MCP.Market

Teardrop MCP server

online · 100% uptime
by HASAVAGE·io.github.HASAVAGE/teardrop·v1.0.0

Teardrop MCP gateway: paid tools for autonomous agents (x402, credits).

A85/100grade A
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed Teardrop yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Teardrop tools (35)

write = sends, deletes, buys or posts
  • assess_counterparty_riskFree

    Return a decision-ready counterparty-risk verdict for an EVM address before funds or authority are committed. The result branches to high_risk, caution, acceptable, or insufficient_data with the evidence needed for the calling agent to act. Use when: Delegate this check before sending funds, granting approvals, or interacting with an unknown EVM address when the caller needs a bounded risk decision. Limitations: Analytics and heuristic risk assessment; not a credit bureau, fraud guarantee, or legal endorsement. Relies on DeBank indexing and on-chain Aave/Compound contract states. Alternatives: get_wallet_approvals, get_liquidation_risk, get_wallet_positions

  • assess_market_resolutionFree

    Return a decision-ready resolution-risk verdict for one Polymarket market before an agent trades, quotes, or forecasts it. The result branches to tradeable, ambiguous, avoid, or insufficient_data and names the resolution basis (price_feed, official_source, media_consensus, unspecified), UMA dispute state, rule-wording risks, and executability (liquidity, spread) so the calling agent can act without reading the full rules. Use when: Call once per market before placing, quoting, or forecasting a Polymarket position when the caller needs to know whether the rules and resolution state make the outcome well-defined. Repeat calls within two minutes return cached data. Limitations: Heuristic analysis of Polymarket rule wording and Gamma API state; not a probability forecast, legal advice, or a guarantee of how UMA voters resolve. Does not read order-book depth, event-level augmented negative-risk settings, or clarifications published off-platform. Alternatives: web_search, http_fetch

  • calculateFree

    Evaluate a safe arithmetic expression and return the numeric result. Supports +,-,*,/,**,%,sqrt,abs,round,floor,ceil,log,sin,cos,tan,pi,e. Use for derived figures (ratios, differences, percentages) that no tool output already provides. Use when: Use when an agent must derive a value that tool outputs do not already include, such as a ratio, spread, or percentage. Do not use to re-derive pre-computed fields like std_30d or dca_baseline_90d that get_token_price_historical returns. Limitations: Arithmetic only — no aggregation over tool history, no unit conversion, and no financial modeling beyond the listed functions. Errors return an error field rather than raising. Alternatives: get_token_price_historical, get_datetime

  • convert_currencyFree

    Convert an amount between fiat currencies (USD, EUR, GBP) and crypto assets (BTC, ETH, USDC, SOL) and return the converted amount plus the exchange rate used. Use when: Use when an amount must be expressed in a different currency than the source data — for example converting a USD portfolio value into EUR, or a fiat amount into its crypto equivalent. For prices only, get_token_price returns the rate directly without a second call. Limitations: Spot-rate conversion at request time; no historical or forward rates, and no slippage or fee modeling. Actual swap execution differs — use get_dex_quote for executable on-chain quotes. Alternatives: get_token_price, get_dex_quote

  • count_text_statsFree

    Return word, character, sentence, and paragraph counts plus average words per sentence for a given text, for length checks and content sizing decisions. Use when: Use when output length must be validated or reported — e.g. verifying a summary meets a length contract or comparing document sizes. Do not use for semantic summarization; it counts only. Limitations: Pure counting on the provided text — no language detection, no reading-level or sentiment analysis, and no retrieval of external content. Alternatives: web_search, http_fetch

  • decode_transactionFree

    Decode a transaction's calldata into a human-readable function name and arguments, and return transaction status (1=success, 0=revert), gas used, and block number. Uses a supplied ABI when provided, otherwise 4byte.directory. Supports Ethereum mainnet and Base. Use when: Use when one known transaction must be explained — what function was called, with what arguments, and whether it succeeded. For wallet-wide activity patterns use get_wallet_history instead. Limitations: 4byte.directory matching can be ambiguous or absent for custom contracts; supply an ABI for precise decoding. One transaction per call; Ethereum mainnet and Base only. Alternatives: get_transaction, get_wallet_history

