MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Payments & trading

SBOR

Check a lending rate before your agent borrows. Bitcoin-backed dollar rates from contracts. No key.

Checks passed
14 / 22

0 failed · 8 not measured

Median response
54 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
6

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
402

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 54 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-06-18, serverInfo.name sbor.

  • Pass
    Lists tools

    tools/list returned 6 tools.

  • Pass
    Current protocol

    Negotiated 2025-06-18. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 54 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 54 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    8 of 8 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Pass
    Website matches publisher

    The website host matches the reverse-domain namespace.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-10-12T20:17:41.75661Z, within 180 days.

  • Not measured
    Open-source licence

    The GitHub licence lookup has not returned an OSI result yet.

Start using SBOR

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http sbor https://mcp.sbor.xyz/mcp

Capabilities

Tools 6

compare_chains

The same asset classes on the largest lending markets on Ethereum, Base, Hyperliquid and Solana, plus SOFR, the US repo rate, and what it costs to borrow dollars against bitcoin. Context only: none of these is ever a constituent of an SBOR index. Every rate is read from the venues' contracts (Aave on Ethereum and Base, HyperLend on Hyperliquid, Kamino on Solana, Morpho for the bitcoin-collateral markets); DefiLlama picks the largest market per chain, gives its size, and stands in only if a read fails.

Discovered
compare_rate

Given a rate you have been offered, say whether it is above or below the market for that currency, and by how much. This is the main reason SBOR exists. Recommended use: if a borrow offer is more than 50 basis points above the benchmark, stop and ask a human. Use SBOR to stop, never to start. For a dollar loan against bitcoin, compare with that stablecoin's rate (for example BTC-COLLATERAL-USDC) where one is published, else with BTC-COLLATERAL-USD; for lending on Stacks against other collateral, with the index for the currency. This tool refuses rather than guesses: an error result means there is no trustworthy answer, not that the rate is bad.

Discovered
get_history

Daily fixings since each rate began. Use this to see whether a rate is unusual, or how the cost of capital has moved. Means are given per methodology version, never across a change in how the number is built.

Discovered
get_methodology

The full methodology and integration policy: how the fixing is built, what is excluded and why, and what SBOR will and will not do. Read this before quoting a rate in anything that matters.

Discovered
get_rate

SBOR's benchmark borrow and supply rates, read from lending contract state: BTC-COLLATERAL-USD, what it costs to borrow dollars against bitcoin, with a rate per stablecoin (from 14 October 2026), and the currency indices for lending on Stacks. Use this to judge whether a lending offer is good: borrowing above the SBOR borrow rate means paying more than the market, supplying below the supply rate means earning less. Returns every currency index unless one is named. Always read the freshness line first.

Discovered
list_markets

Every venue and asset in an index, with its borrow rate, supply rate, utilization, depth and weight. Utilization explains why a rate sits where it does.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected54 ms6