Agent access · Reliability and controls
Which BI tools can cap what agents consume?
2 of 15 tools do, according to their public docs, and 11 partly.
Yes: Databricks, Snowflake. Partly: Omni, Hex, Sigma, BigQuery, Looker, Tableau, Power BI, Alteryx, MotherDuck, Mode, Redshift.
The question we asked: Can you cap or rate-limit what outside agents can consume?
Grading standard
A limit on agent-driven usage (rate limit, quota, spend or compute cap) documented for the agent interface and separate from ordinary user limits. A general API rate limit that applies to agents is partly.
Databricks
Yes
Quoted from Databricks’s docsMCP rate limits apply to tools/call requests and use queries per minute (QPM).
Source: docs.databricks.com/aws/en/ai-gateway/govern-mcp-service · checked Oct 26, 2026 · quoted by Claude
Snowflake
Yespreview
Quoted from Snowflake’s docsThis topic covers how to see what the gateway is spending and how to limit it.
Source: docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-ai-gateway/cost-management · checked Oct 26, 2026 · quoted by Claude
Omni
Partly
Quoted from Omni’s docsToo Many Requests - Rate limit exceeded (60 requests/minute)
Source: docs.omni.co/api/ai/stream-ai-job-results · checked Oct 26, 2026 · quoted by Gemini
Hex
Partly
Quoted from Hex’s docs- hex-api-30rpm: Rate limit group for the Hex API at 30 requests per minute
Source: learn.hex.tech/docs/api-integrations/api/reference · checked Oct 26, 2026 · quoted by GPT
Sigma
Partly
Quoted from Sigma’s docsScreenshots count toward the rate limit on the Sigma API export endpoints, which is 400 requests per minute.
Source: help.sigmacomputing.com/docs/use-sigma-mcp-server · checked Oct 26, 2026 · quoted by Claude
BigQuery
Partly
Quoted from BigQuery’s docsYou are still subject to the quotas enforced by the APIs called by the MCP server tools.
Source: docs.cloud.google.com/bigquery/docs/use-bigquery-mcp · checked Oct 26, 2026 · quoted by Claude
Looker
Partlypreview
Quoted from Looker’s docsHowever, tool calls made by AI agents consume the instance's standard administrative and query-based API quotas.
Source: cloud.google.com/looker/docs/mcp · checked Oct 26, 2026 · quoted by Claude
Tableau
Partly
Quoted from Tableau’s docsGets the list of Tableau MCP settings for a specified site.
Source: help.tableau.com/current/api/rest_api/en-us/REST/rest_api_ref_tableau_mcp.htm · checked Oct 26, 2026 · quoted by Claude
Power BI
Partly
Quoted from Power BI’s docs- There's a limit of 120 query requests per minute per user, regardless of the dataset that's queried.
Source: learn.microsoft.com/en-us/rest/api/power-bi/datasets/execute-queries · checked Oct 26, 2026 · quoted by GPT
Metabase
Alteryx
Partly
Quoted from Alteryx’s docsAPI rate limiting sets the maximum number of requests that are accepted by an endpoint within a specified period of time.
Source: help.alteryx.com/dataprep/en/release-notes/changes-to-system-behavior/changes-to-the-ap... · checked Oct 26, 2026 · quoted by GPT
MotherDuck
Partly
Quoted from MotherDuck’s docsQuery timeout: 55 seconds. Queries exceeding this limit will be cancelled server-side and the tool will respond with an error message.
Source: motherduck.com/docs/sql-reference/mcp/core/query-rw · checked Oct 26, 2026 · quoted by Claude
Mode
Partly
Quoted from Mode’s docsAs of today, our API rate limiting is approximately 40 requests every 10 seconds, or 4 requests per second per username.
Source: mode.com/help/articles/api-reference · checked Oct 26, 2026 · quoted by Claude
Redshift
Partly
Quoted from Redshift’s docsIf the rate of request exceeds the quota, a ThrottlingException with HTTP Status Code: 400 is returned.
Source: docs.aws.amazon.com/redshift/latest/mgmt/data-api.html · checked Oct 26, 2026 · quoted by Gemini
Streamlit