Atlas entry

`satohub.ai`

50 capabilities over ARD and MCP. The inventory is incomplete. First atlas observation.

Observed 10 Nov 2026, 12:04 UTC · passive: no tools called, no credentials sent · sha256:e2ad3a…6172

50 capabilities, 48 of them tools. 32 only read. 2 change records. 14 have no reading.

AI reading, beta. side-effects v1 on claude-haiku-5.5, calibrated on MCP (golden-3). Only readings above a measured precision count. Counts are tools, not calls: no tool was called.

AI readings summary · beta

The service lists 48 tools, and 34 have AI readings.

onchain_agent_join_passport and onchain_agent_register_agent are read as creating records.

32 tools are read as read-only, including onchain_agent_list_wiki_pages, onchain_agent_inspect_listing and onchain_agent_get_changes.

Written by code from the AI readings on this page: it groups them and says nothing they do not.

What an agent can do here

AI readings, beta · Readings on 34 of 48 MCP tools.

Moves money
0
No tool read this way.
Deletes or cancels records
0
No tool read this way.
Sends messages to people
0
No tool read this way.
Changes permissions
0
No tool read this way.
Runs code
0
No tool read this way.
Should ask a person first
0
No tool read this way.

No counted reading 14 tools No reading was counted, so any effect above is possible for them: onchain_agent_build_plan, onchain_agent_check_install, onchain_agent_create_agent, onchain_agent_passport_action, onchain_agent_preflight, onchain_agent_recommend_stack, onchain_agent_resolve_token, onchain_agent_route_agent, onchain_agent_route_launch, onchain_agent_route_swap and 4 more.

What changed

First atlas observation. Atlas history

Look first

AI reading, beta: AI adds items here; it never removes one.

No tool is read as one of the six effects. A zero is a count, not a clearance.

Surfaces

5 protocols checked

ARD	Valid	v0.91 · 1 retrieved artifact
A2A	Not found	0 skills
MCP	Valid	2026-07-28 · 48 tools · resources not advertised · 2 prompts
OpenAPI	Not detected	0 operations
WebMCP	Not detected	0 declarative form tools · experimental

Exact states and meaning

ARD
observed
Exact state: valid · Revision v0.91 · 1 retrieved artifact
A usable protocol document was retrieved and validated.
Directly observed
A2A
absent
Exact state: not found · 0 skills
The supported discovery location returned no matching document.
Not found does not prove the service exposes no such interface elsewhere.
Not observed / not fetched
MCP
observed
Exact state: valid · Revision 2026-07-28 · 48 tools · resources not advertised · 2 prompts
A usable protocol document was retrieved and validated.
Directly observed
OpenAPI
absent
Exact state: not detected · 0 operations
No endpoint was established from the evidence and scope that InterfaceDelta inspected.
Not detected does not prove that no endpoint exists.
Not observed / not fetched
WebMCP
absent
Exact state: not detected · 0 declarative form tools · experimental
No named declarative WebMCP form tools were observed in the origin root HTML.
Script-registered tools and other pages are not observed, so this does not mean the site has no WebMCP tools.
Not observed / not fetched

50 · inventory incomplete

Showing 50 of 50.