  • delegate_to_agentFree

    Delegate a task to a remote A2A-compliant agent: discover its capabilities via its agent card, send it a message, handle payment, and return the result. Use only when no local platform tool can fulfil the request. Use when: Use when a task requires specialist capabilities beyond the local tool set. Call discover_agents first when the remote agent URL is unknown. Do not retry unchanged after error_type=advertised_price_exceeds_cap; pick another result or adjust the cap. Limitations: Requires an allowlisted remote URL and sufficient delegation budget; the remote agent's price and capability claims are read from its card and are not independently verified. Involves real payment. Alternatives: discover_agents, web_search

  • discover_agentsFree

    Find opt-in remote A2A agents, published tool capabilities, endpoints, and public reputation status. Use when: Use before delegate_to_agent when a specialist agent is needed but its URL is unknown. Limitations: Discovery is read-only and does not add an agent to the org allowlist; delegate_to_agent remains authoritative. Alternatives: delegate_to_agent

  • get_blockFree

    Get block details (timestamp, gas used, base fee, miner, transaction count) for an Ethereum or Base block by number, hash, or 'latest'. Use to anchor events to a point in chain time. Use when: Use when a question depends on when a block occurred, how full it was, or its base fee — for example dating a transaction or checking congestion at a specific height. For current fee levels use get_gas_price instead. Limitations: One block per call; Ethereum mainnet and Base only. Historical base fee data depends on RPC node retention for older heights. Alternatives: get_transaction, get_gas_price

  • get_chain_metricsFree

    Compare blockchain ecosystem health via DeFiLlama: current TVL, 7/30-day TVL change, and aggregate fee activity. Pass chains such as ['Ethereum', 'Arbitrum', 'Solana'] for a focused comparison, or omit chains to inspect the highest-TVL ecosystems. Use when: Use for ecosystem-level comparisons — which chains are growing, where fee activity concentrates, or how a chain's TVL trended. For a single protocol's economics use get_protocol_tvl instead. Limitations: Third-party DeFiLlama analytics; historical and fee fields fail open (null) for uncovered chains. Not a real-time measure of chain throughput or security. Alternatives: get_protocol_tvl, get_dex_volume

  • get_datetimeFree

    Return the current UTC date and time as a formatted string and ISO 8601 timestamp, for grounding time-relative reasoning in the actual clock rather than training-data assumptions. Use when: Use when a task must anchor on the current date or time — computing ages, windows, deadlines, or 'as of today' context. The runtime context block already states the date, so call this only when a specific strftime format or a precise timestamp is needed. Limitations: UTC only — no timezone conversion. An unsupported strftime format silently falls back to the default format instead of erroring. Alternatives: calculate, get_block

  • get_defi_positionsFree

    Block-accurate DeFi positions for a wallet across Aave v3, Compound v3, Uniswap v3 LP, and Lido on Ethereum or Base. Returns Aave account health (collateral, debt, health factor, LTV) with per-reserve breakdown, Compound v3 market positions, Uniswap v3 LP positions by token ID, and on Ethereum the Lido stETH/wstETH balances with the current wstETH-to-stETH equivalent. Per-protocol failures are isolated — other protocols still return. Use when: Use when a block-accurate single-wallet protocol snapshot is needed, including health factor and LP position detail. For broad all-chain discovery or net worth across many protocols use get_wallet_positions instead. Limitations: On-chain RPC view of four protocol families on Ethereum and Base only; does not discover wallets' unknown or long-tail protocol positions. Compound v3 reports only a boolean liquidation flag — never state a numeric Compound health factor. Errors list which protocols were unavailable. Alternatives: get_wallet_positions, get_liquidation_risk, get_wallet_portfolio

