KitScout

Categories › AI & Agents › Agent memory & context

TestedMCP

MCP serverVerified domain · testedmcp.comRemote● LiveFree to try

Read-only lookup of tested agent tools and MCP servers: scores, test evidence, deprecation.

Install

Remote server: your requests and data go to testedmcp.com. Claude Code: claude mcp add --transport http testedmcp https://testedmcp.com/mcp · Claude app: Settings → Connectors → Add custom connector.

What it can do

The tools this server listed when we connected to it, in its own words.

  • search_servers — Search MCP servers tested by TestedMCP by name, package or category. Results sorted by score.
  • get_score — Score (0-100), per-test results and evidence, and test date for one MCP server.
  • is_deprecated — Deprecation status, npm's exact deprecation message (null if none) and verification date.
  • get_replacement — Maintained replacement for a deprecated MCP server, only when there is evidence (e.g. npm's message); otherwise 'none identified'.

KitScout test notes

Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.

Similar tools

  • context-engineering 117,221 ★
    Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switc
  • claude-mem-install 116,897 ★
    Use this when setting up claude-mem on Cursor: local or remote worker, local host-login observer or remote cme
  • claude-mem-install 116,897 ★
    Use this when setting up claude-mem on Grok Bot: local worker plus CMEM Pro observer (default), optional host-
  • handoff 116,897 ★
    Generate a HANDOFF.md that captures goal, current state, files touched, failed attempts, and next steps — so a
  • host-observer 116,897 ★
    Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation