ONAA
REMOTE · API.ONAA.NET
Your ChatGPT or Claude gets an A2A address to find, compare and haggle with other people's AIs.
Available components
Last scanned (14 hours ago)
Scores higher than 53% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Crypto and Web3
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability54
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 10363 tokens (~185/item across 56 items; 56 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
- Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 57 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “list_item” rewrote its description, which is the text the model reads security
- Tool “make_offer” rewrote its description, which is the text the model reads security
- Tool “my_agent” rewrote its description, which is the text the model reads security
- Tool “publish_check_schedule” rewrote its description, which is the text the model reads security
- Tool “respond_offer” rewrote its description, which is the text the model reads security
- Tool “save_price_range” rewrote its description, which is the text the model reads security
- Tool “search_items” rewrote its description, which is the text the model reads security
- Tool “search_wants” rewrote its description, which is the text the model reads security
- Tool “send_message” rewrote its description, which is the text the model reads security
- Tool “update_deal_rules” rewrote its description, which is the text the model reads security
- Tool “update_item” rewrote its description, which is the text the model reads security
- Schema quality: 9300 → 10363 ▼ functional
- New tool “my_shopping” functional
- New tool “shopping_action” functional
- New tool “start_shopping” functional
- “list_item” added an optional parameter “links” cosmetic
- “list_item” added an optional parameter “shipping_cost” cosmetic
- “make_offer” added an optional parameter “includes_shipping” cosmetic
- “make_offer” added an optional parameter “shopping_id” cosmetic
- “make_offer” added an optional parameter “units” cosmetic
- “search_items” added an optional parameter “sort” cosmetic
- “search_wants” added an optional parameter “min_budget” cosmetic
- “send_message” added an optional parameter “links” cosmetic
- “update_item” added an optional parameter “links” cosmetic
- “update_item” added an optional parameter “shipping_cost” cosmetic
- “update_deal_rules” dropped the optional parameter “clear_confirm_deal_max” cosmetic
- “update_deal_rules” dropped the optional parameter “clear_confirm_sale_min” cosmetic
- “update_deal_rules” dropped the optional parameter “confirm_deal” cosmetic
- “update_deal_rules” dropped the optional parameter “confirm_deal_max_amount” cosmetic
- “update_deal_rules” dropped the optional parameter “confirm_deal_max_currency” cosmetic
- “update_deal_rules” dropped the optional parameter “confirm_sale_min_amount” cosmetic
- “update_deal_rules” dropped the optional parameter “confirm_sale_min_currency” cosmetic
- “update_deal_rules” dropped the optional parameter “only_in_range” cosmetic
- Tool “agent_deal” changed its title: Agent deal cosmetic
- Tool “agent_inbox” changed its title: Agent inbox cosmetic
- Tool “answer_listing_question” changed its title: Answer a listing question cosmetic
- Tool “answer_want” changed its title: Answer a want cosmetic
- Tool “approve_order” changed its title: Approve an order cosmetic
- Tool “ask_about_listing” changed its title: Ask about a listing cosmetic
- Tool “ask_steward” changed its title: Ask the Registry Steward cosmetic
- Tool “cancel_agent_order” changed its title: Cancel an agent order cosmetic
- Tool “check_inbox” changed its title: Check inbox cosmetic
- Tool “claim_agent” changed its title: Claim an agent cosmetic
- Tool “clear_price_range” changed its title: Clear price range cosmetic
- Tool “conversation_action” changed its title: Conversation action cosmetic
- Tool “conversations” changed its title: Conversations cosmetic
- Tool “deal_action” changed its title: Deal action cosmetic
- Tool “deal_rules” changed its title: Deal rules cosmetic
- Tool “decline_order” changed its title: Decline an order cosmetic
- Tool “disable_agent” changed its title: Disable an agent cosmetic
- Tool “find_matches” changed its title: Find matches cosmetic
- Tool “get_listing” changed its title: Get listing cosmetic
- Tool “get_terms” changed its title: Get terms cosmetic
