What causes "invalid source for %q tool: source %q is not a compatible type" in googleapis/mcp-toolbox?

Set `source:` to a declared `kind: serverless-spark` source.

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

The serverlessspark-list-batches tool throws this in ValidateSource when its configured source does not implement the tool's `compatibleSource` interface, meaning it is not a Serverless Spark source that can supply a batch admin client. This is a startup-time configuration validation, not a runtime database failure — the tool never executes because its source type is wrong.

Source

Thrown at internal/tools/serverlessspark/serverlesssparklistbatches/serverlesssparklistbatches.go:142

	resp, err := source.ListBatches(ctx, pageSize, pt, filter)
	if err != nil {
		return nil, util.ProcessGcpError(err)
	}
	return resp, nil
}

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
}

View on GitHub (pinned to 8cc6e09de2)

Solutions

Set `source:` to a declared `kind: serverless-spark` source.
Fix the sources block so the referenced source is actually serverless-spark (check `kind` field).
Run `./toolbox --tools-file` validation/dev UI startup locally to catch all incompatible pairings at once.

Example fix

# before
tools:
  list-batches:
    kind: serverless-spark-list-batches
    source: cloudsql-pg
# after
tools:
  list-batches:
    kind: serverless-spark-list-batches
    source: serverless-spark-prod

Defensive patterns

Strategy: validation

Validate before calling

# ensure the referenced source kind matches
sources:
  spark-prod:
    kind: serverless-spark
tools:
  list-batches:
    kind: serverless-spark-list-batches
    source: spark-prod

Type guard

func isServerlessSparkSource(s sources.Source) bool {
    _, ok := s.(serverlessspark.Source)
    return ok
}

Prevention

In multi-environment overlays, re-verify each tool's source after substitution.
Add a lint step that cross-checks tool kinds against source kinds in tools.yaml.
Document the required source kind next to each tool definition.

When it happens

Trigger: A `serverless-spark-list-batches` tool bound via `source:` to a source of any kind other than `serverless-spark`, so the assertion `source.(compatibleSource)` in serverlesssparklistbatches.go fails.

Common situations: Bulk-edited tools.yaml where many tools share one wrong source name; environment-specific overlays (staging/prod) replacing the Spark source with another type; forgetting that each tool kind only accepts its matching source kind.

Related errors

AI-assisted analysis of googleapis/mcp-toolbox@8cc6e09de2 (2026-09-05). Data as JSON: /api/errors/5f3cdebfff805ec8. Report an issue: GitHub.