MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations indicate no destructive or read-only behavior, and the description adds meaningful context about browser login, token handling, session-only vs permanent authentication, and the no-argument behavior of returning a link. It gives useful behavioral disclosure beyond the schema and annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loads the authentication action, with the key usage modes explained in three sentences. Minor awkwardness like 'MCP.AI for IDE agents' slightly weakens clarity, but no sentence is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one optional parameter and no output schema, the description covers the essential flow: obtaining the link from the login, optional token input, and persistent config alternative. It is complete enough for an agent to make the right call.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Even though the schema only lists 'token' with no description, the tool description explains that 'token' is a JWT to paste, and that omitting the token returns a login link. This compensates well for the lack of param descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool authenticates to the MCP server via a browser login and access token, with two concrete modes of use. It is specific about the action and resource, though it does not explicitly differentiate from the sibling 'connect' tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance: prefer a config-level Authorization header for permanent login, or pass a token for session-only login, or call with no arguments to get the login link. It does not explicitly mention when not to use the tool, but the alternatives are well covered.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The Databricks-specific tools (e.g., databricks_run_sql, databricks_list_catalogs) are clearly distinct, each targeting a unique resource or action. However, the set also includes several platform-level tools (marketplace, authenticate, connect) that serve a different purpose, creating a mild mix of domains but without direct overlap or ambiguity.
The Databricks tools follow a consistent `databricks_verb_noun` pattern, but the platform tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) do not follow this pattern and use inconsistent naming conventions (some are single verbs, some are noun phrases, some are verb_noun). This mixing of styles makes the set feel patchwork rather than unified.
With 17 tools, the count is slightly above the typical well-scoped range of 3-15 and leans toward being heavy, especially considering that 6 of them are not Databricks-specific but general MCP platform utilities. The number is not extreme, but it feels a bit bloated for a server focused on Databricks.
The Databricks surface covers the core operations: listing catalogs/schemas/tables/warehouses, running SQL, polling and canceling statements, and user/account info. Minor gaps exist (e.g., no table or warehouse creation/deletion), but these are not obvious dead ends for the likely use cases. The platform tools (marketplace, connect, etc.) also provide comprehensive coverage of the MCP platform lifecycle.