mirror of
https://github.com/apache/superset.git
synced 2026-08-04 13:02:41 +00:00
feat(build): migrate from Prettier to Oxfmt for performant code formatting (#42434)
This commit is contained in:
Đỗ Trọng Hải
@@ -55,11 +55,11 @@ The MCP server runs as a separate process alongside Superset:
|
||||
superset mcp run --host 127.0.0.1 --port 5008
|
||||
```
|
||||
|
||||
| Flag | Default | Description |
|
||||
|------|---------|-------------|
|
||||
| `--host` | `127.0.0.1` | Host to bind to |
|
||||
| `--port` | `5008` | Port to bind to |
|
||||
| `--debug` | off | Enable debug logging |
|
||||
| Flag | Default | Description |
|
||||
| --------- | ----------- | -------------------- |
|
||||
| `--host` | `127.0.0.1` | Host to bind to |
|
||||
| `--port` | `5008` | Port to bind to |
|
||||
| `--debug` | off | Enable debug logging |
|
||||
|
||||
The endpoint is available at `http://<host>:<port>/mcp`.
|
||||
|
||||
@@ -193,22 +193,24 @@ MCP_JWT_AUDIENCE = "your-audience"
|
||||
|
||||
:::warning
|
||||
Store `MCP_JWT_SECRET` securely. Never commit it to version control. Use environment variables:
|
||||
|
||||
```python
|
||||
import os
|
||||
MCP_JWT_SECRET = os.environ.get("MCP_JWT_SECRET")
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
#### JWT claims
|
||||
|
||||
The MCP server validates these standard claims:
|
||||
|
||||
| Claim | Config Key | Description |
|
||||
|-------|-----------|-------------|
|
||||
| `exp` | -- | Expiration time (always validated) |
|
||||
| `iss` | `MCP_JWT_ISSUER` | Token issuer (optional but recommended) |
|
||||
| `aud` | `MCP_JWT_AUDIENCE` | Token audience (optional but recommended) |
|
||||
| `sub` | -- | Subject -- primary claim used to resolve the Superset user |
|
||||
| Claim | Config Key | Description |
|
||||
| ----- | ------------------ | ---------------------------------------------------------- |
|
||||
| `exp` | -- | Expiration time (always validated) |
|
||||
| `iss` | `MCP_JWT_ISSUER` | Token issuer (optional but recommended) |
|
||||
| `aud` | `MCP_JWT_AUDIENCE` | Token audience (optional but recommended) |
|
||||
| `sub` | -- | Subject -- primary claim used to resolve the Superset user |
|
||||
|
||||
#### User resolution
|
||||
|
||||
@@ -435,7 +437,7 @@ services:
|
||||
superset:
|
||||
image: apache/superset:latest
|
||||
ports:
|
||||
- "8088:8088"
|
||||
- '8088:8088'
|
||||
volumes:
|
||||
- ./superset_config.py:/app/superset_config.py
|
||||
environment:
|
||||
@@ -443,9 +445,9 @@ services:
|
||||
|
||||
mcp:
|
||||
image: apache/superset:latest
|
||||
command: ["superset", "mcp", "run", "--host", "0.0.0.0", "--port", "5008"]
|
||||
command: ['superset', 'mcp', 'run', '--host', '0.0.0.0', '--port', '5008']
|
||||
ports:
|
||||
- "5008:5008"
|
||||
- '5008:5008'
|
||||
volumes:
|
||||
- ./superset_config.py:/app/superset_config.py
|
||||
environment:
|
||||
@@ -494,31 +496,31 @@ All MCP settings go in `superset_config.py`. Defaults are defined in `superset/m
|
||||
|
||||
### Core
|
||||
|
||||
| Setting | Default | Description |
|
||||
|---------|---------|-------------|
|
||||
| `MCP_SERVICE_HOST` | `"localhost"` | Host the MCP server binds to |
|
||||
| `MCP_SERVICE_PORT` | `5008` | Port the MCP server binds to |
|
||||
| `MCP_SERVICE_URL` | `None` | Public base URL for MCP-generated links (set this when behind a reverse proxy) |
|
||||
| `MCP_DEBUG` | `False` | Enable debug logging |
|
||||
| `MCP_DEV_USERNAME` | -- | Superset username for development mode (no auth) |
|
||||
| `MCP_RBAC_ENABLED` | `True` | Enforce Superset's role-based access control on MCP tool calls. When `True`, each tool checks that the authenticated user has the required FAB permission before executing. Disable only for testing or trusted-network deployments. |
|
