Loading ToolBench

Reading the current corpus…

tracetify-mcp MCP server · F · ToolBench

← Browse

tracetify-mcp

github.com/tracetify/tracetify-mcp

MCP server for Tracetify — trace how any product actually grew, from inside Claude Code or Cursor.

2026-07-28+STDIO1 tools

32/100

Definition Quality10

Protocol Readiness50

Supportability55

Spec posture

Inferred effective spec 2026-07-28+·current baseline 2026-07-28

Static source inference · medium confidence

Current-spec patterns detected

Summary

Single tool 'dynamic_from_manifest' with inferred definitions loaded from tools.generated.json. Tool name lacks action verb (should be verb_noun pattern). Description is generic and does not explain WHAT the tool does, WHEN to use it, or what it returns. No visible input schema in source code, schemas are dynamically loaded from external JSON file not provided for review. Cannot verify parameter descriptions, types, or constraints. This server loads tools dynamically, making static analysis impossible.

Tools (1)

dynamic_from_manifestread onlyauth12/100

Tools are dynamically loaded from tools.generated.json manifest file. Each tool definition includes name, title, description, parameters, REST endpoint mapping, and annotations (readOnly, destructive).

Issues (5)

CRITICALtool ↗

Tool name 'dynamic_from_manifest' lacks action verb. Should follow verb_noun pattern (e.g., 'call_tracetify_api', 'get_tracetify_report'). LLMs infer intent from names, 'dynamic_from_manifest' is opaque.

dynamic_from_manifest

CRITICALtool-description ↗

Tool description 'Tools are dynamically loaded from tools.generated.json manifest file...' is implementation detail, not user-facing guidance. Does not answer: What does this tool do? When should the LLM call it? What does it return? Descriptions must be LLM-optimized (50-200 chars), not technical.

dynamic_from_manifest

CRITICALconstrained-input ↗

Input schemas not visible in source code. tools.generated.json is referenced but not provided for review. Cannot verify parameter types, descriptions, constraints, or enums.

dynamic_from_manifest

CRITICALtool ↗

Tool definitions are dynamically loaded and inferred, not explicitly registered in source. Static analysis cannot verify definition quality.

Recommendations

Rename tool to follow verb_noun pattern. Examples: 'call_tracetify_api', 'get_tracetify_report', 'search_tracetify_data'. This makes intent clear to LLMs.
Replace generic description with user-facing guidance: 'Calls the Tracetify API to retrieve competitive intelligence reports. Requires TRACETIFY_API_KEY. Returns structured report data with metrics, timeline, and analysis.' (50-200 chars).
Provide tools.generated.json in the repository or document its schema inline. Include parameter names, types, descriptions, enums, and constraints for each tool.
Document output schema: what fields does each tool return? Include examples of response structure so LLMs know what to expect.
Add per-parameter descriptions to tools.generated.json. Every parameter needs a description explaining what it controls, valid values, and format constraints.

Score history

Overall score trend

First recorded score · v2 rubric

32/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	32	2026-07-28+	v2