io.github.qg-aramai/coremodels

Official11 toolsLive

by qg-aramai

Schema modeling in JSON, JSON-LD, and other formats with CoreModels platform.

io.github.qg-aramai/coremodels (MCP Server)

This MCP server provides schema modeling focused on JSON and JSON-LD, plus other formats, using the CoreModels platform. Its described scope is schema modeling across multiple data serialization formats rather than general tooling or runtime execution.

🛠️ Key Features

Schema modeling in JSON
Schema modeling in JSON-LD
Schema modeling in other formats
Operates on the CoreModels platform

🚀 Use Cases

Modeling schemas expressed as JSON
Modeling schemas expressed as JSON-LD
Supporting schema needs across multiple formats via CoreModels

⚡ Developer Benefits

Tools (11) available for schema modeling workflows
Consistent schema modeling approach across JSON, JSON-LD, and additional formats

⚠️ Limitations

Details beyond schema modeling in JSON/JSON-LD/other formats are not provided.

Captured live from the server via tools/list.

export_json_ld

Export project data in JSON-LD format using a configured export profile. Use `fetch_json_ld_import_profiles` first to discover the configTypeId. At least one of exportTypes/exportElements/exportTaxonomies/exportDataTypes must be true. Tree-based mode (graphBased=false) requires exactly one nodeId; graph-based mode allows multiple or none.

Parameters11

graphProjectId	string	required
configTypeId	string	required	JSON-LD export profile id (from fetch_json_ld_import_profiles)
exportTypes	boolean	optional
exportElements	boolean	optional
exportTaxonomies	boolean	optional
exportDataTypes	boolean	optional
graphBased	boolean	optional	true = graph-based (no root); false = tree-based (requires exactly one nodeId)
spaceId	string	optional	Optional space id to filter export data; empty = all spaces
nodeIds	array	optional	For tree-based export, exactly one root node id; for graph-based, optional
includeSpace	boolean	optional
useDefaultType	boolean	optional

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    },
    "configTypeId": {
      "type": "string",
      "description": "JSON-LD export profile id (from fetch_json_ld_import_profiles)"
    },
    "exportTypes": {
      "type": "boolean",
      "default": false
    },
    "exportElements": {
      "type": "boolean",
      "default": false
    },
    "exportTaxonomies": {
      "type": "boolean",
      "default": false
    },
    "exportDataTypes": {
      "type": "boolean",
      "default": false
    },
    "graphBased": {
      "type": "boolean",
      "default": true,
      "description": "true = graph-based (no root); false = tree-based (requires exactly one nodeId)"
    },
    "spaceId": {
      "type": "string",
      "description": "Optional space id to filter export data; empty = all spaces"
    },
    "nodeIds": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "For tree-based export, exactly one root node id; for graph-based, optional"
    },
    "includeSpace": {
      "type": "boolean",
      "default": false
    },
    "useDefaultType": {
      "type": "boolean",
      "default": false
    }
  },
  "required": [
    "graphProjectId",
    "configTypeId"
  ]
}

fetch_json_ld_import_profiles

Fetch JSON-LD import/export profiles available for a project.

Parameters1

graphProjectId

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    }
  },
  "required": [
    "graphProjectId"
  ]
}

export_jsonschema

Export project data as a JSON Schema string.

Parameters4

graphProjectId	string	required
spaceId	string	optional
configTypeId	string	optional	Export profile id used for the JSON Schema export.
rootNodeId	string	optional	Optional root node id; empty/omitted to export without a fixed root.

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    },
    "spaceId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    },
    "configTypeId": {
      "type": "string",
      "description": "Export profile id used for the JSON Schema export."
    },
    "rootNodeId": {
      "type": "string",
      "description": "Optional root node id; empty/omitted to export without a fixed root."
    }
  },
  "required": [
    "graphProjectId"
  ],
  "additionalProperties": false
}

fetch_json_schema_import_profiles

Fetch JSON Schema import/export profiles available for a project.

Parameters1

graphProjectId

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string"
    }
  },
  "required": [
    "graphProjectId"
  ]
}

validate_json

Validate a JSON document against a project's stored JSON Schema. The schema is regenerated from the project using the supplied configTypeId (the export profile id) and rootNodeId. Provide the JSON to validate as a serialized string.

