MCP Server Directory

DexL Agents io.github.dexl-io/agents

Pay-per-call AI gateway: models, speech, web search, on-chain reads and NLP tools, via x402.

Delegate from Claude Code to Gemini, Codex, Copilot, Cursor and opencode CLIs as sub-agents.

PageProofer com.pageproofer/pageproofer

Read, fix and reply to PageProofer website feedback notes from Claude Code, Cursor and other agents.

InferIndex io.github.InferIndex/inferindex

LLM API prices across 70+ providers: cheapest offer, comparisons, history and cost estimates.

Pollinations io.github.pollinations/pollinations

Access Pollinations models and API capabilities through agent tools.

Mode VC Chart: Ollama Downloads: Is Local LLM Adoption Keeping Up? com.modevc/chart-ollama-downloads-local-llm-adoption

On npm, Ollama's client fell from 27 to 6.6 downloads per 1,000 cloud lab SDK downloads in 46.

OwnMemory app.ownmemory/ownmemory

Encrypted memory for Claude, on a server you deploy to your own Cloudflare account.

Tideline com.jbpscapital.tideline/tideline

Published end-of-day state of a rules-based SPY/QQQ index model. Read-only. Free tier: 90-day delay.

Turn the OpenAIRE Graph into a ranked replication queue with a Science Live verification overlay.

Hands bulk reading to cheap OpenRouter models, masks secrets, checks each answer against the source

Civitai model and image metadata. No key required.

Epoch Ai Models io.github.pipeworx-io/epoch-ai-models

Epoch AI — AI models database

Search self-contained .pikelet knowledge artifacts over MCP — no vector DB, no embedding API.

sdp-remote-mcp com.opentext/sdp-remote-mcp

Model Context Protocol server for OpenText Software Delivery Platform.

day3 io.github.Mopra/day3

Draft email campaigns in day3 from Claude Code, Cursor or VS Code as editable composer blocks.

Generate and edit images with GPT Image 2.5 for $0.029 — free key, 50 credits, no card.

gateway io.tokenease/gateway

One MCP endpoint for 17 top Chinese LLMs. OpenAI-compatible. Up to 60% cheaper than OpenRouter.

Cursor's agent (cursor-agent CLI) through MCP: any model your plan offers, resumable sessions.

UN Charter 1945 io.arxo/charter

UN Charter (1945, as amended) as an executable model with worked cases; not UN-affiliated

Papertrade AI io.github.nirholas/papertrade-ai

Trade Papertrade BTC and ETH perps from Claude, ChatGPT, Codex, Cursor and any MCP client.

ZRouter io.github.nexusrun/zrouter

Manage your ZRouter AI gateway account: usage, logs, model routers, API keys, budgets, and limits.

tokcalc MCP Server io.github.stevecrates489-commits/tokcalc

LLM serving capacity planner: VRAM, KV cache, GPU topology, latency, and cost.

StudioTV LLM VRAM Calculator com.studiotvai/llm-vram

Does an LLM fit on your GPU? VRAM, KV cache and GPU count for any Hugging Face model.

AI Search Visibility Tracker io.github.mufmo130/ai-search-visibility

How often ChatGPT, Perplexity, Gemini and Claude mention and cite your brand vs competitors.