  • get_dex_quoteFree

    Get the best Uniswap v3 swap quote on Ethereum (chain_id=1) or Base (chain_id=8453) via direct on-chain QuoterV2 calls. Queries all four fee tiers (100/500/3000/10000 bps) in parallel and returns the tier with the highest output amount, along with per-tier breakdown. Inputs are raw uint256 amounts and EIP-55 checksummed addresses; native ETH is not quoted directly — pass the WETH address. Returns no_liquidity=true when no pool exists for the pair. Point-in-time quote at the returned block_number; do not cache. Use when: Choose when you need a best-execution Uniswap v3 swap quote on Ethereum or Base before executing a trade — e.g. price impact, output amount, or route selection. Limitations: Quotes raw uint256 amounts with EIP-55 checksummed addresses only; native ETH is not quoted directly (pass WETH). Point-in-time at the returned block_number — do not cache. Alternatives: get_token_price, get_dex_volume

  • get_dex_volumeFree

    Compare decentralized exchange activity via DeFiLlama: 24h/7d/30-day volume, period-over-period changes, and each protocol's share of reported global 24-hour DEX volume. Filter by protocol and rank by a 1-, 7-, or 30-day lookback window. Use when: Use for landscape questions — which DEXs dominate volume, how activity shifted week-over-week, or a specific protocol's relative share. For executable swap pricing use get_dex_quote instead. Limitations: Third-party DeFiLlama reporting, not on-chain truth; coverage gaps understate smaller protocols. 24-hour share is computed against the unfiltered global total, so filtered results retain landscape context. Alternatives: get_dex_quote, get_chain_metrics

  • get_erc20_balanceFree

    Get the exact on-chain ERC-20 balance of a wallet for one token contract, normalized by decimals and returned with the token's symbol. Use for a precise single-token check. Use when: Use when a specific token contract's balance must be verified block-accurately — e.g. confirming funds before an approval or transfer. For a multi-asset portfolio view use get_wallet_portfolio instead. Limitations: One token contract per call on Ethereum or Base; the contract address is required, so unknown tokens cannot be looked up by symbol. Returns raw balance data only — no USD valuation. Alternatives: get_wallet_portfolio, get_eth_balance

  • get_eth_balanceFree

    Get the exact on-chain native ETH balance of an address on Ethereum or Base, in wei and ether. get_wallet_portfolio already includes native ETH in its holdings — call this only for a standalone balance without a portfolio scan. Use when: Use when a wallet's gas-availability or standalone ETH amount must be verified block-accurately. Do not call after or alongside get_wallet_portfolio — the holdings list already includes native ETH. Limitations: Native ETH only; ERC-20 balances require get_erc20_balance. Requires an EIP-55 checksummed address. Ethereum mainnet and Base only. Alternatives: get_wallet_portfolio, get_erc20_balance

  • get_gas_priceFree

    Get current EIP-1559 gas fees on Ethereum or Base: base fee, priority fee, next-block base fee estimate, and congestion (gas_used_ratio >0.5 busy, >0.9 very congested). Optional USD estimates cover a simple transfer and a swap-like transaction. Cached 10 seconds per chain. Use when: Use before advising a transaction — to time execution, size a gas budget, or judge congestion. Call once per decision; the 10-second cache makes rapid re-calls pointless. Limitations: Point-in-time estimate that changes every block; USD figures are rough heuristics at 21k/150k gas, not an execution quote. Ethereum mainnet and Base only. Alternatives: get_block, get_dex_quote