Tool and inputs							◇ AI reading, beta · confidence
Read as none of the six 34 Not a clearance.
id*							Reads only0.88
`fetch` inputs `id` (required) AI Reads only 0.88
a, b, response_format							Reads only0.87
`onchain_agent_compare_listings` inputs `a` (required), `b` (required), `response_format` AI Reads only 0.87
response_format, slug*							Reads only0.88
`onchain_agent_explain_number` inputs `response_format`, `slug` (required) AI Reads only 0.88
category, chain, limit, max_price_usd and 2 more							Reads only0.80
`onchain_agent_find_x402_service` inputs `category`, `chain`, `limit`, `max_price_usd` and 2 more AI Reads only 0.80
chain, detail, include_platforms, response_format and 1 more							Reads only0.84
`onchain_agent_get_agent_economy` inputs `chain`, `detail`, `include_platforms`, `response_format` and 1 more AI Reads only 0.84
response_format, slug*							Reads only0.92
`onchain_agent_get_agent_passport` inputs `response_format`, `slug` (required) AI Reads only 0.92
chain*, response_format							Reads only0.80
`onchain_agent_get_chain_card` inputs `chain` (required), `response_format` AI Reads only 0.80
detail, since							Reads only0.92
`onchain_agent_get_changes` inputs `detail`, `since` AI Reads only 0.92
chain, contract, include_testnets, kind and 4 more							Reads only0.85
`onchain_agent_get_contract_facts` inputs `chain`, `contract`, `include_testnets`, `kind` and 4 more AI Reads only 0.85
response_format, surface							Reads only0.90
`onchain_agent_get_data_freshness` inputs `response_format`, `surface` AI Reads only 0.90
response_format, slug*							Reads only0.80
`onchain_agent_get_deploy_spec` inputs `response_format`, `slug` (required) AI Reads only 0.80
days, response_format, score_days, slug*							Reads only0.90
`onchain_agent_get_listing_history` inputs `days`, `response_format`, `score_days`, `slug` (required) AI Reads only 0.90
response_format, token_limit							Reads only0.88
`onchain_agent_get_metrics` inputs `response_format`, `token_limit` AI Reads only 0.88
chain, kind, limit, offset and 1 more							Reads only0.92
`onchain_agent_get_news` inputs `chain`, `kind`, `limit`, `offset` and 1 more AI Reads only 0.92
include_activity, response_format, slug*							Reads only0.90
`onchain_agent_get_resource` inputs `include_activity`, `response_format`, `slug` (required) AI Reads only 0.90
response_format							Reads only0.88
`onchain_agent_get_score_methodology` inputs `response_format` AI Reads only 0.88
ecosystem, package*, response_format, version							Reads only0.88
`onchain_agent_get_sdk_lineage` inputs `ecosystem`, `package` (required), `response_format`, `version` AI Reads only 0.88
chain, grain, mode, points and 3 more							Reads only0.88
`onchain_agent_get_trend` inputs `chain`, `grain`, `mode`, `points` and 3 more AI Reads only 0.88
response_format, slug*							Reads only0.86
`onchain_agent_get_wiki_page` inputs `response_format`, `slug` (required) AI Reads only 0.86
chain, response_format, scheme, x402_version							Reads only0.93
`onchain_agent_get_x402_facilitators` inputs `chain`, `response_format`, `scheme`, `x402_version` AI Reads only 0.93
response_format, slug*							Reads only0.90
`onchain_agent_inspect_listing` inputs `response_format`, `slug` (required) AI Reads only 0.90
builder_stamp, claim_sha256, issued_at, name and 3 more							Creates records0.85
`onchain_agent_join_passport` inputs `builder_stamp`, `claim_sha256`, `issued_at`, `name` and 3 more AI Creates records 0.85
response_format							Reads only0.92
`onchain_agent_list_categories` inputs `response_format` AI Reads only 0.92
response_format							Reads only0.90
`onchain_agent_list_chains` inputs `response_format` AI Reads only 0.90
response_format							Reads only0.90
`onchain_agent_list_wiki_pages` inputs `response_format` AI Reads only 0.90
days, limit, response_format, slug							Reads only0.88
`onchain_agent_recent_changes` inputs `days`, `limit`, `response_format`, `slug` AI Reads only 0.88
agent_type, chains_supported, contact_email, description and 10 more							Creates records0.86
`onchain_agent_register_agent` inputs `agent_type`, `chains_supported`, `contact_email`, `description` and 10 more AI Creates records 0.86
chain, pair, response_format							Reads only0.85
`onchain_agent_route_lp` inputs `chain` (required), `pair` (required), `response_format` AI Reads only 0.85
amount, chain*, from, origin and 3 more							Reads only0.85
`onchain_agent_scan_recipient` inputs `amount`, `chain` (required), `from`, `origin` and 3 more AI Reads only 0.85
agent_type, chain, query, response_format and 1 more							Reads only0.86
`onchain_agent_search_agents` inputs `agent_type`, `chain`, `query`, `response_format` and 1 more AI Reads only 0.86
cursor, license, limit, query and 2 more							Reads only0.90
`onchain_agent_search_listings` inputs `cursor`, `license`, `limit`, `query` and 2 more AI Reads only 0.90
category, chain, creator, deploys_as and 22 more							Reads only0.88
`onchain_agent_search_resources` inputs `category`, `chain`, `creator`, `deploys_as` and 22 more AI Reads only 0.88
flag, limit, query, registry and 2 more							Reads only0.82
`onchain_agent_search_skills` inputs `flag`, `limit`, `query`, `registry` and 2 more AI Reads only 0.82
query*							Reads only0.90
`search` inputs `query` (required) AI Reads only 0.90
No counted reading 14 No reading was counted, so any effect is possible.
budget_usd, chain, constraints, goal* and 3 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_build_plan` inputs `budget_usd`, `chain`, `constraints`, `goal` (required) and 3 more
cmd, command, config, install and 4 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_check_install` inputs `cmd`, `command`, `config`, `install` and 4 more
chain, format, framework, goal* and 3 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_create_agent` inputs `chain`, `format`, `framework`, `goal` (required) and 3 more
action*, authorizer, claim_sha256, issued_at and 7 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_passport_action` inputs `action` (required), `authorizer`, `claim_sha256`, `issued_at` and 7 more
address, agent, chain, endpoint and 9 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_preflight` inputs `address`, `agent`, `chain`, `endpoint` and 9 more
chain, goal*, max_per_slot, response_format and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_recommend_stack` inputs `chain`, `goal` (required), `max_per_slot`, `response_format` and 1 more
address, chain, contract, input and 5 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_resolve_token` inputs `address`, `chain`, `contract`, `input` and 5 more
capability, chain, requires_mcp, requires_x402 and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_route_agent` inputs `capability`, `chain`, `requires_mcp`, `requires_x402` and 1 more
chain, deployer, goal, max_pool_fee_pct and 4 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_route_launch` inputs `chain` (required), `deployer`, `goal` (required), `max_pool_fee_pct` and 4 more
amount, chain, referrer, response_format and 4 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_route_swap` inputs `amount` (required), `chain` (required), `referrer`, `response_format` and 4 more
budget_usd, chain, constraints, goal* and 2 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_scaffold_plan` inputs `budget_usd`, `chain`, `constraints`, `goal` (required) and 2 more
category, chains, contact_email, description and 4 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_submit_project` inputs `category` (required), `chains`, `contact_email`, `description` (required) and 4 more
amount_in, chain_in, chain_out, deadline and 11 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_swap` inputs `amount_in` (required), `chain_in` (required), `chain_out`, `deadline` and 11 more
action, notify_to, response_format, target and 1 more	unknown	unknown	unknown	unknown	unknown	unknown	No reading
`onchain_agent_watch` inputs `action`, `notify_to` (required), `response_format`, `target` (required) and 1 more
MCP prompts 2 Not read by AI.
no inputs							Not read
`build_crypto_agent`
no inputs							Not read
`check_before_install`