||||
| `MCP_DISABLED_TOOLS` | `set()` | Set of tool names to remove from the MCP server at startup. Disabled tools are never advertised to AI clients during tool discovery. Useful when a custom extension tool should replace a built-in Superset tool. See [Disabling built-in tools](#disabling-built-in-tools). |
|
||||
| Setting | Default | Description |
|
||||
| -------------------- | ------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `MCP_SERVICE_HOST` | `"localhost"` | Host the MCP server binds to |
|
||||
| `MCP_SERVICE_PORT` | `5008` | Port the MCP server binds to |
|
||||
| `MCP_SERVICE_URL` | `None` | Public base URL for MCP-generated links (set this when behind a reverse proxy) |
|
||||
| `MCP_DEBUG` | `False` | Enable debug logging |
|
||||
| `MCP_DEV_USERNAME` | -- | Superset username for development mode (no auth) |
|
||||
| `MCP_RBAC_ENABLED` | `True` | Enforce Superset's role-based access control on MCP tool calls. When `True`, each tool checks that the authenticated user has the required FAB permission before executing. Disable only for testing or trusted-network deployments. |
|
||||
| `MCP_DISABLED_TOOLS` | `set()` | Set of tool names to remove from the MCP server at startup. Disabled tools are never advertised to AI clients during tool discovery. Useful when a custom extension tool should replace a built-in Superset tool. See [Disabling built-in tools](#disabling-built-in-tools). |
|
||||
|
||||
### Authentication
|
||||
|
||||
| Setting | Default | Description |
|
||||
|---------|---------|-------------|
|
||||
| `MCP_AUTH_ENABLED` | `False` | Enable JWT authentication |
|
||||
| `MCP_JWT_ALGORITHM` | `"RS256"` | JWT signing algorithm (`RS256` or `HS256`) |
|
||||
| `MCP_JWKS_URI` | `None` | JWKS endpoint URL (RS256) |
|
||||
| `MCP_JWT_PUBLIC_KEY` | `None` | Static RSA public key string (RS256) |
|
||||
| `MCP_JWT_SECRET` | `None` | Shared secret string (HS256) |
|
||||
| `MCP_JWT_ISSUER` | `None` | Expected `iss` claim |
|
||||
| `MCP_JWT_AUDIENCE` | `None` | Expected `aud` claim |
|
||||
| `MCP_REQUIRED_SCOPES` | `[]` | Required JWT scopes |
|
||||
| `MCP_JWT_DEBUG_ERRORS` | `False` | Log detailed JWT errors server-side (never exposed in HTTP responses per RFC 6750) |
|
||||
| `MCP_AUTH_FACTORY` | `None` | Custom auth provider factory `(flask_app) -> auth_provider`. Takes precedence over built-in JWT |
|
||||
| `MCP_USER_RESOLVER` | `None` | Custom function `(app, access_token) -> username` to extract a Superset username from a validated JWT token. When `None`, the default resolver checks `preferred_username`, `username`, `email`, and `sub` claims in that order. |
|
||||
| Setting | Default | Description |
|
||||
| ---------------------- | --------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `MCP_AUTH_ENABLED` | `False` | Enable JWT authentication |
|
||||
| `MCP_JWT_ALGORITHM` | `"RS256"` | JWT signing algorithm (`RS256` or `HS256`) |
|
||||
| `MCP_JWKS_URI` | `None` | JWKS endpoint URL (RS256) |
|
||||
| `MCP_JWT_PUBLIC_KEY` | `None` | Static RSA public key string (RS256) |
|
||||
| `MCP_JWT_SECRET` | `None` | Shared secret string (HS256) |
|
||||
| `MCP_JWT_ISSUER` | `None` | Expected `iss` claim |
|
||||
| `MCP_JWT_AUDIENCE` | `None` | Expected `aud` claim |
|
||||
| `MCP_REQUIRED_SCOPES` | `[]` | Required JWT scopes |
|
||||
| `MCP_JWT_DEBUG_ERRORS` | `False` | Log detailed JWT errors server-side (never exposed in HTTP responses per RFC 6750) |
|
||||
| `MCP_AUTH_FACTORY` | `None` | Custom auth provider factory `(flask_app) -> auth_provider`. Takes precedence over built-in JWT |
|
||||
| `MCP_USER_RESOLVER` | `None` | Custom function `(app, access_token) -> username` to extract a Superset username from a validated JWT token. When `None`, the default resolver checks `preferred_username`, `username`, `email`, and `sub` claims in that order. |
