Getting Started
toolscore init
Guides
{}
@toolscore.cases()
toolscore_snapshot
toolscore record
toolscore approve
toolscore snapshots
ANY
Regex
Approx
Contains
OneOf
IsType
expect()
Expectation
Expectation.__init__()
Expectation.on()
Expectation.calls()
Expectation.then_calls()
Expectation.does_not_call()
Expectation.with_score()
Expectation.with_weights()
Expectation.with_strict_args()
Expectation.run()
Expectation.run_async()
JudgeConfig
evaluate_trace
JudgeConfig.model
JudgeConfig.provider
JudgeConfig.api_key
JudgeConfig.base_url
JudgeConfig.temperature
JudgeConfig.max_retries
JudgeConfig.__init__()
infer_provider()
BaseAdapter
API Reference
evaluate()
assert_tools()
test_agent()
test_agent_async()
evaluate_trace()
load_gold_standard()
load_trace()
auto_extract()
from_otel()
EvaluationResult
ToolCall
Approx.__init__()
Approx.matches()
Contains.__init__()
Contains.matches()
IsType.__init__()
IsType.matches()
Matcher
Matcher.matches()
OneOf.__init__()
OneOf.matches()
Regex.__init__()
Regex.matches()
calculate_invocation_accuracy()
calculate_selection_accuracy()
calculate_edit_distance()
calculate_argument_f1()
calculate_required_call_recall()
calculate_redundant_call_rate()
find_secrets()
redact_secrets()
check_forbidden_calls()
rules_from_json()
load_forbidden_rules()
call_matches_rule()
calculate_side_effect_success_rate()
calculate_latency()
calculate_cost_attribution()
calculate_semantic_correctness()
calculate_batch_semantic_correctness()
snapshot_check()
Snapshot
Snapshot.name
Snapshot.calls
Snapshot.approved
Snapshot.source
Snapshot.created_at
Snapshot.updated_at
Snapshot.schema_version
Snapshot.toolscore_version
Snapshot.__post_init__()
Snapshot.to_dict()
Snapshot.from_dict()
Snapshot.__init__()
SnapshotStore
SnapshotStore.__init__()
SnapshotStore.path_for()
SnapshotStore.exists()
SnapshotStore.load()
SnapshotStore.save()
SnapshotStore.approve()
SnapshotStore.delete()
SnapshotStore.list()
SnapshotStore.pending()
MCPStdioClient
MCPToolDef
MCPToolResult
MCPError
MCPTimeoutError
content_to_text()
MCPRecorder
MCPServerSpec
load_mcp_config()
generate_scenarios()
run_scenarios()
lint_tools()
dangling_reference_issues()
poisoning_issues()
Scenario
ScenarioResult
LintIssue
MCPScorecard
grade_meets()
print_scorecard()
scorecard_to_json()
scorecard_to_markdown()
HTTPValidator
FileSystemValidator
SQLValidator
generate_json_report()
generate_html_report()
generate_markdown_report()
generate_csv_report()
behavior_findings()
letter_grade()
FixSuggestion
FixSuggestion.tool
FixSuggestion.problem
FixSuggestion.fix
FixSuggestion.priority
FixSuggestion.__init__()
EvaluationResult.DEFAULT_WEIGHTS
EvaluationResult.__init__()
EvaluationResult.score
EvaluationResult.grade
EvaluationResult.selection_accuracy
EvaluationResult.argument_f1
EvaluationResult.sequence_accuracy
EvaluationResult.required_call_recall
EvaluationResult.policy_violations
EvaluationResult.RECORD_SCHEMA_VERSION
EvaluationResult.to_dict()
ToolCall.tool
ToolCall.args
ToolCall.result
ToolCall.timestamp
ToolCall.duration
ToolCall.cost
ToolCall.metadata
ToolCall.__post_init__()
ToolCall.is_error
ToolCall.__init__()
BaseAdapter.parse()
OpenAIAdapter
AnthropicAdapter
LangChainAdapter
GeminiAdapter
MCPAdapter
OTelAdapter
tool_calls_from_otel()
CustomAdapter
MCPStdioClient.__init__()
MCPStdioClient.server_messages
MCPStdioClient.protocol_version
MCPStdioClient.server_info
MCPStdioClient.server_instructions
MCPStdioClient.server_capabilities
MCPStdioClient.__enter__()
MCPStdioClient.__exit__()
MCPStdioClient.start()
MCPStdioClient.close()
MCPStdioClient.list_tools()
MCPStdioClient.call_tool()
MCPToolDef.name
MCPToolDef.description
MCPToolDef.input_schema
MCPToolDef.__init__()
MCPToolResult.content
MCPToolResult.is_error
MCPToolResult.raw
MCPToolResult.duration
MCPToolResult.text
MCPToolResult.__init__()
MCPRecorder.__init__()
MCPRecorder.calls_recorded
MCPRecorder.write()
MCPRecorder.run()
MCPServerSpec.name
MCPServerSpec.command
MCPServerSpec.env
MCPServerSpec.__init__()
Scenario.tool
Scenario.arguments
Scenario.kind
Scenario.description
Scenario.__init__()
ScenarioResult.scenario
ScenarioResult.ok
ScenarioResult.is_error
ScenarioResult.duration
ScenarioResult.detail
ScenarioResult.__init__()
LintIssue.tool
LintIssue.severity
LintIssue.message
LintIssue.fix
LintIssue.__init__()
MCPScorecard.server_info
MCPScorecard.tools
MCPScorecard.results
MCPScorecard.lint
MCPScorecard.instructions
MCPScorecard.happy_pass_rate
MCPScorecard.edge_resilience_rate
MCPScorecard.lint_error_count
MCPScorecard.lint_warning_count
MCPScorecard.lint_score
MCPScorecard.score
MCPScorecard.grade
MCPScorecard.total_tool_tokens
MCPScorecard.instructions_tokens
MCPScorecard.context_tokens
MCPScorecard.__init__()
HTTPValidator.__init__()
HTTPValidator.validate()
FileSystemValidator.__init__()
FileSystemValidator.validate()
SQLValidator.__init__()
SQLValidator.validate()
Development
toolscore.integrations
toolscore regression
--csv
--markdown
toolscore generate
toolscore compare
--debug