Parameters5

graphProjectId	string	required
configTypeId	string	optional	Profile id used to map mixins/relations to schema keywords
rootNodeId	string	required	Node id used as the root when generating the JSON Schema
spaceId	string	optional	Optional space id to scope the schema
jsonString	string	required	The JSON document to validate, serialized as a string

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    },
    "configTypeId": {
      "type": "string",
      "description": "Profile id used to map mixins/relations to schema keywords"
    },
    "rootNodeId": {
      "type": "string",
      "description": "Node id used as the root when generating the JSON Schema"
    },
    "spaceId": {
      "type": "string",
      "description": "Optional space id to scope the schema"
    },
    "jsonString": {
      "type": "string",
      "description": "The JSON document to validate, serialized as a string"
    }
  },
  "required": [
    "graphProjectId",
    "rootNodeId",
    "jsonString"
  ]
}

get_mixins_and_relation_groups

Get the project schema: all mixin definitions and all relation-group definitions. Use this once at the start of a session to discover the IDs needed by other tools (mixinId, columnId, relationGroupId). Returns compact positional arrays - see the "format" field for the layout.

Parameters1

graphProjectId

string

required

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    }
  },
  "required": [
    "graphProjectId"
  ],
  "additionalProperties": false
}

get_project_summary

Labels and IDs of types, elements, and taxonomies in the project. Each category is paginated independently. Pagination: - First call: omit page (defaults to 0). - Each category reports page, pageSize and hasMore. Re-request with page+1 for any category whose hasMore is true.

Parameters3

graphProjectId	string	required
page	integer	optional	0-based page index, applied independently to each category.
pageSize	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    },
    "page": {
      "type": "integer",
      "minimum": 0,
      "default": 0,
      "description": "0-based page index, applied independently to each category."
    },
    "pageSize": {
      "type": "integer",
      "minimum": 1,
      "maximum": 250,
      "default": 50
    }
  },
  "required": [
    "graphProjectId"
  ],
  "additionalProperties": false
}

list_projects

List the user's CoreModels projects as [id,name,accessLevel] (see the response "format" field). Use a returned id as graphProjectId for other tools. Pass searchTerm to filter by name (case-insensitive substring). Set includePublicProjects=true to also include public projects. Set includeAISummary=true to also return each project's saved AI-generated summary and the time it was generated (4th and 5th elements). Paged: page is 1-based; increment page up to the returned totalPages to get all results.

Parameters5

searchTerm	string	optional	Optional case-insensitive substring to filter projects by name.
includePublicProjects	boolean	optional	When true, public projects the user is not a member of are also included.
includeAISummary	boolean	optional	When true, each project row includes its saved AI-generated summary (markdown) and the time it was generated as 4th and 5th elements, or null if none has been generated.
page	integer	optional	1-based page number. Increment to page through results up to totalPages.
pageSize	integer	optional

Raw schema

{
  "type": "object",
  "properties": {
    "searchTerm": {
      "type": "string",
      "description": "Optional case-insensitive substring to filter projects by name."
    },
    "includePublicProjects": {
      "type": "boolean",
      "default": false,
      "description": "When true, public projects the user is not a member of are also included."
    },
    "includeAISummary": {
      "type": "boolean",
      "default": false,
      "description": "When true, each project row includes its saved AI-generated summary (markdown) and the time it was generated as 4th and 5th elements, or null if none has been generated."
    },
    "page": {
      "type": "integer",
      "minimum": 1,
      "default": 1,
      "description": "1-based page number. Increment to page through results up to totalPages."
    },
    "pageSize": {
      "type": "integer",
      "minimum": 1,
      "maximum": 250,
      "default": 50
    }
  },
  "additionalProperties": false
}

search_nodes

Search nodes in a CoreModels project. Returns compact positional arrays; the response "format" field describes the layout. Filters (provide at least one; they combine with AND): - nodeIds: exact id lookup - nodeType: one of Element, Type, Taxonomy, Exemplar, Component, Space, Tag, Mixin - expression: partial substring match on the node label (plain text, no wildcards) - spaceIds: restrict to specific spaces Optional flags: includeRelations, includeMixins, sortAttr, sortDesc, pageSize. Pagination: - First call: omit pagingToken. - If the response has a pagingToken, more pages exist. Repeat the same call with that exact token to get the next page. - If the response has no pagingToken, this was the last page.

Parameters11

graphProjectId	string	required
nodeType	string	optional
nodeIds	array	optional
expression	string	optional	Partial substring match against the node label. Plain text only - no wildcards, no regex, no '*', '%', '_' or '?' characters; the literal characters are matched as-is.
spaceIds	array	optional
includeRelations	boolean	optional
includeMixins	boolean	optional
sortAttr	string	optional
sortDesc	boolean	optional
pageSize	integer	optional
pagingToken	string	optional	Pagination token from the previous response. Always use the latest one.

