MCP servers · connect in Claude Code

Claude Code MCP servers

4,770 MCP servers have a connect command for Claude Code. 2,136 are SAFE, 937 CAUTION and 1,697 BLOCK. Every one was read in full before it was listed.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Claude Code MCP servers”. Retrieved 30 Oct 2026. https://modelsatlas.com/mcp/for/claude-code/page/79

Verdicts · 4,770 servers

✓SAFE2,136!CAUTION937✕BLOCK1,697

Transports

A server can list more than one transport.

Tool risk

1,345

servers expose at least one destructive tool: delete, overwrite or run. The median server with a readable tool list exposes 10 tools.

Servers with no destructive tools →
4,770 servers for Claude Code · 1,873–1,896 · ranked by trust score, then stars
alibaba-cloud-mcp✓SAFE B

nirholas/alibaba-cloud-mcp

MCP server for Alibaba Cloud DashScope by three.ws — Qwen chat, embeddings, and model discovery using your own Alibaba Cloud API key.

★ 7GitHub starsNot listed in sourcestdio
autopilot-mcp✓SAFE B

nirholas/autopilot-mcp

An AI agent's own autonomous-execution control plane over MCP — set autopilot scopes, a daily SOL spend cap, and auto-execute, then run the propose → execute → undo loop. The agent spends SOL and never sells $THREE. Authenticated, write-heavy; scope + spend enforcement is server-side.

★ 7GitHub starsNot listed in sourcestdio
avatar-agent-mcp✓SAFE B

nirholas/avatar-agent-mcp

3D AI Agent Avatar — MCP server that spawns a textured GLB avatar, inspects/validates/optimizes any 3D model, gives the agent a Solana wallet + a voice, and ships full pump.fun powers (atomic Jito-bundled launches + creator-fee collection). Powered by three.ws.

★ 7GitHub stars1 readstdio
billing-mcp✓SAFE B

nirholas/billing-mcp

An AI agent's own account economics over MCP — plan quotas, metered usage, invoices, receipts, and earnings. Read-only, account-scoped. Powered by three.ws.

★ 7GitHub starsNot listed in sourcestdio
brain-mcp✓SAFE B

nirholas/brain-mcp

Any model, one interface: the three.ws multi-provider LLM router over MCP. Discover available providers/models (Claude, GPT-5, Grok, Qwen, DeepSeek, NVIDIA Nemotron, IBM Granite and more) and run a chat completion through whichever one fits. Free tiers need no key; paid flagships unlock with a three

★ 7GitHub starsNot listed in sourcestdio
cellartracker-mcp✓SAFE B

slavins-co/cellartracker-mcp

A local MCP server to connect AI tools to your wine cellar

★ 7GitHub stars1 destructivestdio
clash-mcp✓SAFE B

nirholas/clash-mcp

Play three.ws Coin Clash — the community faction war backed by real holdings + pump.fun data — from any AI agent. Read the live battle board and leaderboard (public), or enlist your wallet and rally power for a faction (Solana-signed writes).

★ 7GitHub starsNot listed in sourcestdio
crypto-portfolio-mcp✓SAFE B

nirholas/crypto-portfolio-mcp

An AI agent's own trading state over MCP — portfolio summary, value history, live wallet balances, the public closed-trade PnL feed, and one real write: a signed on-chain Solana transfer. Powered by three.ws.

★ 7GitHub starsNot listed in sourcestdio
crypto-signals-mcp✓SAFE B

nirholas/crypto-signals-mcp

Discover, subscribe to, and track three.ws copy-trade signal feeds from any AI agent — a marketplace ranked by proven realized edge, a publisher leaderboard from real on-chain performance, and account-scoped subscribe + kill-switch controls over the live API.

★ 7GitHub starsNot listed in sourcestdio
duckduckgo-mcp✓SAFE B

HasData/duckduckgo-mcp

Hosted DuckDuckGo MCP server from HasData. Ranked results, ads separated, 37 regions, structured JSON for Claude, Cursor and any MCP client.

★ 7GitHub starsNot listed in sourcestdio
iarfhlaith-gaff-check✓SAFE B

iarfhlaith/gaff-check

MCP server exposing Ireland's public property datasets (planning, sold prices, flood, radon, zoning, BER context) as tools for AI agents

★ 7GitHub starsNot listed in sourcestdio
ibm-watsonx-mcp✓SAFE B

nirholas/ibm-watsonx-mcp

MCP server for IBM watsonx.ai by three.ws — chat, text generation, embeddings, tokenization, and model discovery with IBM Granite foundation models. Uses your own IBM Cloud credentials.

