relative-interpreter-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RELATIVE_SERVICE_URL | No | The URL of the Relative service API. | http://localhost:4000/api |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_modelsD | Every model the service holds. |
| select_modelA | Open a model for this session and reset the scope to its root. Returns its outline. |
| create_modelA | Create an empty model and select it. |
| import_modelA | Create a model from exported Relative JSON and select it. |
| delete_modelA | Permanently delete a model and its snapshots. |
| get_scopeB | Which model is selected, how deep the submodel scope is, and whether it is editable. |
| enter_submodelA | Scope into a submodel node, so reads and edits apply inside it. |
| exit_submodelA | Leave the current submodel. Give a depth to jump straight to that level (0 = root). |
| get_modelA | The current scope as a compact outline: nodes with their kind and value, links as arrows between named ports, views, and validation findings. Submodels are summarised, not expanded — use enter_submodel or get_element to look inside one. |
| get_elementB | One node, link, or view in full, including everything the outline summarises away. |
| get_validationB | Validation findings for the whole selected model. |
| get_script_sourceB | A function node's script source, read-only. |
| edit_modelA | Apply one or more changes as a single undoable operation. Put every change you already know you want in one call — steps apply in order and a later step can reference something an earlier one created. References are names ("Switch") or port references ("Switch.out"); anything that does not resolve is rejected before it is sent, so an edit never silently does nothing. |
| link_external_submodelA | Add a submodel node backed by a model directory outside this one. The service validates the path against its RELATIVE_EXTERNAL_ROOTS allowlist and refuses anything outside it. |
| run_nodeC | Execute a function node's pipeline and settle the reactive cascade. |
| undoB | undo the last operation on the selected model. |
| redoB | redo the last operation on the selected model. |
| list_snapshotsC | Named on-disk checkpoints for the selected model. |
| save_snapshotB | Save a named, restorable checkpoint. |
| restore_snapshotC | Restore a snapshot. This is itself undoable. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| models | Every model the service holds. |
TDQS
Scored across 20 tools
Each tool targets a distinct resource and operation: scope management (get_scope, enter_submodel, exit_submodel), model inspection at different granularities (get_model, get_element, get_script_source), model lifecycle (create, select, import, delete, list), editing and execution (edit_model, run_node), validation, snapshots, and undo/redo. No overlapping purposes.
All tools follow a consistent verb_noun snake_case pattern, with plural nouns for list operations (list_models, list_snapshots) and clear imperative verbs. The only exceptions are undo and redo, which are universally accepted single verbs.
With 20 tools, the set is on the heavier side but remains justified by the complexity of a model interpreter. Each tool has a clear role, and no redundant or trivial tools are present.
The core workflow is well-covered: model lifecycle, editing, navigation, validation, execution, and snapshots. Minor gaps exist—such as missing export_model and delete_snapshot—but agents can work around these with existing operations.