Directory / Sato Hub: Build Onchain & Crypto Agents

Sato Hub: Build Onchain & Crypto Agents

Q: Is Sato Hub: Build Onchain & Crypto Agents MCP server safe?

QAmcp's test on 20 Oct 2026: No hidden instructions were found in its tool descriptions. Its error messages showed no secrets or internal details. 42 of its 46 tools are labeled read-only; the others may change or send things. Overall it scored 85/100 on 20 Oct 2026. A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

by satohub.ai · https://satohub.ai/api/mcp

Build any crypto agent: stack picks, x402 and ERC-8004 lookups, wallet-key checks, unsigned swaps.

46 tools✓ no account neededPricing: on their site

See pricing →Visit website

85 /100

PASS · WITH NOTES

12 of 12 checks · 20 Oct 2026

Is Sato Hub: Build Onchain & Crypto Agents MCP server safe?

No hidden instructions were found in its tool descriptions.
Its error messages showed no secrets or internal details.
42 of its 46 tools are labeled read-only; the others may change or send things.
Overall it scored 85/100 on 20 Oct 2026.

A test can only see what the server shows from outside, not what it does with your data behind the scenes. Connect servers from makers you trust.

What it can do

46 tools, in the server's own words.

onchain_agent_search_resourcesread-only

USE WHEN you need to look up crypto-agent tooling (frameworks, MCP servers, wallets, payment rails, data tools) by name, chain, standard or what it does, or ch…

onchain_agent_get_resourceread-only

USE WHEN you need to judge one specific directory project: is it open source, still maintained, who is behind it, what does it support.

searchread-only

USE WHEN you want one query box over Sato Hub, the daily-rebuilt index of what onchain and crypto AI agents are built from (frameworks, MCP servers, wallets, x…

fetchread-only

USE WHEN you hold an id that `search` returned and want that record from Sato Hub, the daily-rebuilt index of what onchain and crypto AI agents are built from,…

onchain_agent_get_deploy_specread-only

USE WHEN a component has been picked (from onchain_agent_recommend_stack, onchain_agent_build_plan or a search) and the next step is installing it, once per pi…

onchain_agent_recent_changesread-only

USE WHEN asked what has changed recently across crypto-agent tooling, or what has happened to one specific project over time, and you want dated, attributable …

onchain_agent_list_categoriesread-only

USE WHEN you need the valid category values before filtering onchain_agent_search_resources, or want to see how the crypto-agent landscape divides up by size.

onchain_agent_list_chainsread-only

USE WHEN you need the valid chain names before filtering onchain_agent_search_resources, or want to know which chains have real agent tooling behind them rathe…

onchain_agent_get_newsread-only

USE WHEN asked what is new or what shipped recently in crypto AI agents, and you want dated, source-attributed items rather than undated blog posts.

onchain_agent_get_metricsread-only

USE WHEN you need one current, citable headline figure for the onchain agent ecosystem rather than a number from an article of unknown age: the ERC-8004 Identi…

onchain_agent_get_wiki_pageread-only

USE WHEN asked to explain a crypto-agent concept (what x402 is, how agents hold wallets, what ERC-8004 does) and you want a sourced explainer you can cite.

onchain_agent_search_agentsread-only

USE WHEN you need a RUNNING agent to work with, hire or pay (not a tool to build one with) and want to see who registered it, on which chain, and whether it ac…

onchain_agent_get_agent_passportread-only

USE WHEN you are about to work with, pay or depend on a REGISTERED agent and want its published identity before committing.

onchain_agent_recommend_stackread-only

USE WHEN someone wants to build any onchain or crypto agent ("Build any crypto agent") and says what it should do in plain words: "a trading agent on Base", "a…

onchain_agent_list_wiki_pagesread-only

USE WHEN you need the slug for a crypto-agent explainer before calling onchain_agent_get_wiki_page, or want to see which concepts have a sourced page you can c…

onchain_agent_get_changesread-only

USE WHEN you keep a local copy of the directory and need only what moved since your last sync (machine-readable added / updated / removed), rather than re-fetc…

onchain_agent_get_agent_economyread-only

USE WHEN asked how big the onchain agent economy actually is (how many agents are really registered, launched, paying or trading) and you want measured chain r…

onchain_agent_search_skillsread-only

USE WHEN someone is about to install an agent skill and should know what it will touch first: keys, credentials, remote scripts, outbound hosts.

onchain_agent_get_trendread-only

USE WHEN the question is whether a measurement is going up or down (ANSWERS ONE QUESTION).

onchain_agent_compare_listingsread-only

USE WHEN the question is how two directory listings compare on the axes Sato Hub tracks for both (ANSWERS ONE QUESTION), e.g.

