Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.hyperd-ai/hyperd-mcp

NPM · HYPERD-MCP · SCANNED SEP 20

Pre-trade DeFi intelligence: 24 paid x402 tools incl. 6 synthesis verdicts, USDC on Base.

Available components

0 this week 83 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security99
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 31 of 113 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability78
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 3203 tokens (~110/item across 29 items; 29 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 Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 29 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 29 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.hyperd-ai/hyperd-mcp server?

io.github.hyperd-ai/hyperd-mcp runs locally as an npm package, launched with npx -y hyperd-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · hyperd-mcp

# add to Claude Code
claude mcp add hyperd-ai-hyperd-mcp -- npx -y hyperd-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "hyperd-ai-hyperd-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hyperd-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "hyperd-ai-hyperd-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hyperd-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add hyperd-ai-hyperd-mcp -- npx -y hyperd-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hyperd-ai-hyperd-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "hyperd-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add hyperd-ai-hyperd-mcp --command npx --arg -y --arg hyperd-mcp
# ~/.hermes/config.yaml
mcp_servers:
  hyperd-ai-hyperd-mcp:
    command: "npx"
    args: ["-y", "hyperd-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "hyperd-ai-hyperd-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "hyperd-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add hyperd-ai-hyperd-mcp -t stdio -c npx -a -y hyperd-mcp
// mcp.json
{
  "mcpServers": {
    "hyperd-ai-hyperd-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "hyperd-mcp"
      ]
    }
  }
}
Changelog

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.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 16 Sept 26 0
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 0
    • Security disclosure: unverified → fail functional
  • 13 Sept 26 0
    • Security disclosure: fail → unverified functional
  • 12 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 10 Sept 26 −2
    • Stability: pass → 0.80 functional
Diagnostics

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 20 Sept 2026 · Analysed npm/hyperd-mcp@1.1.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 113 packages
Packages resolved 113
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 29 exposed · ~3,203 tokens

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 →

Tool Tokens
hyperd.balance.get ~128

Get the on-chain balance for an EVM wallet address. Multi-chain (Base, Ethereum, Polygon, Arbitrum). Supports ERC-20 by symbol or contract address. Pass chain='all' for parallel multi-chain lookup. Costs $0.01 in USDC on Base.

NameTypeReqDescription
addressstringyes0x EVM wallet address
chainstringChain. Default 'base'. Use 'all' for parallel multi-chain.
tokenstringToken symbol (e.g., USDC, WETH) or contract address. Default USDC.

No output schema declared.

No examples provided.

hyperd.budget.guardian ~189

Agent spend visibility: aggregates recent outbound USDC transfers from a wallet over a configurable window (1h/24h/7d/30d). Returns total spend, by-destination breakdown, projected-24h rate, and an optional under_cap flag if cap_usd is provided. Use this BEFORE initiating the next paid x402 call to enforce a self-imposed budget. Bridged USDC.e variants are NOT counted. Costs $0.01 in USDC.

NameTypeReqDescription
addressstringyes0x EVM wallet address
cap_usdnumberOptional self-imposed USDC cap. When provided, response includes under_cap, remainingUsd, and anyTxExceedsTenthOfCap.
chainstringChain to compute spend on. Default 'base'.
windowstringLookback window. Default '24h'.

No output schema declared.

No examples provided.

hyperd.bundle ~142

Bundle multiple paid GET calls into one x402 settlement. Up to 10 sub-calls executed in parallel (concurrency cap 4), per-call results returned in a structured envelope. Fixed $0.20 USDC — typically cheaper than à la carte for any combination summing > $0.24 individually. Best-effort execution: failed sub-calls don't refund in v1.0 (credit ledger planned for v1.1). Use this when you need 3+ paid calls and want to save on facilitator round-trips.

NameTypeReqDescription
callsarrayyes1-10 sub-calls. Each must target a bundleable paid GET endpoint.

No output schema declared.

No examples provided.

hyperd.catalog.list ~48

List all available hyperD x402 API endpoints with their prices, descriptions, and example responses. FREE — no wallet required. Use this to discover what tools are available before configuring a wallet.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

hyperd.contract.audit ~90

Pre-trade contract security audit. Composes GoPlus + Sourcify + DefiLlama protocol recognition + on-chain heuristics into a single 0-100 risk score with structured findings. Use BEFORE interacting with any unfamiliar contract. Costs $0.10 in USDC.