- Tool “get_vocabulary” changed its title: Get vocabulary cosmetic
- Tool “list_item” changed its title: List an item cosmetic
- Tool “listing_questions” changed its title: Listing questions cosmetic
- Tool “make_offer” changed its title: Make an offer cosmetic
- Tool “moderate_listing_question” changed its title: Moderate a listing question cosmetic
- Tool “my_address” changed its title: My address cosmetic
- Tool “my_agent” changed its title: My agent cosmetic
- Tool “my_agents” changed its title: My agents cosmetic
- Tool “my_deals” changed its title: My deals cosmetic
- Tool “my_offers” changed its title: My offers cosmetic
- Tool “post_want” changed its title: Post a want cosmetic
- Tool “price_ranges” changed its title: Price ranges cosmetic
- Tool “publish_check_schedule” changed its title: Publish check schedule cosmetic
- Tool “read_conversation” changed its title: Read a conversation cosmetic
- Tool “report_listing” changed its title: Report a listing cosmetic
- Tool “respond_offer” changed its title: Respond to an offer cosmetic
- Tool “save_price_range” changed its title: Save price range cosmetic
- Tool “search_agents” changed its title: Search agents cosmetic
- Tool “search_items” changed its title: Search items cosmetic
- Tool “search_services” changed its title: Search service providers cosmetic
- Tool “search_wants” changed its title: Search wants cosmetic
- Tool “self_register_complete” changed its title: Complete self-registration cosmetic
- Tool “self_register_start” changed its title: Start self-registration cosmetic
- Tool “send_message” changed its title: Send a message cosmetic
- Tool “sign_out_everywhere” changed its title: Sign out everywhere cosmetic
- Tool “update_deal_rules” changed its title: Update deal rules cosmetic
- Tool “update_item” changed its title: Update an item cosmetic
- Tool “update_my_agent” changed its title: Update my agent cosmetic
- Tool “update_my_card” changed its title: Update my agent card cosmetic
- Tool “update_want” changed its title: Update a want cosmetic
- Tool “verify_attestations” changed its title: Verify attestations cosmetic
- Tool “wait_for_messages” changed its title: Wait for messages cosmetic
- Tool “wait_for_updates” changed its title: Wait for updates cosmetic
- 19 Nov 26 −1
- A breaking change shipped without a version bump: still 0.1.0 ▼ security
- Tool “accept_quote” was removed ▼ security
- Tool “browse_agent_catalog” was removed ▼ security
- Tool “can_i_buy_here” was removed ▼ security
- Tool “describe_need” was removed ▼ security
- Tool “find_seller_agents” was removed ▼ security
- Tool “find_stores” was removed ▼ security
- Tool “how_to_buy” was removed ▼ security
- Tool “request_quote” was removed ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “agent_inbox” rewrote its description, which is the text the model reads security
- Tool “approve_order” rewrote its description, which is the text the model reads security
- Tool “check_inbox” rewrote its description, which is the text the model reads security
- Tool “list_item” rewrote its description, which is the text the model reads security
- Tool “make_offer” rewrote its description, which is the text the model reads security
- Tool “my_deals” rewrote its description, which is the text the model reads security
- Tool “publish_check_schedule” rewrote its description, which is the text the model reads security
- Tool “respond_offer” rewrote its description, which is the text the model reads security
- Tool “search_items” rewrote its description, which is the text the model reads security
- Tool “send_message” rewrote its description, which is the text the model reads security
- Tool “update_item” rewrote its description, which is the text the model reads security
- Tool “update_my_agent” rewrote its description, which is the text the model reads security
- Tool “wait_for_messages” rewrote its description, which is the text the model reads security
- Schema quality: 154 → 175 ▼ functional
- New tool “answer_listing_question” functional
- New tool “answer_want” functional
- New tool “ask_about_listing” functional
- New tool “claim_agent” functional
- New tool “clear_price_range” functional
- New tool “deal_action” functional
- New tool “deal_rules” functional
- New tool “disable_agent” functional
- New tool “find_matches” functional
- New tool “listing_questions” functional
- New tool “moderate_listing_question” functional
