Databricks MCP server
io.github.mcp-dir/databricks-mcpmcp-dirstreamable-httpv0.1.0Scanned
Your Databricks Lakehouse in natural language: run SQL on your SQL warehouses, track long-running qu
17 tools: 1 can delete or cancel things, 5 change things and 11 only read.
- Reads private data · 7
- Reads text others write · 2
- Can send data out · 0
- 3 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Databricks MCP server can do
The Databricks MCP server is published by the GitHub account mcp-dir. It has 17 tools. It can delete or cancel things (1 tool: databricks_cancel_statement) and create or change data (5 tools: databricks_current_user, databricks_run_sql, report_bug, marketplace and 1 more). 11 tools only read.
7 tools read private data (databricks_list_warehouses, databricks_get_warehouse, databricks_run_sql and 4 more); 2 tools bring in text other people can write (databricks_list_catalogs and marketplace).
The fixed checks matched 3 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 9, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
17 tools
Deletes or cancels 1Claude Code: deny
databricks_cancel_statementCancela um ou mais statements em execução por id.1 finding
Why it is in this group
- The name "databricks_cancel_statement" says "cancel": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.
Findings
- Warn
The server marks "databricks_cancel_statement" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "databricks_cancel_statement" says "cancel": a word for removing or ending something.
Description, as the server wrote it Cancela um ou mais statements em execução por id. Aceita lista (`statement_ids`).
Annotations the server declares
- title: databricks_cancel_statement
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Changes things 5Claude Code: ask
authenticateMCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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: "<jwt>" } after the user pastes, or with no args to get the link.
Annotations the server declares
- title: Authenticate
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_current_userIdentifica o usuário do PAT no workspace (whoami via SCIM Me).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Identifica o usuário do PAT no workspace (whoami via SCIM Me). Útil pra confirmar qual conta/host está conectado e validar o token.
Annotations the server declares
- title: databricks_current_user
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_run_sqlExecuta uma instrução SQL num SQL warehouse (Statement Execution API).Reads private dataNo findings
Why it is in this group
- The name "databricks_run_sql" says "run": a word for a change.
- The input takes a statement or command to run (input.statement), which can change anything it can reach.
What it can reach
- private-dataThe name says "run" and the input takes a statement (input.statement): it reads databases.
Description, as the server wrote it Executa uma instrução SQL num SQL warehouse (Statement Execution API). Retorna colunas + linhas quando termina dentro do wait_timeout; senão devolve statement_id + state pra polling via databricks_get_statement. Se `warehouse_id` não for informado, escolhe um warehouse RUNNING automaticamente. PREFIRA queries parametrizadas (`parameters`) a interpolar valores na string (proteção contra SQL injection). SQL é arbitrário (pode DML/DDL) — confirme antes de mutar dados. Bulk support: accepts warehouse_ids for batched execution.
Annotations the server declares
- title: databricks_run_sql
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
marketplaceThe official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them.Reads text others write1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...ating the tool list. If the MCP needs a credential/login, invoke returns a connect link; i..."
Description, as the server wrote it The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.
Annotations the server declares
- title: Marketplace
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
report_bugReport a bug, missing feature, or send feedback.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.
Annotations the server declares
- title: Report Bug
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 11Show 11 read-only tools
connectReturns connection status and URLs.1 finding
Why it is in this group
- The description's first verb is "return": a word for reading.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...nticated:true and empty pending[]. When credentials are missing, returns connect_url for th..."
Description, as the server wrote it Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.
Annotations the server declares
- title: Connection Status
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_get_statementStatus + resultado de um ou mais statements por id (polling de queries longas que voltaram PENDING/RUNNING do run_sql).Reads private dataNo findings
Why it is in this group
- The name "databricks_get_statement" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "status" and "sql": it reads databases.
Description, as the server wrote it Status + resultado de um ou mais statements por id (polling de queries longas que voltaram PENDING/RUNNING do run_sql). Aceita lista (`statement_ids`).
Annotations the server declares
- title: databricks_get_statement
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_get_tableDetalha uma ou mais tabelas (colunas, tipos) por nome completo `catalog.schema.table`.Reads private dataNo findings
Why it is in this group
- The name "databricks_get_table" says "get": a word for reading.
What it can reach
- private-dataThe name "databricks_get_table" says "get" and "table": it reads databases.
- private-dataThe description's first sentence says "table": it reads databases.
Description, as the server wrote it Detalha uma ou mais tabelas (colunas, tipos) por nome completo `catalog.schema.table`. Aceita lista (`full_names`).
Annotations the server declares
- title: databricks_get_table
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_get_warehouseDetalha um ou mais SQL warehouses por id.Reads private dataNo findings
Why it is in this group
- The name "databricks_get_warehouse" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "sql": it reads databases.
Description, as the server wrote it Detalha um ou mais SQL warehouses por id. Aceita lista (`ids`).
Annotations the server declares
- title: databricks_get_warehouse
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_list_accountsLista os workspaces Databricks conectados a este install — host, label.No findings
Why it is in this group
- The name "databricks_list_accounts" says "list": a word for reading.
Description, as the server wrote it Lista os workspaces Databricks conectados a este install — host, label.