NameTypeReqDescription
chainstringChain. Default 'base'.
contractstringyesContract address to audit

No output schema declared.

No examples provided.

hyperd.dex.quote ~137

Get the best DEX swap route across multiple aggregators (Paraswap + 0x). Returns the highest output amount and per-source quotes. Costs $0.02 in USDC.

NameTypeReqDescription
amountstringyesDecimal amount of source token
chainstringChain. Default 'base'.
fromstringyesSource token symbol or contract address
slippageintegerMax slippage in basis points. Default 50.
takerstringOptional payer address for 0x quote (improves accuracy)
tostringyesDestination token symbol or contract address

No output schema declared.

No examples provided.

hyperd.gas.estimate ~52

Get current gas price + base fee + tip percentiles for fast/standard/slow inclusion. Costs $0.005 in USDC.

NameTypeReqDescription
chainstringChain. Default 'base'.

No output schema declared.

No examples provided.

hyperd.gov.translate ~100

Composed DAO governance translator. Takes a Snapshot or Tally proposal URL, fetches structured data via /api/governance/summarize, then produces a 2-3 sentence plain-language translation + domain band (economic_param / treasury / code_upgrade / governance_meta / social_signal). 1-year cache — proposals are immutable. Costs $1.00 in USDC.

NameTypeReqDescription
proposal_urlstringyesSnapshot or Tally proposal URL

No output schema declared.

No examples provided.

hyperd.governance.summarize ~71

Summarize a DAO governance proposal (Snapshot or Tally URL). Returns structured impact analysis: who benefits, who pays, recommended position. LLM-summarized. Costs $0.10 in USDC.

NameTypeReqDescription
proposal_urlstringyesSnapshot or Tally proposal URL

No output schema declared.

No examples provided.

hyperd.health.check ~48

Check the health of the hyperD API: which network it's on, whether the payment facilitator is configured, which optional backend keys are wired, and cache stats. FREE — no wallet required.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

hyperd.liquidation.risk ~109

Cross-protocol liquidation risk for a wallet's lending positions. Health factor, USD-at-risk, and recommendations across Aave V3, Compound v3, Spark Lend, and Morpho Blue. Pass chain='all' for cross-chain aggregate. Costs $0.10 in USDC.

NameTypeReqDescription
addressstringyes0x EVM wallet address
chainstringChain to check, or 'all' for cross-chain aggregate. Default 'base'.

No output schema declared.

No examples provided.

hyperd.pricing.get ~35

Get the current price list for all hyperD paid endpoints (in USDC on Base). FREE — no wallet required.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

hyperd.protocol.tvl ~106

Get a DeFi protocol's TVL, audits, chain distribution from DefiLlama. Pass slug for detail (e.g., 'aave', 'morpho-blue') or list=true for top 50. Costs $0.01 in USDC.

NameTypeReqDescription
listbooleanIf true, returns top 50 protocols by TVL
slugstringProtocol slug, e.g., 'aave' or 'morpho-blue'

No output schema declared.

No examples provided.

hyperd.risk.full_audit ~113

Composed wallet risk verdict. Fans out to balance, wallet_risk, wallet_persona, contract_audit, and privacy_mixer_risk then returns a Haiku 4.5-authored summary + confidence + band (safe / moderate / elevated / critical). One verdict replaces a manual 5-call audit walk. Costs $0.35 in USDC.

NameTypeReqDescription
addressstringyes0x EVM wallet address
chainstringChain. Default 'base'.

No output schema declared.

No examples provided.

hyperd.sentiment.token ~93

Get a token's sentiment score (0-100) from recent Farcaster discussion. Returns score, band (very_negative to very_positive), volume, trend, sample casts. Costs $0.05 in USDC.

NameTypeReqDescription
tokenstringyesToken symbol or name
windowstringDays (1-30) or "24h" / "7d". Default "24h".

No output schema declared.

No examples provided.

hyperd.token.archetype ~93

Composed token classification. Fans out to token_info, token_security, and protocol_tvl then returns a single archetype (stablecoin / blue_chip / mid_cap / memecoin / wrapped / governance / unverified) plus a plain-language verdict. Costs $0.30 in USDC.

