Rate Limits
To ensure a reliable experience for all users, Vansah MCP enforces rate limits on API requests made through AI assistants. All requests performed by MCP tools count toward your API usage limits.
Rate limits are applied at two levels:
Per User – Limits the number of requests an authenticated user can make within a given time period.
Per Workspace – Limits the total number of requests across all users, AI assistants, and integrations connected to the same Vansah workspace. This limit depends on your Vansah subscription plan.
Because the workspace limit is shared, requests may be rate limited even if an individual user has not reached their personal limit.
Some MCP tools may also have tool-specific rate limits that are lower than the general API limits. These limits may change over time as the platform evolves.
Current Limits
Limit | Value |
General API Requests | 180 requests per minute (example) |
Search Operations | 30 requests per minute (example) |
Note: The values above are examples. Refer to the latest Vansah API documentation for the current limits applicable to your workspace.
Examples
The following examples demonstrate when rate limiting may occur:
35 search requests per minute → Exceeds the search-specific limit.
12 search requests + 170 API requests per minute → Exceeds the general API request limit.
185 API requests per minute → Exceeds the general API request limit.
When a rate limit is exceeded, your MCP client may receive a 429 Too Many Requests response. We recommend implementing exponential backoff or retry logic before sending additional requests.