|
||||
|
||||
### Response Size Guard
|
||||
|
||||
@@ -539,13 +541,13 @@ MCP_RESPONSE_SIZE_CONFIG = {
|
||||
}
|
||||
```
|
||||
|
||||
| Key | Default | Description |
|
||||
|-----|---------|-------------|
|
||||
| `enabled` | `True` | Enable response size checking |
|
||||
| `token_limit` | `25000` | Maximum estimated token count per response |
|
||||
| `warn_threshold_pct` | `80` | Warn when response exceeds this percentage of the limit |
|
||||
| `max_list_items` | `100` | Cap on list-field length (e.g. `charts`, `native_filters`) applied to the `get_*_info` tools before falling back to more aggressive truncation. Raised from a hardcoded 30 in earlier versions; the higher default only keeps more data before the same token-budget fallback kicks in, so it's not a breaking change, but tenants that tuned workflows around the old 30-item cap should lower this value explicitly. |
|
||||
| `excluded_tools` | See above | Tools exempt from size checking (e.g., tools that return URLs, not data) |
|
||||
| Key | Default | Description |
|
||||
| -------------------- | --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `enabled` | `True` | Enable response size checking |
|
||||
| `token_limit` | `25000` | Maximum estimated token count per response |
|
||||
| `warn_threshold_pct` | `80` | Warn when response exceeds this percentage of the limit |
|
||||
| `max_list_items` | `100` | Cap on list-field length (e.g. `charts`, `native_filters`) applied to the `get_*_info` tools before falling back to more aggressive truncation. Raised from a hardcoded 30 in earlier versions; the higher default only keeps more data before the same token-budget fallback kicks in, so it's not a breaking change, but tenants that tuned workflows around the old 30-item cap should lower this value explicitly. |
|
||||
| `excluded_tools` | See above | Tools exempt from size checking (e.g., tools that return URLs, not data) |
|
||||
|
||||
### Caching
|
||||
|
||||
@@ -571,18 +573,18 @@ MCP_CACHE_CONFIG = {
|
||||
}
|
||||
```
|
||||
|
||||
| Key | Default | Description |
|
||||
|-----|---------|-------------|
|
||||
| `enabled` | `False` | Enable response caching |
|
||||
| `CACHE_KEY_PREFIX` | `None` | Optional prefix for cache keys (useful for shared Redis) |
|
||||
| `list_tools_ttl` | `300` | Cache TTL in seconds for `tools/list` |
|
||||
| `list_resources_ttl` | `300` | Cache TTL for `resources/list` |
|
||||
| `list_prompts_ttl` | `300` | Cache TTL for `prompts/list` |
|
||||
| `read_resource_ttl` | `3600` | Cache TTL for `resources/read` |
|
||||
| `get_prompt_ttl` | `3600` | Cache TTL for `prompts/get` |
|
||||
| `call_tool_ttl` | `3600` | Cache TTL for `tools/call` |
|
||||
| `max_item_size` | `1048576` | Maximum cached item size in bytes (1 MB) |
|
||||
| `excluded_tools` | See above | Tools that are never cached (mutating or non-deterministic) |
|
||||
| Key | Default | Description |
|
||||
| -------------------- | --------- | ----------------------------------------------------------- |
|
||||
| `enabled` | `False` | Enable response caching |
|
||||
| `CACHE_KEY_PREFIX` | `None` | Optional prefix for cache keys (useful for shared Redis) |
|
||||
| `list_tools_ttl` | `300` | Cache TTL in seconds for `tools/list` |
|
||||
| `list_resources_ttl` | `300` | Cache TTL for `resources/list` |
|
||||
| `list_prompts_ttl` | `300` | Cache TTL for `prompts/list` |
|
||||
| `read_resource_ttl` | `3600` | Cache TTL for `resources/read` |
|
||||
| `get_prompt_ttl` | `3600` | Cache TTL for `prompts/get` |
|
||||
| `call_tool_ttl` | `3600` | Cache TTL for `tools/call` |
|
||||
| `max_item_size` | `1048576` | Maximum cached item size in bytes (1 MB) |
|
||||
