MCP Marketplace
Sign inSign up
Back to Browse

Sato Hub Integrations MCP Server

by Satohubai
Developer ToolsLow Risk9.7MCP RegistryLocal
Free

Server data from the Official MCP Registry

Prepare -> execute for onchain agent actions: policy pre-flight, simulation, receipt log.

About

Prepare -> execute for onchain agent actions: policy pre-flight, simulation, receipt log.

Security Report

9.7
Low Risk9.7Low Risk

Valid MCP server (3 strong, 4 medium validity signals). No known CVEs in dependencies. ⚠️ Package registry links to a different repository than scanned source. Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.

17 files analyzed · 1 issue found

Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.

Permissions Required

This plugin requests these system permissions. Most are normal for its category.

file_system

Check that this permission is expected for this type of plugin.

HTTP Network Access

Connects to external APIs or services over the internet.

Shell Command Execution

Runs commands on your machine. Be cautious — only use if you trust this plugin.

How to Install

Add this to your MCP configuration file:

{
  "mcpServers": {
    "ai-satohub-kit": {
      "args": [
        "-y",
        "@satohub/kit"
      ],
      "command": "npx"
    }
  }
}

Documentation

View on GitHub

From the project's GitHub README.

Sato Hub integrations

⬡ Sato Hub inside the agent frameworks people already run.

Sato Hub indexes what onchain agents are built from — agent frameworks, MCP servers, wallets and key management, x402 and stablecoin payment rails, ERC-8004 identity, trading venues, onchain data, agent skills — rebuilds the index daily from public evidence, and scores every listing on how open, active and verifiable it is.

This repository packages four of those calls for the agent frameworks below, so an agent can reach them without anyone writing a fetch wrapper first.

PackageFrameworkInstall
elizaos-plugin-satohubelizaOSnpm i elizaos-plugin-satohub
satohub-ai-sdk-toolsVercel AI SDKnpm i satohub-ai-sdk-tools
satohub-langchain-toolsLangChain.jsnpm i satohub-langchain-tools
goat-plugin-satohubGOAT SDKnpm i goat-plugin-satohub — Preflight + search only
agentkit-satohubCoinbase AgentKitnpm i agentkit-satohub — Preflight + search only
satohub-coreanything with fetchnpm i satohub-core
examples/claude-agent-sdkClaude Agent SDKconfig only — no package
examples/openai-agents-sdkOpenAI Agents SDKconfig only — no package
examples/base-ts-agent-starterTypeScript on Base, viemrunnable starter: Preflight before install, a policy check, a quote. Holds no key

Two of those rows are deliberately not packages. Both SDKs speak MCP, and Sato Hub serves MCP; a package between them would be a wrapper around a URL.

The four calls

CallWhat it answers
search_resourcesWhat is there to build this from, and is this project real, maintained and open source?
preflightShould I install / connect / pay / trade this — what is on record about it?
route_swapWhich venue would you route this swap to, on what readings, and what is the fee?
build_planHere is my goal in plain words — what is the stack, and what is the first action?

All four are read-only. All 32 MCP tools are at https://satohub.ai/mcp if you want the rest.

What these packages do, and do not

They wrap. They never re-implement. No scoring, ranking or verdict logic lives in this repo. Sato Hub decides; these packages carry the answer and check the signature on it.

The payload comes back verbatim. Every tool returns the record as Sato Hub sent it, with provenance beside it and never folded into it — so nothing the model reads has passed through a summariser of ours.

Responses are verified. Preflight verdicts and Sato Route decisions leave satohub.ai with a detached Ed25519 signature. satohub-core fetches the JWKS, verifies the raw bytes, and by default throws when a signature is present and does not match. An unsigned response is reported as unsigned — unknown, not invalid. We never emit a placeholder signature and this code never invents one. (the scheme)

Non-custodial, everywhere. Nothing here signs a transaction, holds a key, deploys or moves funds. A swap tool returns a quote and calldata for the caller to read and sign with its own signer. An unsigned route costs nothing. The Sato fee — 3 bps stable-to-stable, 15 bps on any volatile leg — is stated in the response before anything is signed, including when it is zero.

The readings, and their limits

These are in every tool description, because a tool description is the part a model actually reads:

  • A Sato Score measures how open, active and verifiable a project is. It is not a security review, a quality judgment or a statement about returns.
  • A Preflight verdict names what was checked and when. unknown means Sato Hub holds no record — not that something is wrong.
  • A route is a recommendation, chosen by the fields named in chosen_by. A quote is not a fill.
  • null means unknown. It never means zero.

Citation

The data is free under CC-BY-4.0. Every record carries a sato_url — its canonical page. When you surface a listing in an answer, cite that URL, so the reader can check what the record says today rather than what it said when the model read it.

Development

Zero runtime dependencies beyond satohub-core; the frameworks are peer dependencies, so nothing here drags a runtime into your tree.

npm install
npm test        # builds, then runs every package's tests against a mocked fetch
npm run typecheck

No test in this repo asserts a fact about a real listing. A test that pinned today's Sato Score would fail tomorrow for the right reason, and teach everyone to ignore it.

MIT.

Install it in one line

claude mcp add --transport http satohub https://satohub.ai/api/mcp   # Claude Code
codex mcp add satohub --url https://satohub.ai/api/mcp               # Codex CLI
gemini mcp add --transport http satohub https://satohub.ai/api/mcp   # Gemini CLI

One click for VS Code or VS Code Insiders.

Cursor, Windsurf, Zed, Cline, Continue, JetBrains, LM Studio, Goose, Warp, Claude Desktop — deep links and the exact config block for each, generated from one endpoint constant: https://satohub.ai/install (machine-readable at /api/install.json). GitHub strips cursor:// and lmstudio:// links from READMEs, which is why the one-click buttons live on that page rather than here.

Then drop in the agent kit — AGENTS.md, CLAUDE.md, .cursor/rules/satohub.mdc, .windsurfrules — so the model reaches for the server instead of answering from memory. Copies in kit/.

Reviews

No reviews yet

Be the first to review this server!

More Developer Tools MCP Servers

Fetch

Free

by Modelcontextprotocol · Developer Tools

Web content fetching and conversion for efficient LLM usage

90.7K
Stars
18
Installs
5.3
Security
5.0
Local

Git

Free

by Modelcontextprotocol · Developer Tools

Read, search, and manipulate Git repositories programmatically

90.7K
Stars
20
Installs
6.5
Security
No ratings yet
Local

Paperclip

Free

by Paperclipai · Developer Tools

Trending hip-hop artist momentum scores across four cultural dimensions.

81.1K
Stars
1
Installs
10.0
Security
No ratings yet
Remote

Toleno

Free

by Toleno · Developer Tools

Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.

224
Stars
799
Installs
8.0
Security
4.8
Local

mcp-creator-python

Free

by mcp-marketplace · Developer Tools

Create, build, and publish Python MCP servers to PyPI — conversationally.

-
Stars
138
Installs
10.0
Security
4.7
Local

MCP Marketplace

Free

by mcp-marketplace · Developer Tools

Search and install MCP servers from inside your AI client.

-
Stars
127
Installs
10.0
Security
5.0
Remote