googleapis/mcp-toolbox · error
invalid source for %q tool: source %q is not a compatible ty
Error message
invalid source for %q tool: source %q is not a compatible type
What it means
Tool.ValidateSource checks that the source bound to the conversational analytics tool implements the compatibleSource interface (a BigQuery-family source). If the configured source is of a different kind, the tool cannot obtain the client it needs, so it rejects the binding at initialization/validation time.
Source
Thrown at internal/tools/bigquery/bigqueryconversationalanalytics/bigqueryconversationalanalytics.go:161
// validate interface
var _ tools.Tool = Tool{}
type Tool struct {
tools.BaseTool[Config]
}
func (t Tool) GetSourceName() string {
return t.Cfg.Source
}
func (t Tool) ToConfig() tools.ToolConfig {
return t.Cfg
}
func (t Tool) ValidateSource(source sources.Source) error {
_, ok := source.(compatibleSource)
if !ok {
return fmt.Errorf("invalid source for %q tool: source %q is not a compatible type", t.Cfg.Type, t.Cfg.Source)
}
return nil
}
func (t Tool) Invoke(ctx context.Context, s sources.Source, params parameters.ParamValues, accessToken tools.AccessToken) (any, util.ToolboxError) {
source, ok := s.(compatibleSource)
if !ok {
return nil, util.NewClientServerError("source used is not compatible with the tool", http.StatusInternalServerError, nil)
}
var tokenSource oauth2.TokenSource
var err error
// Get credentials for the API call
if source.UseClientAuthorization() {
// Use client-side access token
if accessToken == "" {
return nil, util.NewClientServerError("tool is configured for client OAuth but no token was provided in the request header", http.StatusUnauthorized, nil)
}
tokenStr, err := accessToken.ParseBearerToken()View on GitHub (pinned to 8cc6e09de2)
Solutions
- Point the tool's source field at a BigQuery-compatible source (e.g. a bigquery source kind)
- Verify source kind and tool kind match in the YAML config
- If wrapping a managed source, use a source type that implements the BigQuery client interface
Example fix
// before
tools:
ask-data:
kind: bigquery-conversational-analytics
source: my-postgres-source
// after
tools:
ask-data:
kind: bigquery-conversational-analytics
source: my-bigquery-source Defensive patterns
Strategy: type-guard
Validate before calling
// check the source kind matches before binding
desiredSource := "my-bigquery-source"
src := sources[desiredSource]
if src == nil || src.SourceType() != "bigquery" {
return fmt.Errorf("source %q is not a BigQuery-compatible source", desiredSource)
} Type guard
func asCompatibleBigQuerySource(s sources.Source) (compatibleSource, bool) {
c, ok := s.(compatibleSource)
return c, ok
} Try / catch
if err := tool.ValidateSource(src); err != nil {
return fmt.Errorf("source binding failed: %w (use a BigQuery source kind)", err)
} Prevention
- Match tool kind to source kind when writing YAML configs
- Verify source names after renaming/refactoring configs
- Use prebuilt configs for the engine you actually target
When it happens
Trigger: A bigquery-conversational-analytics tool's config references a source whose type is not a compatible BigQuery source (e.g. a postgres or cloud-sql source), producing this error when ValidateSource runs.
Common situations: Copy-pasting a tool definition and leaving another source's name in the source field; mixing sources and tools of different engines in one YAML; renaming sources and pointing the tool at the wrong one.
Related errors
- invalid source for %q tool: source %q is not a compatible ty
- invalid source for %q tool: source %q is not a compatible ty
- invalid source for %q tool: source %q is not a compatible ty
- invalid source for %q tool: source %q is not a compatible ty
- invalid source for %q tool: source %q is not a compatible ty
AI-assisted analysis of googleapis/mcp-toolbox@8cc6e09de2 (2026-09-05).
Data as JSON: /api/errors/58198bdf52e2a1f1.
Report an issue: GitHub.