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

io.github.nowi333/monerometrics

Live Monero network metrics: reorgs, orphans, pool centralization and the Haveno order book.

Checks passed
14 / 22

0 failed · 8 not measured

Median response
487 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
19

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

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 487 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name monerometrics.

  • Pass
    Lists tools

    tools/list returned 19 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 487 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 487 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

    16 of 16 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.

  • Not measured
    Website matches publisher

    This namespace is not a reverse domain, so the website comparison does not apply.

  • Pass
    Source repo linked

    A repository URL is on file.

  • Pass
    Repo owner matches

    The GitHub repository owner matches the namespace login.

  • Pass
    Recently updated

    Updated 2026-11-05T14:57:53.131254Z, within 180 days.

  • Not measured
    Open-source licence

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

Start using io.github.nowi333/monerometrics

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 io-github-nowi333-monerometrics https://api.monerometrics.net/mcp

Capabilities

Tools 19

chain_fork_window

Range of consecutive heights ending at `to` (default the current tip), listing every canonical block and any competing orphan, with fork-point flags. Use this to browse a stretch of the chain or see recent blocks; for a single block use search_block or get_block.

Discovered
chain_provenance

Evidence quality behind pool attribution over a window: share of blocks proven cryptographically by view key, claimed by a pool API, inferred from the coinbase, or unattributed, plus claims a pool could not prove with its own key and the merge-mined share. Use this to judge how far to trust pool_distribution.

Discovered
get_block

Full detail of one block given its exact 64-character hash: height, previous hash, timestamp, size, difficulty, reward, coinbase, transaction hashes, merge-mining tag, mining pool and, when proven, the view-key proof inputs. Use this when you already have a block hash (e.g. from recent_orphans or chain_fork_window). If you only have a height, use search_block.

Discovered
haveno_book

Live Haveno XMR/USD order book as price levels, both sides, each priced against centralized spot. Each level carries cumulative depth, offer count, payment methods and a reversible flag. `asks` are makers selling XMR (taking one means buying); `bids` are makers buying (taking one means selling). Offers are advertisements with differing payment methods, not a matched book, so the best bid can sit at or above the best ask. Use this to see liquidity at each price; for a single headline price use price. Takes no arguments.

Discovered
haveno_payment_methods

Executed Haveno trades grouped by payment method (PayPal, Zelle, cash by mail...), with trade count, volume and the average, median and standard deviation of the premium over spot. Use this to compare what each payment rail costs. The premium tracks how reversible the rail is (chargeback risk), not privacy. The reversible flag is our own classification, not a Haveno field; methods with few trades give a fragile premium.

Discovered
haveno_premium

Time series of the Haveno peer-to-peer premium over centralized spot, both sides of the book, sampled every 10 minutes. Use this to see how the P2P premium moved over time; for the current value only, use price. Series carry price, amount and offer count but not the payment method (see haveno_payment_methods for that). History starts on 24 August 2026, when recording began.

Discovered
lookup_transaction

Look up one transaction by its 64-character hash: in the mempool or mined, block height, confirmations, whether it is spendable yet, the pool that mined its block, and whether that height was ever contested by a reorg. Use this for any transaction-hash question. It never returns amounts, senders or recipients: the Monero protocol encrypts them.

Discovered
network_blocktime

Time series of the actual time between consecutive canonical blocks, in seconds (target 120 s), one point per block, capped at 1500 points. Use this to spot unusually slow or fast block production, e.g. around a hashrate shift or selfish-mining episode.

Discovered
network_emission

Time series of the average block reward in XMR per block (Monero tail emission is about 0.6 XMR plus fees). Use this to follow emission and fee income over time.

Discovered
network_hashrate

Time series of the Monero network hashrate in H/s, derived from difficulty / 120 s target, bucketed to about 300 points per window. Use this for hashrate trends; for the current value only, use network_info.

Discovered
network_info

Live snapshot of the Monero network right now: node sync status, latest indexed height, difficulty, estimated hashrate and current mempool size. Use this for "what is the state of the network now". For how a metric evolved over time, use network_hashrate, network_blocktime, network_mempool or network_emission instead. Takes no arguments.

Discovered
network_mempool

Time series of the mempool size: number of transactions waiting to be mined. Use this for congestion trends; for the current count only, use network_info. This series is observed live and cannot be rebuilt, so it starts when monitoring began.

Discovered
pool_distribution

Share of blocks mined by each pool over a window, plus the largest pool's share, the top-two combined share and the Nakamoto coefficient (fewest pools controlling over 50% of blocks). Use this to assess mining centralization. Unattributed blocks stay in the denominator but are credited to no pool, so the coefficient is an upper bound. For how each attribution was established, use chain_provenance.

Discovered
pool_sources

Health of each mining-pool API used for block attribution: whether it is reachable and how many blocks it returned. Use this to explain a high unattributed share in pool_distribution. Takes no arguments.

Discovered
price

Current XMR price in one call: the centralized spot (CoinGecko, Kraken fallback) and the Haveno peer-to-peer quote on both sides. Returns the best offer and the amount-weighted average on each side, resting depth, offer counts and round_trip_cost_pct, the cost of buying XMR and selling it straight back (an upper bound, usually far above the headline premium). Use this for "what does XMR cost now". For the premium history use haveno_premium; for individual price levels use haveno_book. Takes no arguments.

Discovered
recent_orphans

Orphan blocks (blocks that lost a fork race) paired with the canonical block that won at the same height, newest first. Use this to list losing blocks and which pool mined them; for whole reorg events (depth, fork point) use reorgs. The default window "all" returns the last N orphans however old.

Discovered
reorg_stats

Summary statistics of reorganizations per period (24h, 7d, 30d, 90d and everything recorded): event count, average and maximum depth, transactions affected, plus the date monitoring began. Use this for "how many reorgs and how deep"; for the individual events use reorgs. Takes no arguments.

Discovered
reorgs

List of individual chain reorganizations detected, most recent first: fork point height, depth in blocks, old and new chain tips, transactions displaced, detection time. Use this to inspect specific reorg events. For counts and depth summaries per period use reorg_stats; for the losing blocks themselves use recent_orphans. Takes no arguments.

Discovered
search_block

Find one block from a height or a hash, anywhere from the genesis block (height 0) to the tip. Returns the same detail as get_block plus is_canonical and, for a height, any orphan blocks competing at that height. Use this when the user gives a height, or when unsure whether a value is a height or a hash. For a range of consecutive blocks use chain_fork_window.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected487 ms19