MCP Server Directory

AI Crawler Access Check io.github.hamzawamiqhq/ai-crawler-check

Can GPTBot, ClaudeBot and PerplexityBot reach a site? Real fetch per crawler, firewall/CDN blocks.

RankRoot: AI visibility audit io.github.zachhhhh/rankroot

Audit a site's visibility to ChatGPT, Perplexity, Claude and AI agents. Generates llms.txt.

Private memory layer for AI assistants. Local-first: remember, recall, forget, expand.

Forward Deployed work.forwardeployed/forward-deployed

Research, strategy, financial models and decks, priced and approved per job, in your AI assistant

Find and remove the writing patterns a profile lists. Deterministic rules, model rewrite opt-in.

zRev AI ai.zrev/zrev

Grade any llms.txt, cold-read a homepage, run a B2B GTM ROI model, get a GTM diligence checklist.

AI Compute Radar dev.aicomputeradar/ai-compute-radar

Which open models fit your GPU or Mac, measured. Model momentum, GPU rental prices, weekly pick.

OpenNodes io.github.opennodes-io/opennodes

Discover verified AI inference nodes, get the best node+model per task, pre-price chains.

OpenAI-compatible multi-model inference via ComputeFlux (Polkadot testnet, TEE-verifiable). stdio.

Pryzm Memory com.pryzm-memory/memory

Encrypted long-term memory shared across your AI assistants (Claude, ChatGPT, Perplexity).

Myncellium Paid MCP com.myncellium.paid/paid-mcp

Pay-per-call MCP tools over x402 (USDC/Solana): LLM, utilities, x402 market and model prices.

vivento-mcp click.vivento365/vivento-mcp

Vivento 365 (CRM inmobiliario) desde Claude, ChatGPT o cualquier cliente MCP: prospectos y citas.

toro4n com.toro4n/toro4n

Ask your AI assistant to sketch or change a Neo4j graph data model, then open it in toro4n.

Relay com.relaygpu/mcp

Run any Relay model (image, video, audio, LLM), poll tasks, upload files and search Relay's docs.

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

Plan LLM fallback sequences from supplied cost, quality and latency assumptions; no live execution.

Superpowers tools.superpowers/superpowers

Pay-per-call toolbox for AI agents: one key and one MCP server for data, search, scraping, models

Delegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.

Hydori io.hydori/hydori

Read, write, translate and sync WordPress and Webflow blog articles from Claude.

Several models from different labs plan in a blind proposal, debate and review loop. Your own keys.

knowsme dev.knowsme/memory

One memory for you and your AI agents, shared by ChatGPT, Claude, Gemini, Grok, Codex and Cursor.

FastAPI-native Model Context Protocol framework and stdio runner.

MCP server for Matrix42: explore the API and data model, search the service desk, act on tickets

LLM Configurator io.github.aikuba/llmconfigurator

Read-only: which local LLMs a GPU or Mac can run - VRAM fit, tokens/sec, model specs.

Measured data: Claude Code and the coding-agent market work.agentexchange/measured-data

Measured weekly data on Claude Code and coding agents: costs, plugins, MCP registry, npm, HN, issues