★ 7GitHub starsNot listed in sourcestdio
ibm-x402-mcp✓SAFE B

nirholas/ibm-x402-mcp

x402 pay-per-use MCP server for IBM Granite AI — chat, code, embeddings, analysis, and time-series forecasting. Pay USDC on Solana per call. No IBM Cloud account required.

★ 7GitHub starsNot listed in sourcestdio
jev-mcp✓SAFE B

rashedInt32/jev-mcp

MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.

★ 7GitHub stars7 readstdio
kol-mcp✓SAFE B

nirholas/kol-mcp

Track one smart trader from any AI agent — a tracked KOL wallet's portfolio P&L (realized/unrealized, win rate, top holding) and its trades on a given mint. Read-only over the live public three.ws KOL API. No key, no signer, no payment.

★ 7GitHub starsNot listed in sourcestdio
mcp-server-pixeltable-developer!CAUTION B

pixeltable/mcp-server-pixeltable-developer

A local Model Context Protocol server for building, inspecting, and operating Pixeltable applications.

★ 7GitHub stars3 writestdio
mneme✓SAFE B

AgentGameLab/mneme

Persistent long-term memory for Claude Code agents — SQLite + FTS5 + sqlite-vec + RRF hybrid recall over MCP, with Chinese tokenization. Local-first, graceful degradation.

★ 7GitHub stars2 readstdio
nft-marketplace-mcp✓SAFE B

nirholas/nft-marketplace-mcp

Browse the three.ws agent marketplace and skills catalog from any AI agent. browse_agents and browse_skills search & page the public listings; agent_detail and the category tools round out discovery. Read-only — no key, no signer, no payment.

★ 7GitHub starsNot listed in sourcestdio
provenance-mcp✓SAFE B

nirholas/provenance-mcp

The three.ws agent action-provenance log over MCP — append-only, ERC-191-signed, on-chain-verifiable. Any AI agent can record what it did and audit another agent's provenance trail. Cursor-paginated reads + a signed append to an immutable ledger.

★ 7GitHub starsNot listed in sourcestdio
push-notifications-mcp✓SAFE B

nirholas/push-notifications-mcp

Read and manage your three.ws notification inbox from any AI agent — list inbound events (pump/market alerts, sales, purchases, social, IRL, account), mark read, tune the per-category delivery matrix, and register Web Push devices. Account-scoped over the live API via a Bearer API key.

★ 7GitHub starsNot listed in sourcestdio
solana-vanity-mcp✓SAFE B

nirholas/solana-vanity-mcp

Read the three.ws vanity-address grind-bounty market and proof-of-grind rarity gallery from any AI agent. Quote a pattern's difficulty + USDC price, appraise any address's rarity, and browse the bounty board, claimable queue, stats, leaderboard, config, and gallery. Read-only — no key, no signer, no

★ 7GitHub starsNot listed in sourcestdio
steam-mcp✓SAFE B

Sarg338/steam-mcp

Read-only Steam MCP server for AI agents: 41 tools + prompts + resources across library, friends, achievements, store, reviews, sales, discovery, recommendations, and co-op planning. Official Steam Web API, bring-your-own-key, open source. On PyPI + the MCP Registry.

★ 7GitHub stars2 writestdio
three-token-mcp✓SAFE B

nirholas/three-token-mcp

The first MCP server whose actions burn a token. Let any AI agent price, hold, and burn $THREE on-chain — every burn splits to the incinerator + treasury via the live three.ws token rail, with Jupiter USD pricing. Deflation as an agent primitive.

★ 7GitHub starsNot listed in sourcestdio
threews-avatar-mcp✓SAFE B

nirholas/threews-avatar-mcp

MCP server for three.ws 3D avatars by three.ws — render a live, rotatable on-chain avatar inline (interactive MCP App), get a paste-anywhere embed iframe, or fetch avatar metadata. Free, no API key.

★ 7GitHub stars2 readstdio

More about Claude Code

Other client hubs

By risk

Questions

How do I add an MCP server to Claude Code?
Run the claude mcp add command shown on the server's page; it names the package and its version.
Which Claude Code MCP servers are safe?
Of the 4,770 servers with a Claude Code connect command, 2,136 are SAFE, 937 CAUTION and 1,697 BLOCK. Cards are ranked by trust score, so the safest are first; open one to read its findings before you connect it.
Are any of these servers remote?
1,942 of the 4,770 list a remote transport (streamable HTTP or SSE). The rest run as a local process your client starts.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.