datalens-dev-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| YC_IAM_TOKEN | No | Your Yandex Cloud IAM token (alternative to DATALENS_IAM_TOKEN). | |
| DATALENS_ORG_ID | No | Your Yandex Cloud organization ID. | |
| DATALENS_ENV_FILE | No | Path to environment file containing credentials. | |
| DATALENS_IAM_TOKEN | No | Your IAM token (alternative to YC_IAM_TOKEN). | |
| DATALENS_API_VERSION | No | API version. | auto |
| DATALENS_API_BASE_URL | No | Base URL for DataLens API. | https://api.datalens.tech |
| DATALENS_MCP_LOCAL_CONFIG | No | Path to local configuration file. | |
| DATALENS_MCP_ENABLE_WRITES | No | Enable write operations. | 0 |
| DATALENS_MCP_LIVE_ALLOW_SAVE | No | Allow save operations. | 0 |
| DATALENS_MCP_ENABLE_EXPERT_RPC | No | Enable expert RPC. | 0 |
| DATALENS_MCP_LIVE_ALLOW_PUBLISH | No | Allow publish operations. | 0 |
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": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| dl_server_infoA | Return active process/package identity, capability revision and installed version comparison without accessing DataLens or the project. |
| dl_auth_checkA | Run one harmless DataLens authentication probe and return a secret-free status. |
| dl_auth_refreshA | Refresh the process IAM credential once through the configured yc profile without returning the token. |
| dl_method_schemaC | Return the versioned backend and effect contract for one supported DataLens operation. |
| dl_workbooks_listC | List DataLens workbooks with bounded pagination and an explicit completeness marker. |
| dl_workbook_entriesB | List compact workbook objects with bounded full pagination and an explicit completeness marker. |
| dl_object_getB | Read one typed DataLens object by exact type, ID, branch and optional revision. |
| dl_object_relationsC | Read compact direct relations for one exact DataLens object ID. |
| dl_dashboard_snapshotC | Read one dashboard and only its direct dependencies; keep an optional style reference separate. |
| dl_dataset_validateB | Validate Dataset field GUIDs, calculation levels and known cross-field formula restrictions without mutation. |
| dl_dataset_previewC | Run a bounded Dataset query by exact field GUIDs; this is data evidence, not chart branch proof. |
| dl_authoring_defaultsC | Resolve compact generic, user, project, reference and explicit authoring defaults for one visual family. |
| dl_compile_recipeC | Compile a typed recipe to a compact local artifact reference; never access or write DataLens. |
| dl_editor_validateB | Validate one Editor draft or a mixed typed draft batch, including artifact references, without execution. |
| dl_object_diffB | Read one saved object and return the narrow semantic diff for a typed patch without mutation. |
| dl_object_createB | Create typed DataLens drafts or local JSON artifact references ({artifact_path: absolute path}) in dependency order, save, and read back. A typed Dataset uses top-level object_type/name/client_ref and nested dataset.connection_id/source/fields. References may override client_ref/depends_on only. |
| dl_object_updateB | Apply narrow saved-object patches with revision checks and per-object saved readback. A compiled Editor artifact update places artifact_path beside object_type/object_id/expected_revision; its tabs are mapped into saved data without echoing renderer source. |
| dl_object_publishB | Publish chart or dashboard objects only from a fresh verified saved revision, then read the published branch. |
| dl_operation_getB | Read one compact modifying-operation record by exact ID. |
| dl_operation_reconcileB | Reconcile an uncertain modifying result by exact target readback without replaying the write. |
| dl_backup_exportC | Export exact object snapshots and a completeness manifest to local files; this is not a full-restore claim. |
| dl_cleanup_previewB | Compute dependency-based preserve and delete sets without deleting anything. |
| dl_cleanup_applyA | Delete only the exact ordered objects confirmed from an unchanged cleanup preview. |
| dl_admin_inventoryA | Read documented license inventory and limits; report that license revoke is unsupported. |
| dl_admin_assign_licensesB | Apply explicit documented license assignments; this operation does not support revoke. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 25 tools
Each tool maps to a distinct DataLens operation (auth, object CRUD, validation, cleanup, admin), and descriptions clearly state bounded scope. Minor conceptual overlap between workbooks_list/workbook_entries and object_get/dashboard_snapshot is resolved by explicit wording.
All tools use snake_case with a consistent dl_ prefix, mostly following dl_<resource>_<action>. A few entries use noun-first or verb-first ordering (dl_compile_recipe, dl_workbooks_list), but the set remains predictable.
25 tools is heavy for a single MCP server and sits at the upper boundary where agents may struggle to scan capabilities. The functions are granular but could likely be consolidated without losing coverage.
The surface covers read, validate, create/update/publish, operations, cleanup, backup, and admin licensing, which is strong for DataLens development. Gaps include no direct single-object delete and no operation listing, though cleanup_apply and operation_get provide partial workarounds.