TC13 update_graph_node: data (object with no properties) - warn TC13 update_graph_schema: schema (object with no properties) - warn TC13 update_schema: schema (object with no properties) - warn TC21 delete_project: described almost the same as delete_graph_project (92% of the same words) - warn TC21 deploy_production: described almost the same as deploy_graph_production (83% of the same words) - warn TC23 server: 50 tools - note TC24 server: 50 of 50 tools have no outputSchema - JSON: https://www.anchorterminal.com/api/v1/tools/rationalbloks-mcp.json - Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming