Adobe Customer Journey Analytics
Run cross-channel reports and build segments in Adobe Customer Journey Analytics.
Explore BigQuery metadata and run SQL from an AI assistant.
Opens Agent Studio, where connecting is one click. The connector URL below works in any MCP client.
Paste it into any MCP client. Setup docs
Google's BigQuery MCP server connects your own BigQuery projects to Claude, ChatGPT and any MCP client over OAuth. Six tools list datasets, read table metadata and run SQL. Five only read. One, execute_sql, runs any statement BigQuery accepts — and that asymmetry is the whole security and cost story of this connector.
Verified connector
Listed by Anthropic as a partner connector in its Connectors Directory.
Connection checked by Agentman on .
Anthropic states this reflects the level of review a connector received, not a security audit.
List BigQuery dataset IDs in a Google Cloud project. Supports pagination. Use `page_size` to limit results and `page_token` to retrieve next page.
Get metadata information about a BigQuery dataset.
List table ids in a BigQuery dataset. Supports pagination. Use `page_size` to limit results and `page_token` to retrieve next page.
Get metadata information about a BigQuery table.
Run a read-only SQL query in the project and return the result. Prefer this tool over `execute_sql` if possible. This tool is restricted to only `SELECT` statements. `INSERT`, `UPDATE`, and `DELETE` statements and stored procedures aren't allowed. If the query doesn't include a `SELECT` statement, an error is returned. For information on creating queries, see the [GoogleSQL documentation](https://cloud.google.com/bigquery/docs/reference/standard-sql/query-syntax). Example Queries: -- Count the number of penguins in each island. SELECT island, COUNT(*) AS population FROM bigquery-public-data.ml_datasets.penguins GROUP BY island -- Evaluate a bigquery ML Model. SELECT * FROM ML.EVALUATE(MODEL `my_dataset.my_model`) -- Evaluate BigQuery ML model on custom data SELECT * FROM ML.EVALUATE(MODEL `my_dataset.my_model`, (SELECT * FROM `my_dataset.my_table`)) -- Predict using BigQuery ML model: SELECT * FROM ML.PREDICT(MODEL `my_dataset.my_model`, (SELECT * FROM `my_dataset.my_table`)) -- Forecast data using AI.FORECAST SELECT * FROM AI.FORECAST(TABLE `project.dataset.my_table`, data_col => 'num_trips', timestamp_col => 'date', id_cols => ['usertype'], horizon => 30) Queries executed using the `execute_sql_readonly` tool will have the job label `goog-mcp-server: true` automatically set. Queries are charged to the project specified in the `projectId` field.
Run a SQL query in the project and return the result. Prefer the `execute_sql_readonly` tool if possible. This tool can execute any query that bigquery supports including: * SQL Queries (SELECT, INSERT, UPDATE, DELETE, CREATE, etc.) * AI/ML functions like AI.FORECAST, ML.EVALUATE, ML.PREDICT * Any other query that bigquery supports. Example Queries: -- Insert data into a table. INSERT INTO `my_project.my_dataset`.my_table (name, age) VALUES ('Alice', 30); -- Create a table. CREATE TABLE `my_project.my_dataset`.my_table ( name STRING, age INT64); -- DELETE data from a table. DELETE FROM `my_project.my_dataset`.my_table WHERE name = 'Alice'; -- Create Dataset CREATE SCHEMA `my_project.my_dataset` OPTIONS (location = 'US'); -- Drop table DROP TABLE `my_project.my_dataset`.my_table; -- Drop dataset DROP SCHEMA `my_project.my_dataset`; -- Create Model CREATE OR REPLACE MODEL `my_project.my_dataset.my_model` OPTIONS ( model_type = 'LINEAR_REG' LS_INIT_LEARN_RATE=0.15, L1_REG=1, MAX_ITERATIONS=5, DATA_SPLIT_METHOD='SEQ', DATA_SPLIT_EVAL_FRACTION=0.3, DATA_SPLIT_COL='timestamp') AS SELECT col1, col2, timestamp, label FROM `my_project.my_dataset.my_table`; Queries executed using the `execute_sql` tool will have the job label `goog-mcp-server: true` automatically set. Queries are charged to the project specified in the `projectId` field.
Read from the server on 2026-08-17, including each tool's own safety annotations.
execute_sql and execute_sql_readonly take identical parameters and return identical output. Only the tool name and the annotations separate them.maximumBytesBilled exists in BigQuery's API and is not among the seven input properties the six MCP tools expose. dryRun is the only in-band control.execute_sql nor execute_sql_readonly supports querying Google Drive external tables.https://www.googleapis.com/auth/bigquery scope, which Google describes as view *and manage*. Least-privilege has to be expressed in IAM, not in the token.run_bq_command tool on the Cloud CLI MCP server — rather than this one.resource.service and tool.name are not available in the Google Cloud console and must be managed with the CLI.tools/list is open to anyone. Google states the method doesn't require authentication, and we confirmed it. Nothing sensitive is exposed — the tool list is identical for every caller — but do not read a successful handshake as a successful connection.initialize, tools/list and one deliberately unauthenticated get_dataset_info call to observe the auth challenge. Every behavioural claim above comes from Google's documentation, the tool schemas or the server's own protected-resource descriptors.Yes, for every tool call. Our anonymous request on 2026-08-17 listed all six tools without a credential, then a call to get_dataset_info returned HTTP 401 and a WWW-Authenticate header. Google's documentation states the tools/list method doesn't require authentication, so discovery is open and execution is not. Tool calls need a Google Cloud OAuth 2.0 token.
execute_sql, and only that one. It is the single tool annotated destructiveHint true and readOnlyHint false, and Google's documentation states it can run any query BigQuery supports, listing DELETE, DROP TABLE and DROP SCHEMA among its own examples. The other five tools, including execute_sql_readonly, are annotated read-only and cannot mutate anything.
The permitted statement set. Google's documentation states execute_sql_readonly allows only read-only operations and rejects DML statements, DDL statements and Python UDFs, returning an error when a query contains no SELECT. execute_sql accepts all of those. Both tools take identical parameters and both descriptions tell the caller to prefer the read-only one.
Whatever the underlying query costs, on your own project. Google's pricing documentation states on-demand queries bill by bytes processed, and that a LIMIT clause on a non-clustered table does not reduce the bytes read. The tool schema exposes no cost cap, so a single agent-written query can scan far more than the returned rows suggest.
Yes, with an IAM deny policy. Google exposes tool.isReadOnly as a deny-policy attribute and publishes a policy that denies mcp.googleapis.com/tools.call whenever that attribute is false. Google's documentation names execute_sql as the only tool such a policy blocks. The deny is server-side, so it holds regardless of which MCP client the agent uses.
No. Google's documentation states the BigQuery MCP server has no quotas of its own and no limit on the number of calls. The underlying REST methods each tool calls still apply their own quotas, and Google maps every tool to its API method. Query results are separately capped at 3,000 rows and three minutes of processing time.
One scope for all six tools. The server's own protected-resource descriptor, read on 2026-08-17, names https://www.googleapis.com/auth/bigquery for every tool including execute_sql. Google describes that scope as view and manage your data in BigQuery. There is no narrower read-only scope, so scope choice cannot separate the destructive tool from the safe five.
documentation value is https://cloud.google.com/bigquery/docs/use-bigquery-mcp, which 301-redirects to the docs.cloud.google.com URL cited here. Source for the API-enablement statement, required roles and permissions, the OAuth scope table, the endpoint and transport, the limitations list (3,000 rows, three-minute cancellation, no Drive external tables, read-only restrictions), the unauthenticated tools/list statement, the "only MCP tool that isn't read-only" statement, the quota position, the four sample prompts and the redirect-URI note. · retrieved 2026-08-17initialize, tools/list and one unauthenticated tools/call against https://bigquery.googleapis.com/mcp (2026-08-17). initialize and tools/list returned HTTP 200 anonymously with 6 tools, descriptions, JSON Schemas and annotations; get_dataset_info returned HTTP 401 with WWW-Authenticate: Bearer and a missing-credential message. Source for the tool count, every annotation state, the parameter union, dryRun, the totalBytesProcessed and totalBytesBilled output fields, and the auth posture. · retrieved 2026-08-17https://bigquery.googleapis.com/.well-known/oauth-protected-resource/<tool> (2026-08-17; HTTP 200 for all six real tool names, HTTP 404 for a control name that does not exist). Source for the single https://www.googleapis.com/auth/bigquery scope, the accounts.google.com authorization server and the header-only bearer method. · retrieved 2026-08-17tool.isReadOnly deny attribute, the read-write deny policy, the dual-permission check, and the console-availability and permission-scope limitations. · retrieved 2026-08-17maximumBytesBilled and the LIMIT-does-not-reduce-bytes rule for non-clustered tables. · retrieved 2026-08-17QueryUsagePerDay and QueryUsagePerUserPerDay, the proactive-enforcement statement and the 200 TiB default. · retrieved 2026-08-17Connect Google Cloud BigQuery once and your agents call these tools on their own: on a schedule, in a workflow, with nobody at the keyboard.