Annotations the server declares
- title: databricks_list_accounts
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_list_catalogsLista os catálogos do Unity Catalog visíveis ao PAT (name, comment, owner).Reads text others writeNo findings
Why it is in this group
- The name "databricks_list_catalogs" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "comment": it reads comments, which other people can write.
Description, as the server wrote it Lista os catálogos do Unity Catalog visíveis ao PAT (name, comment, owner).
Annotations the server declares
- title: databricks_list_catalogs
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_list_schemasLista os schemas (databases) de um catálogo Unity.Reads private dataNo findings
Why it is in this group
- The name "databricks_list_schemas" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "database": it reads databases.
Description, as the server wrote it Lista os schemas (databases) de um catálogo Unity. Informe `catalog_name`.
Annotations the server declares
- title: databricks_list_schemas
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_list_tablesLista as tabelas de um schema Unity (name, table_type, data_source_format).Reads private dataNo findings
Why it is in this group
- The name "databricks_list_tables" says "list": a word for reading.
What it can reach
- private-dataThe name "databricks_list_tables" says "list" and "table": it reads databases.
- private-dataThe description's first sentence says "table": it reads databases.
Description, as the server wrote it Lista as tabelas de um schema Unity (name, table_type, data_source_format). Informe `catalog_name` e `schema_name`.
Annotations the server declares
- title: databricks_list_tables
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
databricks_list_warehousesLista os SQL warehouses do workspace (id, name, state, cluster_size, warehouse_type).Reads private dataNo findings
Why it is in this group
- The name "databricks_list_warehouses" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "sql": it reads databases.
Description, as the server wrote it Lista os SQL warehouses do workspace (id, name, state, cluster_size, warehouse_type). Use o `id` em databricks_run_sql (ou deixe o run_sql escolher um RUNNING automaticamente).
Annotations the server declares
- title: databricks_list_warehouses
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
show_versionShow the current MCP platform and adapter versions.No findings
Why it is in this group
- The name "show_version" says "show": a word for reading.
Description, as the server wrote it Show the current MCP platform and adapter versions.
Annotations the server declares
- title: Show Version
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
toolkit_infoReturns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.
Annotations the server declares
- title: Toolkit Info
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data7
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write2
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:38 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (1 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.mcp.ai/p_databricks: tools/list returned 17 tools to an anonymous client, including databricks_cancel_statement (destructive), databricks_current_user (write), databricks_run_sql (write), report_bug (write), marketplace (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "databricks_cancel_statement" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "databricks_cancel_statement" says "cancel": a word for removing or ending something.
- Infoconnect
The description mentions "credentials".
What this check looks forMatched text
description: "...nticated:true and empty pending[]. When credentials are missing, returns connect_url for th..."
- Infomarketplace
The description mentions "credential".
What this check looks forMatched text
description: "...ating the tool list. If the MCP needs a credential/login, invoke returns a connect link; i..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http databricks https://api.mcp.ai/p_databricksclaude mcp add --transport http databricks https://api.mcp.ai/p_databricksRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__databricks__databricks_list_accounts",
"mcp__databricks__databricks_list_warehouses",
"mcp__databricks__databricks_get_warehouse",
"mcp__databricks__databricks_get_statement",
"mcp__databricks__databricks_list_catalogs",
"mcp__databricks__databricks_list_schemas",
"mcp__databricks__databricks_list_tables",
"mcp__databricks__databricks_get_table",
"mcp__databricks__show_version",
"mcp__databricks__connect",
"mcp__databricks__toolkit_info"
],
"ask": [
"mcp__databricks__databricks_current_user",
"mcp__databricks__databricks_run_sql",
"mcp__databricks__report_bug",
"mcp__databricks__marketplace",
"mcp__databricks__authenticate"
],
"deny": [
"mcp__databricks__databricks_cancel_statement"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as databricks. Review it before you use it.
Capability tags behind 9 rules
- mcp__databricks__databricks_list_warehouses private-data
- mcp__databricks__databricks_get_warehouse private-data
- mcp__databricks__databricks_run_sql private-data
- mcp__databricks__databricks_get_statement private-data
- mcp__databricks__databricks_list_catalogs untrusted-input
- mcp__databricks__databricks_list_schemas private-data
- mcp__databricks__databricks_list_tables private-data
- mcp__databricks__databricks_get_table private-data
- mcp__databricks__marketplace untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.mcp-dir/databricks-mcp/verify?hash=850ad59d3669a2e79d8618b1afa6dce8d67d2fc649eeab2ae8bdf3c271a720a1" | jq -e '.changed == false'Pinned hash 850ad59d3669, from Nov 9, 2026, 19:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.mcp-dir/databricks-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.mcp-dir/databricks-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:39 UTC.
Databricks MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Databricks MCP server safe?
- No scan can promise that. What its definitions show: 17 tools, 6 of which can change, send or delete something, and 3 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Databricks MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: databricks_cancel_statement.
Can the Databricks MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Databricks MCP server have?
- 17 tools: 1 destructive, 5 write, 11 read. databricks_cancel_statement, databricks_current_user, databricks_run_sql, report_bug, marketplace, authenticate, databricks_list_accounts, databricks_list_warehouses and 9 more.
Does the Databricks MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Databricks MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Databricks MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.