Read as this effect No reading: unknown Not read as this effect◇ AI readings, beta. A zero is a count, not a clearance.

Not observed in this Passport: A2A skills, MCP resources, OpenAPI operations.

The atlas shows each capability by its plain identifier, inputs and declared sign-in. Publisher descriptions, paths, links and source evidence are not published here.

The comparison with the previous observation is shown only to the account that recorded it.

Atlas history

1 observation

10 Nov 2026, 12:04 UTC50 capabilities · ARD, MCP 2026-07-28 and MCP Server Card · MCP endpoint validFirst observation
Fingerprint and versions
Fingerprint
e2ad3ae733d554a18894e29dae3a4d183dd3120dc089ddcb8d49cfe1257a6172
Passport schema
0.5.0, passport-semantic-v4
Consistency
ARD_DECLARED_MCP_SERVER_CARD: mismatch · MCP_PROMPTS_ADVERTISEMENT_LIST: match · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable

Each class compares an observation with the previous atlas observation. Runs of unchanged observations are grouped. Struck values are what the previous observation recorded; inserted values are what this one recorded.

Declared and observed

48 tools declare hints; the AI readings agree with all 34 that have a reading.

A disagreement is not a finding about the service: either side can be wrong. How we compare declarations and readings.

About this entry

ai.satohub/onchain-agents
Listed
Official MCP Registry · first listed 13 Sep 2026 · last listed 25 Oct 2026

Passive observations of a public interface listed in the Official MCP Registry. An observation does not verify security, ownership or compliance, and InterfaceDelta assigns no scores or rankings. Methodology · Report an inaccuracy · Ask for removal

Identity and snapshot

Target key: sha256:237b1eba8fa8d75199f0d5c32525cfe405ed724173015f4a854724ed4eb65f9f
Locator SHA-256: d38e9e3d8e60f915f0d5a8e58505c7a3b0039f68478d90a837032ffc5bcf9188
Snapshot generated: 11 Nov 2026, 22:36 UTC

The entry is one exact observed target, not a real-world service identity, and implies no ownership. Endpoint paths are not published; the locator hash lets an operator confirm their own URL.

Capability facts

As observed from outside, at the time below

Observed: 10 Nov 2026, 12:04 UTC
Signed: 10 Nov 2026, 12:05 UTC

Protocols: ARD, MCP, MCP server card
Tools: 48
Declared sign-in: None declared

Effects counted AI readings, beta

Moves money: 0
Deletes or cancels records: 0
Sends messages to people: 0
Changes permissions: 0
Runs code: 0
Asks a person: 0

48 tools examined; 0 counted above a measured threshold.

Declared vs read disagreements

Declared read-only, read as writing: 0
Declared destructive, read as not writing: 0
Declared non-destructive, read as deleting: 0
Declared closed-world, read as reaching out: 0

Change since previous: First observation
Label status: Current