Loading ToolBench

Reading the current corpus…

librechat-analytics-mcp MCP server · F · ToolBench

← Browse

librechat-analytics-mcp

github.com/Avishkar-Kabadi-ODA/librechat-analytics-mcp

MCP server for LibreChat analytics and usage statistics

<=2025-11-25STREAMABLE_HTTP4 tools

48/100

Definition Quality50

Protocol Readiness66

Supportability31

Spec posture

Inferred effective spec <=2025-11-25·current baseline 2026-07-28

Static source inference · medium confidence · detected: Logging

Deprecated protocol patterns detected

Summary

LibreChat Analytics MCP has 4 read-only tools with basic schemas and minimal descriptions. Tool names follow verb_noun convention (get_*), but descriptions are generic and under 50 chars. No output schemas documented. Parameter 'limit' in get_top_users lacks type info in schema (number declared but no description). Error handling returns raw error messages without recovery guidance. No tool annotations (readOnlyHint, etc.). Overall structure is present but falls short of production quality.

Tools (4)

get_model_usageread onlysource verified45/100

Get model usage statistics

get_token_usageread onlysource verified53/100

Get token usage grouped by period

get_top_usersread onlysource verified48/100

Get top users by token consumption

get_usage_summaryread onlysource verified53/100

Get overall LibreChat usage summary

Issues (5)

CRITICALtool-description ↗

All parameter descriptions missing. 'period' enum in get_usage_summary and get_token_usage lacks explanation of what each period represents (daily=last 24h? calendar day?). 'limit' in get_top_users has no description.

get_usage_summaryget_token_usageget_top_users

HIGHtool-description ↗

Tool descriptions are generic and under 50 chars. 'Get overall LibreChat usage summary' and 'Get token usage grouped by period' do not explain WHEN to use each tool, what data they return, or how they differ.

get_usage_summaryget_token_usageget_model_usage

HIGHresponse-shaper ↗

No output schemas documented. LLMs cannot plan downstream calls or extract fields without knowing response structure.

get_usage_summaryget_token_usageget_top_usersget_model_usage

Recommendations

Add 50-150 char descriptions to each tool explaining WHAT it returns and WHEN to use it. Example: 'get_usage_summary: Returns total messages, tokens, and cost for the specified period (daily/monthly/quarterly/yearly). Use to track overall platform consumption trends.'
Add descriptions to all parameters. For 'period', explain: 'Time period for aggregation: daily (last 24h), monthly (calendar month), quarterly (calendar quarter), yearly (calendar year).' For 'limit', add: 'Maximum number of users to return (1-100, default 10).'
Document output schemas in tool descriptions or as a separate schema field. Example: 'Returns {total_messages: number, total_tokens: number, total_cost: number, period: string}'.
Enhance error messages with recovery guidance. Instead of 'Error executing tool get_usage_summary: period must be daily|monthly|quarterly|yearly', return 'Invalid period: got "weekly", must be one of: daily, monthly, quarterly, yearly.'
Add tool annotations to inputSchema. Mark all tools with readOnlyHint: true since they are read-only analytics tools. Example: {name: 'get_usage_summary', inputSchema: {...}, readOnlyHint: true}.

Spec posture evidence

Inferred effective spec: <=2025-11-25.

Relies on Logging (deprecated) - log to stderr or use OpenTelemetry

Score history

Overall score trend

First recorded score · v2 rubric

48/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	F	48	<=2025-11-25	v2