Loading ToolBench

Reading the current corpus…

mcp-handler MCP server · D · ToolBench

← Browse

mcp-handler

github.com/factspark23-hash/mcp-handler

Meta-MCP server that manages multiple backend MCP servers through your host agent

<=2025-11-25STDIO34 tools

58/100

Definition Quality63

Protocol Readiness47

SupportabilityNot measured-

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

34 tools with explicit schemas and descriptions, but significant quality gaps. Most descriptions are terse (10-50 chars), below the 50-200 char LLM-optimized baseline. Parameter descriptions are sparse or missing entirely. No output schemas documented. Error handling is absent, tools return raw text without recovery guidance. Tool names follow verb_noun convention (good), but many lack context about when to use them vs. similar tools. Composition is weak: hub_session_begin/hub_session_step and hub_compose/hub_compose_template duplicate concerns. No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Schemas present but minimal, many parameters lack descriptions, and no constraints (enums, ranges) are enforced.

Tools (34)

hub_alias_listread onlysource verified58/100

List all tool aliases

hub_alias_removewritesource verified63/100

Remove a tool alias

hub_alias_setwritesource verified63/100

Create a tool alias

hub_composewritesource verified63/100

Compose multiple tool calls into a workflow

hub_compose_templatewritesource verified63/100

Save or load a workflow template

hub_config_reloadwritesource verified58/100

Reload configuration from file

hub_config_showread onlysource verified58/100

Show current configuration

hub_cost_estimateread onlysource verified65/100

Estimate cost of a tool call

Issues (5)

HIGHtool-description ↗

Descriptions are uniformly terse (10-50 chars), far below the 50-200 char LLM-optimized baseline. Examples: 'Get hub and all servers status' (31 chars), 'List all available tools' (24 chars). LLMs cannot infer when to use hub_status vs hub_server_info or hub_tools vs hub_search_tools without richer context.

hub_statushub_toolshub_tool_infohub_search_toolshub_refreshhub_statshub_top_toolshub_error_summaryhub_session_statshub_slow_toolshub_server_infohub_enable_serverhub_disable_serverhub_restart_serverhub_server_logshub_quiet_statushub_alias_sethub_alias_removehub_alias_listhub_config_reloadhub_config_showhub_export_stats

HIGHresponse-shaper ↗

No output schemas documented. Tools return TextContent with raw text; LLMs cannot parse structured results or extract IDs for chaining. Example: hub_status returns status but no schema shows what fields are in the response.

Recommendations

Expand all tool descriptions to 50-200 characters. Include WHAT the tool does, WHEN to use it (vs similar tools), and WHAT it returns. Example: 'hub_status' → 'Get the operational status of the hub and all connected servers. Returns uptime, error counts, and last-seen timestamps. Use this to diagnose connectivity issues before calling hub_refresh.'
Document output schemas for all tools. Define the structure of returned data (fields, types, required vs optional). Example: hub_tools should return {tools: [{name, description, server, risk}], total_count, next_cursor}.
Add descriptions to all parameters. For enums, explain what each value means in context. Example: hub_quiet_on 'scope' → 'Target type: "tool" disables a single tool; "server" disables all tools from a server.'
Implement structured error responses with recovery guidance. Return {error: string, code: string, retryable: bool, suggestion: string}. Example: 'Server not found. Available servers: [list]. Did you mean one of these?'
Consolidate session and compose workflows. Choose one pattern (stateful sessions OR templated composition) and document it clearly. If both are needed, explain the use case for each in their descriptions.

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

58/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	D	58	<=2025-11-25	v2