NameTypeReqDescription
chainstringChain. Default 'base'.
contractstringyesToken contract address

No output schema declared.

No examples provided.

hyperd.token.info ~113

Get aggregated token metadata: market cap, supply, contract addresses across chains, recent volume. One call replaces multiple CoinGecko / Etherscan / DefiLlama lookups. Costs $0.01 in USDC.

NameTypeReqDescription
chainstringChain when using contract. Default 'base'.
contractstringContract address (alternative to query)
querystringSymbol, name, or coingecko id (e.g., 'USDC' or 'usd-coin')

No output schema declared.

No examples provided.

hyperd.token.security ~95

Get a token's security risk score (0-100). Ensemble of GoPlus signals: honeypot detection, owner permissions, holder concentration, buy/sell taxes, source verification. Returns score, band (safe/caution/warning/danger), and structured findings. Costs $0.05 in USDC.

NameTypeReqDescription
chainstringChain. Default 'base'.
contractstringyesToken contract address

No output schema declared.

No examples provided.

hyperd.wallet.anomaly ~134

Wallet behavioral anomaly detection. Compares recent activity against the wallet's own 180-day baseline — surfaces tx-volume spikes, dormant-wakeup patterns, new-protocol interactions, counterparty diversification. Catches compromised hot wallets, dormant whales, MEV-bot strategy shifts. Costs $0.10 in USDC.

NameTypeReqDescription
addressstringyes0x EVM wallet address
chainstringChain to analyze. Default 'base'.
windowstringRecent activity window. "24h", "7d", "30d", or bare integer days. Default "24h".

No output schema declared.

No examples provided.

hyperd.wallet.persona ~102

Classify a wallet's persona based on on-chain behavior. Returns one of: Trader, HODLer, MEV-bot, Whale, Smart-Money, Airdrop-Farmer, Compromised, Inactive — plus confidence and supporting signals. Costs $0.10 in USDC.

NameTypeReqDescription
addressstringyes0x EVM wallet address
chainstringChain to analyze. Default 'base'.

No output schema declared.

No examples provided.

hyperd.wallet.pnl ~232

Realized + unrealized P&L for a wallet over a time window. ERC-20 + native, single chain per call. Three cost-basis methods: FIFO (default, IRS standard), LIFO (last-in-first-out), HCFO (highest-cost-first-out, tax-loss-harvesting view). Per-token breakdown with weighted-avg cost + mark-to-market. Unpriced trades and untracked-proceeds gaps surfaced honestly under coverage.* fields. v1.0 defers per-tx gas-fee USD attribution. Costs $0.05 in USDC.

NameTypeReqDescription
addressstringyes0x EVM wallet address
chainstringChain to compute P&L on. Default 'base'.
fromintegerWindow start, unix seconds. Default = to - 30 days. Must be >= 1577836800 (2020-01-01).
methodstringCost-basis method. Default 'fifo'.
tointegerWindow end, unix seconds. Default = now. Cannot be > now+60.

No output schema declared.

No examples provided.

hyperd.wallet.risk ~108

Check a wallet's risk profile. Combines Chainalysis Sanctions Oracle (OFAC SDN authoritative) with GoPlus address heuristics (mixers, phishing, scams). Returns sanctioned flag + 0-100 heuristic score. Costs $0.10 in USDC.

NameTypeReqDescription
addressstringyes0x EVM wallet address
chainstringChain. Default 'base'.
deepbooleanCross-check across multiple chains. Default false.

No output schema declared.

No examples provided.

hyperd.wallet.thesis ~102

Composed wallet behavioral thesis. Fans out to balance, wallet_persona, wallet_pnl, and wallet_anomaly then returns a plain-language summary of the wallet's investing posture plus archetype (trader / hodler / yield_farmer / mev_bot / compromised / inactive). Costs $0.50 in USDC.

NameTypeReqDescription
addressstringyes0x EVM wallet address
chainstringChain. Default 'base'.

No output schema declared.

No examples provided.

hyperd.wallet.threat_brief ~111

Composed wallet threat brief. Fans out to wallet_risk, wallet_anomaly, privacy_mixer_risk, budget_guardian, and wallet_persona then returns a 2-3 sentence security verdict + band (clean / watch / elevated / critical). Replaces a manual 5-call security audit walk. Costs $1.50 in USDC.