onchain_agent_explain_numberread-only

USE WHEN the question is where a published Sato Hub number comes from (ANSWERS ONE QUESTION) and you need its method, sample and reproduce call before quoting …

onchain_agent_get_score_methodologyread-only

USE WHEN you are about to describe, apply or compare the Sato Score — or when asked how to tell whether a crypto-agent project is real, maintained or open — so…

onchain_agent_get_data_freshnessread-only

USE WHEN you are about to quote a Sato Hub number, score, count or feed item and want to know how old it is — or when a figure looks stale and you need to know…

onchain_agent_search_listingsread-only

USE WHEN someone wants a ready-made onchain agent PACKAGE to download or fork rather than assemble one.

and 22 more

Test results

Safe mode: only tools labeled read-only were run. How the test works

!
Every tool is described
5 warnings
- !onchain_agent_search_skills: Inputs with no description: limit
- !onchain_agent_search_listings: Inputs with no description: limit
- !onchain_agent_preflight: Description is very long (4852 characters), which uses up the AI's memory
- !onchain_agent_preflight: Description uses vague words ("something", "handles") instead of saying what it does and returns: "USE WHEN you are about to install a package, clone a repo, connect to an MCP end"
- !onchain_agent_build_plan: Description is very long (4366 characters), which uses up the AI's memory
note
!
Tools work with good inputs
1 warning
- !onchain_agent_create_agent: Answered with about 781 KB of text. Many AI apps cut off tool answers this big, so the AI may never see the end of it.
- –onchain_agent_recommend_stack: Not run: labeled read-only, but its description says "charges", which usually means it changes something. Skipped to be safe: if it only reads, a clearer description helps AI apps too, or test again with --owner
- –onchain_agent_preflight: Not run: labeled read-only, but its description says "permanently", which usually means it changes something. Skipped to be safe: if it only reads, a clearer description helps AI apps too, or test again with --owner
- and 37 more
note
!
Bad inputs give a clean error
33 warnings
- !onchain_agent_get_resource: Accepted missing required input "slug" without complaining
- !onchain_agent_get_resource: Accepted wrong type for "slug" without complaining
- !search: Accepted missing required input "query" without complaining
- !search: Accepted wrong type for "query" without complaining
- !onchain_agent_get_deploy_spec: Accepted missing required input "slug" without complaining
- !onchain_agent_get_deploy_spec: Accepted wrong type for "slug" without complaining
- !onchain_agent_get_wiki_page: Accepted missing required input "slug" without complaining
- !onchain_agent_get_wiki_page: Accepted wrong type for "slug" without complaining
- and 32 more
note
✓
ConnectsConnected in 237 ms
pass
✓
Ready for the newest MCP versionUses the latest MCP version (2026-07-28)
pass
✓
Lists its toolsFound 46 tools
pass
✓
Tools are labeled safe or dangerousEvery tool has a safety label
pass
✓
No hidden instructionsNo hidden instructions found in tool descriptions
pass
✓
Tools work together
5 chains working
- ✓onchain_agent_search_resources → onchain_agent_get_resource: onchain_agent_get_resource found what onchain_agent_search_resources returned (slug = "coinbase-agentkit")
- ✓onchain_agent_search_resources → onchain_agent_get_deploy_spec: onchain_agent_get_deploy_spec found what onchain_agent_search_resources returned (slug = "coinbase-agentkit")
- ✓onchain_agent_search_resources → onchain_agent_recent_changes: onchain_agent_recent_changes found what onchain_agent_search_resources returned (slug = "coinbase-agentkit")
- ✓onchain_agent_search_resources → onchain_agent_get_wiki_page: onchain_agent_get_wiki_page found what onchain_agent_search_resources returned (slug = "coinbase-agentkit")
- ✓onchain_agent_search_resources → onchain_agent_get_agent_passport: onchain_agent_get_agent_passport found what onchain_agent_search_resources returned (slug = "coinbase-agentkit")
pass
✓
Fast enough
All good
- ✓Connecting took 237 ms
- ✓Listing tools took 470 ms
- ✓Average tool answer: 530 ms
- ✓onchain_agent_create_agent: Slowest tool: onchain_agent_create_agent (1.6 s)
pass
✓
No secrets leakedChecked 33 error messages: no secrets or internal details
pass
✓
Resources and prompts workOpened 2 of 2 prompts
pass

Test it yourself

Free and open source. Same checks, same score.

npx qamcp-cli https://satohub.ai/api/mcp

Score over time

20 Oct 202685

One test so far. New tests will show here.

Reviews

Coming soon: reviews from people who use Sato Hub: Build Onchain & Crypto Agents, signed in with GitHub, one per person. Reviews never change the score.

Is this your server?

Soon you can claim this page: re-test it from here, reply to results, and show a "Tested by QAmcp" badge.

Have a concern, or want it removed? Ask us and we'll take it off the list. How the directory works