For agents & builders · Live

Speaks agent

Sato Hub exposes the library behind the builder — directory, wiki, news, live metrics — over the Model Context Protocol. Any MCP client can query it directly.

16 read-only toolsNo key requiredStreamable HTTP

EndpointStreamable HTTP · read-only · no auth

https://satohub.ai/api/mcp

One clickAdd to Cursor Add to VS Code VS Code Insiders

Claude Desktop has no install link — paste the endpoint above into Settings → Connectors. Everything else is below.

Connect

▲

One line, Claude Code

Nothing to configure by hand — the CLI writes the entry for you:

claude mcp add --transport http onchain-agent https://satohub.ai/api/mcp

◆

Any client, native HTTP

Most current clients speak Streamable HTTP directly. Drop this into your MCP config — no bridge process, no install:

{
  "mcpServers": {
    "onchain-agent": {
      "type": "http",
      "url": "https://satohub.ai/api/mcp"
    }
  }
}

●

Remote connectors

In a client with a connector UI, add a custom connector and paste the endpoint URL. That's the whole setup.

▸

Older clients (fallback)

Only if your client has no native HTTP transport — bridge to the endpoint with mcp-remote:

{
  "mcpServers": {
    "onchain-agent": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://satohub.ai/api/mcp"]
    }
  }
}

⌕

Inspect it live

Point the MCP Inspector at the endpoint and browse the tools:

npx @modelcontextprotocol/inspector
# transport: Streamable HTTP → https://satohub.ai/api/mcp

Tools

Every list tool paginates and accepts response_format of markdown (default) or json.

⬡

Library

search_resources

Search and filter the directory by free text, chain, category, status, liveness, and the agent / skill / framework flags. Sortable and paginated.

onchain_agent_search_resources

get_resource

The full record for one resource by slug, with its recent release and post activity.

onchain_agent_get_resource

list_categories

Every resource category with counts, most populated first.

onchain_agent_list_categories

list_chains

Every blockchain represented in the directory, with resource counts.

onchain_agent_list_chains

⚡

Build

get_deploy_spec

The structured deploy manifest for one resource — runtime, install commands, entry snippet, required keys/env, and a verified vs self-reported deploy status.

onchain_agent_get_deploy_spec

recent_changes

The auditable Listing History — status flips, verification grants, Sato Score tier moves, releases — site-wide or for one resource.

onchain_agent_recent_changes

recommend_stack

Given a goal in plain words, a trust-ranked build stack — bucketed by slot (framework, wallet, payments, trading, data, MCP tooling, security), each pick with its Sato Score, liveness, and deploy-spec status, plus honest gaps.

onchain_agent_recommend_stack

✦

Registry

search_agents

Search the Agent Registry — registered onchain agents with Sato Agent Passports — by text, chain, agent type, or x402 support.

onchain_agent_search_agents

get_agent_passport

One registered agent's full passport manifest: identity, chains, stack, links, payment/x402 metadata, and verification + liveness status.

onchain_agent_get_agent_passport

◈

Signals

get_news

The filtered news feed — official releases, project announcements, and reputable RSS — by kind or chain.

onchain_agent_get_news

get_metrics

Live ecosystem metrics: the ERC-8004 registered-agent count (read from Ethereum mainnet) and the curated project-token index.

onchain_agent_get_metrics

get_changes

What changed since a date — additions, per-resource events, retirements. Keep a local copy in sync without re-fetching the whole catalog.

onchain_agent_get_changes

get_agent_economy

What is actually happening on-chain across the agent venues we track — registries, launchpads, payment rails, account infrastructure — measured weekly per venue, per chain and per lifecycle stage. Every figure carries its evidence tier, method and sample size, and nothing in the payload can be added up.

onchain_agent_get_agent_economy

search_skills

Crypto-relevant agent skills from ClawHub and skills.sh with their static disclosures — hosts contacted, key generation, credential requests, remote-to-shell. Filter by registry, flag or text. A disclosure describes; it never says safe.

onchain_agent_search_skills

◇

Knowledge

get_wiki_page

A full wiki explainer by slug — summary, how it works, key components, risks, related resources.

onchain_agent_get_wiki_page

list_wiki_pages

Every wiki page with its title, keyword, and summary.

onchain_agent_list_wiki_pages

Not using MCP?

The same catalog over plain HTTP. Free, no key, CC-BY-4.0 with attribution to satohub.ai.

/api/openapi.json

OpenAPI contract

Every public read endpoint described in one document, so a client can be generated without anyone being asked.

/api/changes?since=2026-08-01

Change feed

What moved since a date, instead of re-pulling the whole index. Read its coverage block — it says which parts are complete and which are partial.

/api/export/index.json

Full export — JSON

The complete catalog. Slice it with ?category= / ?chain= / ?standard= / ?use_case=.

/api/export/index.csv

Full export — CSV & NDJSON

The same rows for a spreadsheet, or one record per line for streaming and warehouse loads.

Read-only

No writes, no transactions signed. Submissions and briefing signups live on the website forms.

Same data, same rules

Returns exactly what the site shows — no new claims. Self-reported stays labeled; retired projects are never returned.

Fair use

Open and unmetered for now. Be reasonable; heavy or commercial use may be rate limited later.

Building an onchain agent? Submit it to the directory — it'll show up here, queryable by every agent on the protocol.

Join the Sato Hub Briefing

One email a week — the agents, tools, and infrastructure that actually shipped, and why they matter.