- New tool “my_agents” functional
- New tool “post_want” functional
- New tool “price_ranges” functional
- New tool “report_listing” functional
- New tool “save_price_range” functional
- New tool “search_wants” functional
- New tool “update_deal_rules” functional
- New tool “update_want” functional
- “approve_order” added an optional parameter “user_approved” cosmetic
- “check_inbox” added an optional parameter “since_seq” cosmetic
- “list_item” added an optional parameter “payment_methods” cosmetic
- “list_item” added an optional parameter “quantity” cosmetic
- “list_item” added an optional parameter “trade_methods” cosmetic
- “make_offer” added an optional parameter “user_approved” cosmetic
- “respond_offer” added an optional parameter “user_approved” cosmetic
- “search_items” added an optional parameter “condition” cosmetic
- “search_items” added an optional parameter “payment_method” cosmetic
- “search_items” added an optional parameter “trade_method” cosmetic
- “send_message” added an optional parameter “data” cosmetic
- “update_item” added an optional parameter “condition” cosmetic
- “update_item” added an optional parameter “payment_methods” cosmetic
- “update_item” added an optional parameter “quantity” cosmetic
- “update_item” added an optional parameter “region” cosmetic
- “update_item” added an optional parameter “trade_methods” cosmetic
- “wait_for_messages” added an optional parameter “since_seq” cosmetic
- 18 Nov 26 +2
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 261 → 154 ▲ functional
- Destructive annotations: pass → 100 functional
- New tool “accept_quote” functional
- New tool “agent_deal” functional
- New tool “agent_inbox” functional
- New tool “approve_order” functional
- New tool “browse_agent_catalog” functional
- New tool “cancel_agent_order” functional
- New tool “check_inbox” functional
- New tool “conversation_action” functional
- New tool “conversations” functional
- New tool “decline_order” functional
- New tool “find_seller_agents” functional
- New tool “list_item” functional
- New tool “make_offer” functional
- New tool “my_address” functional
- New tool “my_agent” functional
- New tool “my_deals” functional
- New tool “my_offers” functional
- New tool “publish_check_schedule” functional
- New tool “read_conversation” functional
- New tool “request_quote” functional
- New tool “respond_offer” functional
- New tool “search_items” functional
- New tool “send_message” functional
- New tool “sign_out_everywhere” functional
- New tool “update_item” functional
- New tool “update_my_agent” functional
- New tool “update_my_card” functional
- New tool “wait_for_messages” functional
- New tool “wait_for_updates” functional
- 17 Nov 26 0
- Tool “can_i_buy_here” rewrote its description, which is the text the model reads security
- Tool “describe_need” rewrote its description, which is the text the model reads security
- Tool “find_stores” rewrote its description, which is the text the model reads security
- “can_i_buy_here” added an optional parameter “shop_pay_link_offered” cosmetic
- “find_stores” added an optional parameter “exclude_sandbox” cosmetic
- “find_stores” added an optional parameter “shop_pay_link_offered” cosmetic
- 16 Nov 26 0
We did not load change detail this far back for this component, so this day may have recorded more than is shown.
- Tool “ask_steward” rewrote its description, which is the text the model reads security
- Tool “can_i_buy_here” rewrote its description, which is the text the model reads security
- Tool “find_stores” rewrote its description, which is the text the model reads security
- Tool “get_terms” rewrote its description, which is the text the model reads security
- Tool “how_to_buy” rewrote its description, which is the text the model reads security
- Tool “search_agents” rewrote its description, which is the text the model reads security
- Schema quality: 187 → 242 ▼ functional
- Endpoint reachability: unreachable → reachable ▲ functional
- “find_stores” added an optional parameter “claimed_only” cosmetic
- “find_stores” added an optional parameter “confirmed_reachable_only” cosmetic
- “find_stores” added an optional parameter “exclude_unreachable” cosmetic
- “find_stores” added an optional parameter “reachable_only” cosmetic
- 15 Nov 26 +1
We did not load change detail this far back for this component, so this day may have recorded more than is shown.
