Loading ToolBench

Reading the current corpus…

creator-agent-plugin MCP server · F · ToolBench

← Browse

creator-agent-plugin

github.com/LottieFiles/creator-agent-plugin

MCP server providing access to LottieFiles animation creation and export tools via GraphQL API

2025-06-18+STREAMABLE_HTTP9 tools

34/100

Definition Quality21

Protocol Readiness65

SupportabilityNot measured-

Spec posture

Inferred effective spec 2025-06-18+·current baseline 2026-07-28

Static source inference · medium confidence · detected: Dynamic Client Registration

Deprecated protocol patterns detected

Summary

Critical failure: Tool definitions are inferred from check-contract.py validation script, not from actual MCP server implementation code. No source code showing tool registration, schemas, or descriptions is provided. The script validates a contract JSON (public-mcp-v1.json) but that file is not included in the submission. Tool names, descriptions, and risk levels are extracted from comments in a validation script, not from live tool definitions. Average across 9 tools: ~28.

Tools (9)

engine_cancel_jobwriteauthsource verified23/100

Cancel an active export job

engine_docsread onlyauthsource verified23/100

Get documentation for the LottieFiles Engine API

engine_documentwriteauthsource verified20/100

Access or manipulate animation documents

engine_execwriteauthsource verified17/100

Execute operations on the LottieFiles Engine

engine_exportwriteauthsource verified23/100

Export an animation to various formats

engine_job_resultread onlyauthsource verified23/100

Retrieve the result of a completed export job

engine_job_statusread onlyauthsource verified23/100

Check the status of an export job

Issues (5)

CRITICALtool ↗

No tool definitions visible in source code. Tool existence is inferred from validation script comments only. The actual contract JSON (public-mcp-v1.json) containing schemas and full descriptions is not provided.

engine_cancel_jobengine_docsengine_documentengine_execengine_exportengine_job_resultengine_job_statuslf_graphqlrequest_upload

CRITICALconstrained-input ↗

No input schemas visible for any tool.

engine_cancel_jobengine_docsengine_documentengine_execengine_exportengine_job_resultengine_job_statuslf_graphqlrequest_upload

CRITICALtool-description ↗

No parameter descriptions visible. Tool descriptions in check-contract.py are minimal (10-20 chars) and do not explain parameters, constraints, or expected formats.

engine_cancel_job

Recommendations

Provide the complete contracts/public-mcp-v1.json file showing full tool definitions, input schemas (JSON Schema draft 2020-12), output schemas, and parameter descriptions.
Ensure every tool description is 50-200 characters and answers: What does it do? When to use it? What does it return?
Add parameter descriptions to all tools explaining format, constraints, and valid values. Use enums for constrained inputs (e.g. export format: 'json|lottie|gif|mp4').
Rename lf_graphql to execute_graphql_query and engine_exec to specific operation names (engine_render, engine_compile, etc.) to follow verb_noun convention.
Document output schemas for all tools showing return field types, pagination support (if applicable), and IDs needed for downstream tool chaining.

Score history

Overall score trend

First recorded score · v2 rubric

34/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	34	2025-06-18+	v2