| `excluded_tools` | See above | Tools that are never cached (mutating or non-deterministic) |
|
||||
|
||||
### Redis Store (Multi-Pod)
|
||||
|
||||
@@ -597,12 +599,12 @@ MCP_STORE_CONFIG = {
|
||||
}
|
||||
```
|
||||
|
||||
| Key | Default | Description |
|
||||
|-----|---------|-------------|
|
||||
| `enabled` | `False` | Enable Redis-backed store |
|
||||
| `CACHE_REDIS_URL` | `None` | Redis connection URL (e.g., `redis://redis-host:6379/0`) |
|
||||
| `event_store_max_events` | `100` | Maximum events retained per session |
|
||||
| `event_store_ttl` | `3600` | Event TTL in seconds |
|
||||
| Key | Default | Description |
|
||||
| ------------------------ | ------- | -------------------------------------------------------- |
|
||||
| `enabled` | `False` | Enable Redis-backed store |
|
||||
| `CACHE_REDIS_URL` | `None` | Redis connection URL (e.g., `redis://redis-host:6379/0`) |
|
||||
| `event_store_max_events` | `100` | Maximum events retained per session |
|
||||
| `event_store_ttl` | `3600` | Event TTL in seconds |
|
||||
|
||||
### Tool Search
|
||||
|
||||
@@ -625,15 +627,15 @@ MCP_TOOL_SEARCH_CONFIG = {
|
||||
}
|
||||
```
|
||||
|
||||
| Key | Default | Description |
|
||||
|-----|---------|-------------|
|
||||
| `enabled` | `True` | Enable tool search. When `False`, all tools are listed upfront |
|
||||
| `strategy` | `"bm25"` | Search ranking algorithm. `"bm25"` supports natural language; `"regex"` supports pattern matching |
|
||||
| `max_results` | `5` | Maximum tools returned per search query |
|
||||
| `always_visible` | See above | Tools that always appear in `list_tools`, regardless of search |
|
||||
| `include_schemas` | `False` | When `False` (default, "summary mode"), search results omit `inputSchema` entirely and include a lightweight `parameters_hint` listing top-level parameter names. Set to `True` to include the full `inputSchema` in search results. Full schemas are always used when a tool is actually invoked via `call_tool`. |
|
||||
| `compact_schemas` | `True` | Strip `$defs` / `$ref` and replace with `{"type": "object"}` in search results to reduce token cost. Only takes effect when `include_schemas=True` — ignored in summary mode. |
|
||||
| `max_description_length` | `300` | Truncate tool descriptions in search results (0 = no truncation). Applies in both summary and full-schema modes. |
|
||||
| Key | Default | Description |
|
||||
| ------------------------ | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| `enabled` | `True` | Enable tool search. When `False`, all tools are listed upfront |
|
||||
| `strategy` | `"bm25"` | Search ranking algorithm. `"bm25"` supports natural language; `"regex"` supports pattern matching |
|
||||
| `max_results` | `5` | Maximum tools returned per search query |
|
||||
| `always_visible` | See above | Tools that always appear in `list_tools`, regardless of search |
|
||||
| `include_schemas` | `False` | When `False` (default, "summary mode"), search results omit `inputSchema` entirely and include a lightweight `parameters_hint` listing top-level parameter names. Set to `True` to include the full `inputSchema` in search results. Full schemas are always used when a tool is actually invoked via `call_tool`. |
|
||||
| `compact_schemas` | `True` | Strip `$defs` / `$ref` and replace with `{"type": "object"}` in search results to reduce token cost. Only takes effect when `include_schemas=True` — ignored in summary mode. |
|
||||
| `max_description_length` | `300` | Truncate tool descriptions in search results (0 = no truncation). Applies in both summary and full-schema modes. |
|
||||
|
||||
:::tip
|
||||
Set `enabled: False` to revert to the traditional "show all tools at once" behavior, which some clients or workflows may prefer.
