MCP Server Directory

titan com.thetempleofdoom.titan-mcp/titan

GPU compute API: LLM inference (ornith-1.5) on RTX 4080, pay-per-credit in Bitcoin.

Mode VC Chart: Anthropic vs. OpenAI vs. Google: Who Holds the Top 20? com.modevc/chart-anthropic-vs-openai-vs-google-arena-top-20

Anthropic holds 8 of the Arena top 20, Google 7 and OpenAI 0. In Apr 2025 OpenAI held 9 and.

CodexGuild com.codexguild/codexguild

What changed in your stack since the model's cutoff, error fixes, and security-scanned skills/MCPs

Mode VC Chart: How Many AI Models Are There? Arena Rates 399 com.modevc/chart-how-many-ai-models-are-there

Arena rates 399 text models from 52 labs, up from 10 models in May 2023. Yet only 5 labs hold.

Mode VC Chart: AI Model Releases in 2026: Which Labs Ship Most com.modevc/chart-ai-model-releases-2026

14 labs launched 50 named AI models from 6 Jul 2026 to 27 Sept 2026. Alibaba's Qwen team led.

Model Context Protocol server that exposes the Macula mesh to any agent harness

Local-first persistent session memory for Claude Code and other agents. SQLite + FTS5, no cloud.

ai-model-lifecycle-index io.github.oscarlopez-gif/ai-model-lifecycle-index

Cross-vendor AI model lifecycle: status, sunset dates, and migration targets, source-cited.

OneInfer io.github.oneinfer/mcp-server

Signed-in OneInfer models, chat, media, Studio movies, music, GPUs, and credits.

Search your local Claude Code archive. For continuous capture, use the Rootz Archive plugin.

social-data com.superagnt/social-data

superagnt: marketing plugin for Claude and ChatGPT. Know your market across 7 social networks.

Turn Zero Cloud ai.turnzero/cloud

Free backend for apps built with Claude Code and Codex: hosting, database, storage, sign-in, AI.

recallsapi.com US recalls com.recallsapi/recallsapi

Is it recalled? US recalls from 9 agencies by UPC, model, NDC, VIN or lot. Its API also takes x402.

ovanek-mcp io.github.yofor/ovanek-mcp

Ovanek MCP: Model Context Protocol server for Ovanek platform tools; writes are dry-run by default.

Contexel ai.contexel/contexel

Shared AI memory. ChatGPT, Claude, Cursor and any MCP app read and write the same memory.

Klisten ModelRoute kr.co.klisten.api/modelroute

Read public model catalog metadata with freshness timestamps. No model execution or payments.

Html Vers Markdown io.github.Dawaxwx/html-vers-markdown

HTML to clean Markdown for LLM and RAG pipelines: headings, lists, tables, links, code fences. Pr...

Tuval Studio MCP: Graphic design, AI design & PDF catalog generator for Claude, Cursor & AI agents.

agiscorecard-web3-incentives io.github.f-tiger/agiscorecard-web3-incentives

Model contributor rewards with declared quality weights and caps; separate revenue from subsidies.

time-tracking-billing-hours io.github.theluckystrike/time-tracking-billing-hours

Billable-hours time tracking with rates and CSV export, running inside Claude or Cursor.

Read-only stdio MCP server for a versioned convention card in Claude Code.

Design transformer LLM architectures and report their parameters, FLOPs, memory and cost

TopxAI Models com.topxea.ai/models

Ask Claude, GPT, Grok, GLM, Kimi or DeepSeek from your client; token price plus a $0.001 call fee.

ETFIQ com.etfiq/etfiq

Independent US ETF data and benchmarks for model portfolios, each number with its source and date.