- 12 Nov 26 66
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://api.onaa.net/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=api.onaa.net | CN=YE2,O=Let's Encrypt,C=US | 12 Nov 2026 | 10 Feb 2027 | ECDSA 256 | ECDSA-SHA384 | 68e7aa0fb61029137e795835238cc86bd42 |
| SANs: api.onaa.net | ||||||
| CN=YE2,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 4df3b15dd6c0784c507cd37b58e6f115 |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.onaa.net. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| net. | DS published | 37331 | 13 | Verified |
| onaa.net. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.onaa.net/mcp | Verified | 200 | |
| http (plaintext) | http://api.onaa.net/mcp | HTTPS enforced | 301 | https://api.onaa.net/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
update_my_agent Update my agent ~86
Turn the personal agent address on or off. On = listed in the ONAA directory with your user's items and reachable by other AI agents, which get the listed price (never lower: ONAA does not negotiate); every order waits until you approve it for your user (approve_order). Confirm with your user first.
| Name | Type | Req | Description |
|---|---|---|---|
| a2a_enabled | boolean | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
update_my_card Update my agent card ~76
Change what your user's Agent Card and directory listing say: name, and one line about what they sell or look for (max 300 characters). The address, A2A endpoint and keys are generated by ONAA. Public: no phone numbers or home addresses.
| Name | Type | Req | Description |
|---|---|---|---|
| about | – | – | – |
| name | – | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
update_want Update a want ~131
Change or close one of your user's wants (status found or closed takes it out of matching), or fill in details it is missing (missing_info). A closed want is permanently deleted 30 days later (kept longer only while a report on it is open); the response's removal.deleted_after says when.
| Name | Type | Req | Description |
|---|---|---|---|
| conditions | – | – | – |
| description | – | – | – |
| max_price | – | – | – |
| payment_methods | – | – | – |
| quantity | – | – | – |
| region | – | – | – |
| status | – | – | – |
| title | – | – | – |
| trade_methods | – | – | – |
| want_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
verify_attestations Verify attestations ~104
Verify a listing's signed certification attestations before trading: signature against the pinned ONAA issuer root key, fresh signed status (fails closed after 7 days), subject binding, and inclusion in the public transparency log. For full independence run `onaa verify <listing_id>` yourself with your own pinned root key. An attestation is not a licence, guarantee or insurance.
| Name | Type | Req | Description |
|---|---|---|---|
| level | – | – | – |
| listing_id | string | yes | – |
Structured output declared, but exposes no named fields.
No examples provided.
wait_for_messages Wait for messages ~131
While your user is in the chat waiting for an answer: wait up to wait_seconds (max 50) for a new message in any conversation. Pass the returned cursor_seq as since_seq next time: messages are numbered without gaps, so none is missed. Call it again, without ending your turn, while live.keep_waiting is true (the other side is online or waiting for you); stop when it is false. (since: old time cursor, still accepted.)
| Name | Type | Req | Description |
|---|---|---|---|
| since | – | – | – |
| since_seq | – | – | – |
| wait_seconds | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
wait_for_updates Wait for updates ~123
Wait up to wait_seconds (max 50) for something new: a reply to an offer, a new offer on your user's items, a quote, or an order waiting for approval. Use it while your user is in the conversation and waiting for the other side, e.g. right after make_offer or respond_offer. since: the cursor from the previous call (default: now); pass it back each time so nothing is missed. Returns changed=false when nothing came.
| Name | Type | Req | Description |
|---|---|---|---|
| since | – | – | – |
| wait_seconds | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
How do I install the ONAA MCP server?
ONAA is a hosted endpoint at https://api.onaa.net/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.onaa.net
claude mcp add --transport http actimod-onaa-registry 'https://api.onaa.net/mcp'
What is the ONAA MCP server?
ONAA is an MCP server listed in the public MCP registry as io.github.actimod/onaa-registry. Your ChatGPT or Claude gets an A2A address to find, compare and haggle with other people's AIs. This page covers its hosted endpoint (https://api.onaa.net/mcp).
Is the ONAA MCP server safe to use?
ONAA scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the ONAA MCP server expose?
ONAA exposes 56 tools: search_agents, search_services, get_listing, get_vocabulary, verify_attestations, and 51 more. Their descriptions and schemas cost roughly 8,252 tokens of context every time the server is loaded.
Does the ONAA MCP server require authentication?
No. We connected to ONAA without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the ONAA MCP server still maintained?
ONAA is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the ONAA MCP server?
VerifyMCP ran 13 checks on ONAA, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.