|
||||
@@ -670,16 +672,16 @@ The MCP server respects Superset's full role-based access control (RBAC). Every
|
||||
|
||||
Each tool declares one or more required FAB permissions. The table below maps tool groups to their permission requirements:
|
||||
|
||||
| Tool group | Required FAB permission |
|
||||
|------------|------------------------|
|
||||
| `list_charts`, `get_chart_info`, `get_chart_data`, `get_chart_preview`, `generate_chart`, `update_chart` | `can_read` on `Chart` (read), `can_write` on `Chart` (mutate) |
|
||||
| `list_dashboards`, `get_dashboard_info`, `generate_dashboard`, `add_chart_to_existing_dashboard` | `can_read` on `Dashboard` (read), `can_write` on `Dashboard` (mutate) |
|
||||
| `list_datasets`, `get_dataset_info`, `create_virtual_dataset` | `can_read` on `Dataset` (read), `can_write` on `Dataset` (mutate) |
|
||||
| `list_databases`, `get_database_info` | `can_read` on `Database` |
|
||||
| `execute_sql` | `can_execute_sql_query` on `SQLLab` |
|
||||
| `open_sql_lab_with_context` | `can_read` on `SQLLab` |
|
||||
| `save_sql_query` | `can_write` on `SavedQuery` |
|
||||
| `health_check` | None (public) |
|
||||
| Tool group | Required FAB permission |
|
||||
| -------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------- |
|
||||
| `list_charts`, `get_chart_info`, `get_chart_data`, `get_chart_preview`, `generate_chart`, `update_chart` | `can_read` on `Chart` (read), `can_write` on `Chart` (mutate) |
|
||||
| `list_dashboards`, `get_dashboard_info`, `generate_dashboard`, `add_chart_to_existing_dashboard` | `can_read` on `Dashboard` (read), `can_write` on `Dashboard` (mutate) |
|
||||
| `list_datasets`, `get_dataset_info`, `create_virtual_dataset` | `can_read` on `Dataset` (read), `can_write` on `Dataset` (mutate) |
|
||||
| `list_databases`, `get_database_info` | `can_read` on `Database` |
|
||||
| `execute_sql` | `can_execute_sql_query` on `SQLLab` |
|
||||
| `open_sql_lab_with_context` | `can_read` on `SQLLab` |
|
||||
| `save_sql_query` | `can_write` on `SavedQuery` |
|
||||
| `health_check` | None (public) |
|
||||
|
||||
To disable RBAC checking globally (for trusted-network deployments or testing), set:
|
||||
|
||||
@@ -706,13 +708,13 @@ This makes MCP activity fully auditable alongside regular Superset activity. The
|
||||
|
||||
Every MCP request passes through a middleware stack before reaching the tool function. The default stack (assembled in `build_middleware_list()` in `server.py`) is:
|
||||
|
||||
| Middleware | Purpose | Default |
|
||||
|------------|---------|---------|
|
||||
| `StructuredContentStripperMiddleware` | Strips `structuredContent` from responses for Claude.ai bridge compatibility | Enabled |
|
||||
| `LoggingMiddleware` | Logs each tool call with user, parameters, and duration | Enabled |
|
||||
| `GlobalErrorHandlerMiddleware` | Catches unhandled exceptions and sanitizes sensitive data before it reaches the client | Enabled |
|
||||
| `ResponseSizeGuardMiddleware` | Estimates token count, warns at 80% of limit, blocks at limit | Enabled (configurable via `MCP_RESPONSE_SIZE_CONFIG`) |
|
||||
| `ResponseCachingMiddleware` | Caches read-heavy tool responses (in-memory or Redis) | Disabled (enable via `MCP_CACHE_CONFIG`) |
|
||||
| Middleware | Purpose | Default |
|
||||
| ------------------------------------- | -------------------------------------------------------------------------------------- | ----------------------------------------------------- |
|
||||
| `StructuredContentStripperMiddleware` | Strips `structuredContent` from responses for Claude.ai bridge compatibility | Enabled |
|
||||
| `LoggingMiddleware` | Logs each tool call with user, parameters, and duration | Enabled |
|
||||
| `GlobalErrorHandlerMiddleware` | Catches unhandled exceptions and sanitizes sensitive data before it reaches the client | Enabled |
|
||||
| `ResponseSizeGuardMiddleware` | Estimates token count, warns at 80% of limit, blocks at limit | Enabled (configurable via `MCP_RESPONSE_SIZE_CONFIG`) |
|
||||
| `ResponseCachingMiddleware` | Caches read-heavy tool responses (in-memory or Redis) | Disabled (enable via `MCP_CACHE_CONFIG`) |
|
||||
|
||||
Additional middleware classes (`RateLimitMiddleware`, `FieldPermissionsMiddleware`, `PrivateToolMiddleware`) are implemented in `superset/mcp_service/middleware.py` but are not added to the default pipeline. They are available for operators who want to layer them in via a custom startup path.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user