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    },
    "nodeType": {
      "type": "string",
      "enum": [
        "Element",
        "Type",
        "Taxonomy",
        "Exemplar",
        "Component",
        "Space",
        "Tag",
        "Mixin"
      ]
    },
    "nodeIds": {
      "type": "array",
      "items": {
        "type": "string",
        "pattern": "^[a-f0-9]{32}$"
      }
    },
    "expression": {
      "type": "string",
      "description": "Partial substring match against the node label. Plain text only - no wildcards, no regex, no '*', '%', '_' or '?' characters; the literal characters are matched as-is.",
      "examples": [
        "Patient",
        "Address"
      ]
    },
    "spaceIds": {
      "type": "array",
      "items": {
        "type": "string",
        "pattern": "^[a-f0-9]{32}$"
      }
    },
    "includeRelations": {
      "type": "boolean",
      "default": false
    },
    "includeMixins": {
      "type": "boolean",
      "default": false
    },
    "sortAttr": {
      "type": "string",
      "enum": [
        "Label",
        "CreationTime",
        "UpdateTime",
        ""
      ]
    },
    "sortDesc": {
      "type": "boolean",
      "default": false
    },
    "pageSize": {
      "type": "integer",
      "minimum": 1,
      "maximum": 250,
      "default": 50
    },
    "pagingToken": {
      "type": "string",
      "description": "Pagination token from the previous response. Always use the latest one."
    }
  },
  "required": [
    "graphProjectId"
  ],
  "additionalProperties": false
}

export_shex

Export project data as a ShEx (Shape Expressions) schema string.

Parameters4

graphProjectId	string	required
spaceId	string	optional
nodeIds	array	optional	Optional type node ids to export; omit to export all types (optionally scoped to a space).
includeCardinality	boolean	optional	Whether to emit ShEx cardinality markers (?, *, +). Defaults to true.

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    },
    "spaceId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    },
    "nodeIds": {
      "type": "array",
      "description": "Optional type node ids to export; omit to export all types (optionally scoped to a space).",
      "items": {
        "type": "string",
        "pattern": "^[a-f0-9]{32}$"
      }
    },
    "includeCardinality": {
      "type": "boolean",
      "description": "Whether to emit ShEx cardinality markers (?, *, +). Defaults to true."
    }
  },
  "required": [
    "graphProjectId"
  ],
  "additionalProperties": false
}

run_code

Execute a JavaScript program that orchestrates this server's tools, and return only its result. Prefer this over many individual tool calls when a task needs several steps, looping, filtering, or combining data: intermediate results stay in the sandbox, so only what you return reaches the model. Inside the script: - listTools() -> [{name, summary}] discover available tools - getToolDoc(name) -> {name, description, parameters, required} inspect one tool's inputs - tools.<name>(args) -> parsed result call a tool (graphProjectId is injected automatically; do NOT pass it) - console.log(...) captured and returned alongside the result - return <value> JSON-serialized and returned Environment: sandboxed JavaScript, no network or filesystem, with limits on time, memory, statements and number of tool calls. Currently only read-only tools are callable from code.

Parameters2

graphProjectId	string	required
code	string	required	JavaScript to execute. Use tools.<name>(args), listTools(), getToolDoc(name); end with `return <value>`.

Raw schema

{
  "type": "object",
  "properties": {
    "graphProjectId": {
      "type": "string",
      "pattern": "^[a-f0-9]{32}$"
    },
    "code": {
      "type": "string",
      "description": "JavaScript to execute. Use tools.<name>(args), listTools(), getToolDoc(name); end with `return <value>`."
    }
  },
  "required": [
    "graphProjectId",
    "code"
  ],
  "additionalProperties": false
}

Install

Tools (11)

export_json_ldfetch_json_ld_import_profilesexport_jsonschemafetch_json_schema_import_profilesvalidate_jsonget_mixins_and_relation_groupsget_project_summarylist_projects

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://go.coremodels.io/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "coremodels": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://go.coremodels.io/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.qg-aramai/coremodels (MCP Server)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

export_json_ld

fetch_json_ld_import_profiles

export_jsonschema

fetch_json_schema_import_profiles

validate_json

get_mixins_and_relation_groups

get_project_summary

list_projects

search_nodes

export_shex

run_code

Install

Remote endpoint

Related servers