Skip to main content
Glama
ADIKANT

datalens-dev-mcp

by ADIKANT

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
YC_IAM_TOKENNoYour Yandex Cloud IAM token (alternative to DATALENS_IAM_TOKEN).
DATALENS_ORG_IDNoYour Yandex Cloud organization ID.
DATALENS_ENV_FILENoPath to environment file containing credentials.
DATALENS_IAM_TOKENNoYour IAM token (alternative to YC_IAM_TOKEN).
DATALENS_API_VERSIONNoAPI version.auto
DATALENS_API_BASE_URLNoBase URL for DataLens API.https://api.datalens.tech
DATALENS_MCP_LOCAL_CONFIGNoPath to local configuration file.
DATALENS_MCP_ENABLE_WRITESNoEnable write operations.0
DATALENS_MCP_LIVE_ALLOW_SAVENoAllow save operations.0
DATALENS_MCP_ENABLE_EXPERT_RPCNoEnable expert RPC.0
DATALENS_MCP_LIVE_ALLOW_PUBLISHNoAllow 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

CapabilityDetails
tools
{
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.3/5.0

Scored across 25 tools

Disambiguation5/5

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.

Naming Consistency4/5

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.

Tool Count3/5

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.

Completeness4/5

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.

Maintenance

ActivityActive
ResponsivenessNo issues