Loading ToolBench

Reading the current corpus…

mcp-server-mcpindex MCP server · C · ToolBench

mcp-server-mcpindex

github.com/mcpindex-ai/mcp-server-mcpindex

The MCP server index that vets servers, not just lists them. Search by task, then get an advisory screen on a server before your agent calls its tools: whether each tool does what it claims, backed by conformance monitoring and a public drift ledger. Advisory (REVIEW / UNVERIFIED), monitored not enforced, not a safety verdict. Drop-in for Claude Desktop, Claude Code, Cursor, Gemini CLI, Cline.

2026-07-28+STDIO6 tools

62/100

Definition Quality75

Protocol Readiness50

Supportability47

Spec posture

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

Static source inference · medium confidence

Current-spec patterns detected

Summary

Server exposes 6 tools with complete JSON schemas and descriptions. All tools are READ_ONLY and stateless. Naming follows verb_noun convention (recommend_, search_, get_, compare_, check_, assess_). Descriptions are present but vary in quality: some are terse (e.g., 'Search query.' for search_mcp_servers) while others provide context. Parameters have types and descriptions. However, several descriptions fall below the 50-200 char LLM-optimized baseline, and output schemas are not documented in the source. Error handling is basic (API errors thrown as generic messages). No tool annotations (readOnlyHint, etc.) despite all being read-only.

Tools (6)

assess_serverread onlysource verified70/100

Server slug to assess.

check_tool_trustread onlysource verified80/100

Registry slug from search_mcp_servers / recommend results, e.g. "io-github-microsoft-playwright-mcp" (NOT a short name like "github").

compare_serversread onlysource verified70/100

Server slugs to compare.

get_install_commandread onlysource verified78/100

Slug of the server (from search_mcp_servers or recommend_mcp_for_task results).

recommend_mcp_for_taskread onlysource verified80/100

Natural-language description of the task, e.g. "read PDFs and write to S3" or "search GitHub and open a PR".

search_mcp_serversread onlysource verified73/100

Search query.

Issues (5)

HIGHtool ↗

Output schemas not documented. Tools return API responses but LLMs cannot see what fields to expect, forcing them to infer structure and plan downstream calls blindly.

recommend_mcp_for_tasksearch_mcp_serversget_install_commandcompare_serverscheck_tool_trustassess_server

MEDIUMtool-description ↗

Terse parameter descriptions. 'Search query.' and 'Server slugs to compare.' lack context on expected format, constraints, or when to use. Descriptions should be 50-200 chars and explain WHAT, WHEN, and HOW.

search_mcp_serverscompare_serversassess_server

MEDIUMtool-annotations ↗

No tool annotations. All 6 tools are read-only (no side effects), but lack readOnlyHint annotation. This forces LLMs to reason about safety instead of relying on machine-readable hints.

recommend_mcp_for_tasksearch_mcp_serversget_install_commandcompare_serverscheck_tool_trust

Recommendations

Document output schemas for all 6 tools. Include field names, types, and descriptions so LLMs know what to expect. Example: 'Returns {servers: [{id, name, description, category, trust_status}], total_count, next_cursor}'.
Expand terse descriptions to 50-200 characters. Replace 'Search query.' with 'Natural-language search term (e.g., "PDF reader", "GitHub integration"). Searches server names, descriptions, and tags.'
Add readOnlyHint annotation to all tools via fromJsonSchema or direct schema extension. This signals to LLMs that these tools are safe to call without confirmation.
Implement structured error responses with error codes and recovery hints. Example: '{error: "NOT_FOUND", message: "Server not found", suggestion: "Try search_mcp_servers() with a partial name."}'
Document the limit constraint in search_mcp_servers description: 'Max results returned (default 10, max 50). Use pagination to retrieve more.'

Score history

Overall score trend

First recorded score · v2 rubric

62/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	C	62	2026-07-28+	v2