kerne-honesty-index
Registry code: fb86df0ffe27cbaa
Advertised versus realized yield for synthetic and yield-bearing dollars, measured from ERC-4626 share-price growth on chain and published as a signed hourly snapshot. Call list_rows, then get_row for the evidence behind a figure. Read get_methodology before comparing rows: a null gap means the two figures are not comparable, never that a protocol paid zero, and a protocol in an announced wind down paying nothing is behaving correctly. The board is published by Kerne Protocol, which is measured on it and lists its own row first by rule; get_board reports in summary.kerneIsWorst whether Kerne…
- endpoint
- https://kerne.fi/api/mcp
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is kerne-honesty-index live?
- Yes — it answered the hub's last check (checked 21m ago). It answered 100% of checks over the last 30 days.
- Is kerne-honesty-index free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does kerne-honesty-index have?
- 6 tools: get_row, get_corrections, get_right_of_reply, list_rows, get_methodology, get_board.
- Is kerne-honesty-index safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 99.7%· all time 99.7%
last good check
of 6 tools
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- unknown → live
- used for
- compare advertised vs realized stablecoin yield
- get evidence for a yield figure
- read yield methodology
- takes → gives
- text → data
- tools
- 6 reads
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
get_corrections reads open 14h ago
Every time this board changed something it had stated about a named company, or changed a method rule, with the old value, the new one, the date and the rule that stops a repeat. Append only: entries are never edited or removed.
{ "type": "object", "properties": {}, "additionalProperties": false }arguments 5 linesget_right_of_reply reads open 14h ago
The free, permanent, unedited reply slot every measured protocol has on its own row, its terms, the only three things that will not be published, and every reply received so far.
{ "type": "object", "properties": {}, "additionalProperties": false }arguments 5 lineslist_rows reads open 10h ago
The roster: every vault the Kerne Honesty Index measures, with its key, protocol, symbol, chain and contract address. Cheap. Call this first to find the key for get_row.
{ "type": "object", "properties": {}, "additionalProperties": false }arguments 5 linesget_methodology reads open 10h ago
The measurement, the comparability rules that decide when a gap may be stated at all, the capture expiry, what this board deliberately does not cover, and the standing commitment if you reproduce a row and get a different answer.
{ "type": "object", "properties": {}, "additionalProperties": false }arguments 5 linesget_board reads open 14h ago
The full Kerne Honesty Index: what each of the measured synthetic and yield-bearing dollars ADVERTISES against what its holders actually REALIZED, computed from ERC-4626 share-price growth on chain over a 30 day window, plus the board summary and the provenance of the snapshot. Kerne Protocol publishes this board, is on it, and lists its own row first by rule. A gap of null means the two figures are not comparable, never that the protocol paid zero.
{ "type": "object", "properties": {}, "additionalProperties": false }arguments 5 linesget_row reads unknown 10h ago
One row with everything behind it: the verbatim advertised quote and the first-party page it was read from, the capture date, both block heights, both share prices, the arithmetic, the exact eth_call payloads needed to reproduce it, and any right of reply the protocol has published.
{ "type": "object", "required": [ "row" ], "properties": { "row": { "enum": [ "kerne-skusd", "aegis-syusd", "avant-savusd", "cap-stcusd", "curve-scrvusd", "ethena-susde", "falcon-susdf", "frax-sfrxusd", "maple-syrupusdc", "maple-syrupusdt", "neutrl-snusd", "noon-susn", "sky-susds", "spark-susdc", "tori-strusd", "usual-susd0", "stableslabs-susdx", "resolv-wstusr", "yieldfi-yusd", "elixir-sdeusd", "level-slvlusd" ], "type": "string", "description": "Row key, from list_rows." } }, "additionalProperties": false }arguments 36 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's idfb86df0ffe27cbaa.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/fb86df0ffe27cbaa/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/fb86df0ffe27cbaa?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.