NameTypeReqDescription
addressstringyes0x EVM wallet address
chainstringChain. Default 'base'.

No output schema declared.

No examples provided.

hyperd.watch.cancel ~76

Cancel a watch you own. $0.001 USDC ops fee covers the x402 auth path. Returns 404 (not 403) if the watch_id doesn't exist OR if you're not the owner — no existence-leak side-channel.

NameTypeReqDescription
watch_idstringyesThe watch_id returned from hyperd.watch.create.

No output schema declared.

No examples provided.

hyperd.watch.create ~240

Subscribe to a continuous watch on a wallet/position. Returns watch_id and webhook_secret (shown ONCE — store it; we cannot recover it). HMAC-SHA256 signed alerts POSTed to your webhook_url when threshold conditions are met. v1.0 supports liquidation watches across Aave V3 / Compound v3 / Spark / Morpho. $3.00 USDC prepays for duration_days (default 30, max 90).

NameTypeReqDescription
duration_daysintegerWatch lifetime in days. Default 30, max 90.
fire_on_band_or_worsestringFire when health-factor band reaches this severity OR worse. Default 'warning'.
target_addressesarrayyesWallet to watch (length-1 in v1.0; multi-target reserved for v1.1 Pro tier).
target_chainstringChain to watch. Default 'base'.
typestringyesWatch type. v1.0 only supports 'liquidation'.
webhook_urlstringyesHTTPS endpoint to POST alerts to. Must be publicly reachable; private/loopback IPs rejected.

No output schema declared.

No examples provided.

hyperd.watch.list ~64

List the active watches owned by your wallet. $0.001 USDC ops fee — covers the x402 auth path that proves wallet ownership (without it, the server can't tell which wallet is asking). webhook_secret is NEVER returned — store it from the create response.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

hyperd.yield.allocation ~129

Composed yield allocation recommender. Fans out 3 parallel /api/yield calls at low/medium/high risk tiers for the same amount + duration, then returns a recommended portfolio split + 2-sentence rationale. Bands: conservative / balanced / aggressive / bespoke. 6h cache bucketed by amount tier × duration × chain. Costs $1.00 in USDC.

NameTypeReqDescription
amountnumberyesUSDC equivalent to allocate
chainstringChain filter. Default 'base'.
durationintegerInvestment horizon in days. Default 30.

No output schema declared.

No examples provided.

hyperd.yield.recommend ~143

Get an opinionated DeFi yield recommendation. Filters DefiLlama's pool universe by risk tier (low/medium/high), TVL, and IL exposure, then ranks by APY. Returns the top picks plus projected $ yield over your duration. Costs $0.05 in USDC.

NameTypeReqDescription
amountnumberyesUSD amount to invest
chainstringOptional chain filter (e.g., 'base')
durationintegerInvestment duration in days. Default 30.
riskstringyesRisk tolerance
stablesbooleanStablecoins-only filter. Default false (true for low risk).

No output schema declared.

No examples provided.

Common questions

What is the io.github.hyperd-ai/hyperd-mcp server?

io.github.hyperd-ai/hyperd-mcp is listed in the public MCP registry as io.github.hyperd-ai/hyperd-mcp. Pre-trade DeFi intelligence: 24 paid x402 tools incl. 6 synthesis verdicts, USDC on Base. This page covers its npm package (hyperd-mcp).

Is the io.github.hyperd-ai/hyperd-mcp server safe to use?

io.github.hyperd-ai/hyperd-mcp scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 io.github.hyperd-ai/hyperd-mcp server expose?

io.github.hyperd-ai/hyperd-mcp exposes 29 tools: hyperd.catalog.list, hyperd.pricing.get, hyperd.health.check, hyperd.balance.get, hyperd.yield.recommend, and 24 more. Their descriptions and schemas cost roughly 3,203 tokens of context every time the server is loaded.

Is the io.github.hyperd-ai/hyperd-mcp server still maintained?

io.github.hyperd-ai/hyperd-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.hyperd-ai/hyperd-mcp server under?

io.github.hyperd-ai/hyperd-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.