Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
slop-eval
MCP serversWraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.
slop-eval-cli@0.1.4 -
Sealed
MCP serversPer-call paid skills for AI agents, run server-side: inputs in, outputs back. The body never ships.
sealed-mcp@0.1.0 -
agiscorecard-web3-compute
MCP serversCompare GPU workload costs per accepted output, including setup, storage, egress and failed work.
-
FixMyJSON
MCP serversRepair broken LLM JSON and check it against a JSON Schema. Flags cut-off output. Free trial.
-
LLM Cutover
MCP serversChecks if a cheaper model agrees with your GPT, Claude or Gemini outputs, and what routing saves.
-
lms-front
MCP serversOpen-source multi-tenant LMS for creators and schools: sell courses on your own subdomain. Next.js 16 + React 19 + Supabase (RLS) + Stripe Connect, an AI tutor over MCP, gamification, certificates, i18n (en/es). Self-hostable.
git clone https://github.com/guillermoscript/lms-front.git -
CompletionKit
MCP serversPrompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
-
WIA Braille + WIA Talk
MCP serversText to WIA Braille (pronunciation-based, not a national code), BRF output and checks, Nemeth math.
-
ai-model-pricing
MCP serversLive pricing data for AI models across vendors: input/output prices per 1k tokens as JSON.
-
Eval Engine API
MCP serversPay-per-call AI evaluation MCP server. Score LLM outputs against benchmark rubrics via Workers AI.
-
prompt-guard-mcp
MCP serversScans untrusted web pages, emails, or tool outputs for prompt injections and returns sanitized tex
-
pdf-merger
MCP serversMerge PDFs from your AI chat: combine, order pages, output one clean PDF. All data is local.
https://github.com/theluckystrike/mcp-servers/releases/download/v0.22.0/pdf.mcpb@0.22.0 -
WeasyPrint by pagespool
MCP serversHosted WeasyPrint: render HTML and print CSS to PDF, with PDF/A output on the paid plans.
-
xc-mcp
MCP serversXCode CLI & Simulator MCP. Progressive disclosure of tool responses reduces context and token waste. Lets AI agents build, run and drive iOS apps — without drowning in Xcode's output.
git clone https://github.com/conorluddy/xc-mcp.git -
Andi Search
MCP serversReal-time web search and page fetch for AI agents from Andi's own index. LLM-ready markdown output.
-
Repairs truncated or malformed LLM JSON outputs (trailing commas, markdown fences, single quotes).
-
Buyer-side trust oracle + capped sessions for x402 agents: verified_route, receipts, 17 free tools.
@romudille/agentpay-mcp@2.9.0 -
erb-escape-audit
MCP servers15 rules that find every line in a Rails .erb view where output escaping was switched off or was the
@readystack/erb-escape-audit@1.0.4 -
Fixzi — MCP & API Schema Drift Monitor
MCP serversMonitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.
-
Darwin-owned AntV Charts
MCP serversDarwin-hosted AntV bar, column and line charts, plus bounded CSV bar charts. Free PNG output.
-
token-optimizer-mcp
MCP servers91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
git clone https://github.com/ooples/token-optimizer-mcp.git -
tersio
MCP servers✂️ Token saver & usage tracker for coding agents: terse caveman replies, compact RTK shell output, lean Ponytail code, Headroom compression, pstack rigor, and a gain dashboard — one-command combos over one shared extension tree.
git clone https://github.com/KurutoDenzeru/tersio.git -
SideEye Human Signal Court
MCP serversScore two AI outputs, get exact failure reasons, and issue a $0.01 USDC receipt via x402.
-
Scout Intel MCP — The Google for AI Agents
MCP serversThe Google for AI agents — company intel, competitor tracking, market research via MCP. JSON output
scout-intel-mcp@1.0.3
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.