  • get_lending_ratesFree

    Get current on-chain lending supply/borrow APYs for Aave v3 reserves and Compound v3 markets on Ethereum or Base, with per-asset snapshots and Compound utilization. Use for protocol-specific yield comparisons such as USDC on Aave vs Compound. Use when: Use for protocol-specific lending-rate questions (e.g. 'Aave vs Compound USDC rates'). Prefer over get_yield_rates when the protocols are known; use get_yield_rates for broad pool discovery across many protocols. Do not fall back to web_search when this returns errors — report them. Limitations: On-chain snapshots of Aave v3 and Compound v3 on Ethereum and Base only; not a multi-protocol yield aggregator. Rates are point-in-time and change per block. Returns an errors list — report each unavailable protocol explicitly and treat empty rates with empty errors as transient RPC unavailability. Alternatives: get_yield_rates, get_defi_positions, get_liquidation_risk

  • get_liquidation_riskFree

    Assess DeFi liquidation risk for up to 50 wallets across Aave v3 and Compound v3 on Ethereum or Base. Returns per-wallet health factor, tiered risk classification (liquidatable, critical, warning, caution, healthy, no_debt), and an overall_tier aggregate. Per-protocol failures are isolated — one protocol's RPC error does not blank the other's result. Use when: Use for multi-wallet batch risk assessment (2+ wallets). For a single-wallet DeFi analysis use get_defi_positions, which already includes risk metrics. Use assess_counterparty_risk when the question is counterparty trust rather than position health. Limitations: View-only scan of Aave v3 and Compound v3 on Ethereum and Base with hardcoded market addresses; not a liquidation simulation or guarantee. Compound v3 exposes only a boolean liquidation flag — no numeric health factor. Duplicate wallet addresses are silently removed. Alternatives: get_defi_positions, assess_counterparty_risk, get_wallet_positions

  • get_protocol_tvlFree

    Get Total Value Locked for one or many DeFi protocols from DeFiLlama: current USD TVL, 7/30-day change, fees and revenue when reported, per-chain breakdown, and optional daily historical series. Batch multiple protocols via protocols=[...] — batch responses return one compact economic summary per protocol; single-protocol calls add chain and historical detail. Supports 3,000+ protocols; use DeFiLlama slugs ('aave-v3', 'uniswap-v3'); common aliases are auto-corrected. Use when: Use for protocol-level economic questions — size, growth, fees, or revenue of a specific protocol. For 2+ protocols always batch in one call rather than calling per-protocol. Pass include_historical=true with days when a trend is needed; without it the response is a current TVL scalar. For ecosystem-level chain comparisons use get_chain_metrics instead. Limitations: Third-party DeFiLlama analytics, not on-chain truth. Upstream revenue failures surface as revenue_error_type and null economic fields are data gaps — never fabricate values for them. Alternatives: get_chain_metrics, get_yield_rates, get_dex_volume

  • get_token_approvalsFree

    Block-accurate audit of ERC-20 allowances for a wallet across curated DeFi spenders (Uniswap, Aave, Compound, 1inch, 0x, OpenSea) on Ethereum or Base. Flags unlimited approvals by risk level (high=unknown spender, medium=trusted protocol, low=bounded). Use before swaps or after security incidents to detect active exploit vectors. Use when: Use for a free, block-accurate Ethereum/Base check of an address's exposure to the curated spender list. For broad all-chain spender discovery, hacked/abandoned flags, or NFT-adjacent exposure use get_wallet_approvals instead. Limitations: Covers only the tracked-asset registry and curated spenders — untracked tokens and custom spenders are excluded. Does not inspect NFT approvals or off-chain Permit2 sub-permits. An error field marks results as incomplete rather than clean. Alternatives: get_wallet_approvals, assess_counterparty_risk

  • get_token_priceFree

    Get current price, 24h change, market cap, FDV, and volume for one or more crypto tokens. Accepts ticker symbols, full names, or CoinGecko IDs; unknown symbols resolve automatically. Batch up to 50 tokens. Reuse price_usd/value_usd already returned by get_wallet_portfolio instead of re-calling. Use when: Use for spot pricing of named tokens — including batched multi-token queries. Do not call for tokens whose price get_wallet_portfolio already returned, or for address-only unknown tokens (report them as unrecognized). For historical windows use get_token_price_historical. Limitations: CoinGecko spot data; point-in-time and not an executable swap quote. Bare 0x addresses are not resolvable and should be treated as unknown tokens. Alternatives: get_token_price_historical, get_wallet_portfolio, get_dex_quote

  • get_token_price_historicalFree

    Get historical crypto prices over a 1–365 day window: period statistics (start, end, % change, high, low), a downsampled daily series, high_30d, std_30d, and dca_baseline_90d. Use for period comparisons and trend analysis; prefer over web_search for time-comparative financial queries. Pass stats_only=true when the daily series is unnecessary. Use when: Use for time-comparative financial questions — month-over-month, YTD, volatility, or DCA baselines. Prefer over web_search for such queries. Use the pre-computed stats directly; do not re-derive them with calculate. Limitations: Daily granularity (downsampled), max 365-day window, CoinGecko coverage only. Check dca_baseline_90d_partial before relying on the baseline — incomplete history yields a partial baseline. Alternatives: get_token_price, web_search

  • get_transactionFree

    Get details and receipt for one Ethereum or Base transaction by hash: bounded calldata, normalized event logs, transaction index, and receipt-derived effective gas price and fee when available. Use to verify a specific transaction's status and outcome. Use when: Use when one known transaction must be verified — status, logs, gas paid, or execution outcome. To understand what the calldata means use decode_transaction; for wallet-wide activity use get_wallet_history. Limitations: One transaction hash per call on Ethereum or Base; pending transactions may not resolve yet. Calldata is returned bounded, not decoded — use decode_transaction for semantic decoding. Alternatives: decode_transaction, get_block, get_wallet_history

  • get_wallet_approvalsFree

    Inspect a wallet's current ERC-20 token authorization exposure on one DeBank-supported chain. Returns discovered spenders, USD exposure, protocol attribution, and hacked or abandoned protocol flags. This is broader than the curated block-accurate get_token_approvals tool. Use when: Use when broad spender discovery or cross-chain security screening is needed. Call once per chain because DeBank requires a chain_id. Use get_token_approvals for a free, block-accurate Ethereum or Base scan of curated tokens and spenders. Limitations: The result is third-party analytics and may be stale. It covers token approvals only, not NFT approvals or off-chain Permit2 sub-permits; each chain consumes a separate billable provider call. Alternatives: get_token_approvals

  • get_wallet_historyFree

    Get one page of decoded transaction history for an EVM wallet across DeBank-supported chains. Returns send, receive, and approval categories with protocol, token, exchange, gas, and USD metadata. Use the returned next_cursor as start_time to page backward. Use when: Use for wallet activity discovery, protocol interaction history, exchange exposure, and gas analysis. Page backward with next_cursor for older activity. Use get_transaction or decode_transaction when one known transaction needs block-level details. Limitations: DeBank returns at most 20 entries per call and the data may be stale. This tool is not a complete ledger, PnL engine, or cost-basis calculator because historical execution prices and all transfer semantics are not guaranteed. Alternatives: get_transaction, decode_transaction

  • get_wallet_portfolioFree

    Get aggregated token holdings with USD values for a wallet address. Tracks 19 major assets on Ethereum and 12 on Base, including spot, lending, liquid-staking, restaking, and stablecoin assets. Sorted by USD value. Returns up to 20 holdings. Includes native ETH balance in the holdings list — calling get_eth_balance separately after this is redundant. Use when: Choose when you need a wallet's overall token exposure and USD value on Ethereum or Base in one call. Call once per chain for a cross-chain comparison. Limitations: Tracks a fixed set of major assets per chain, not arbitrary tokens. Returns up to 20 holdings. Native ETH is included, so calling get_eth_balance separately is redundant. Alternatives: get_eth_balance, get_token_price, get_defi_positions

  • get_wallet_positionsFree

    Get a wallet's DeFi positions across all DeBank-supported chains and protocols. Returns protocol-level positions, asset/debt/net USD values, optional token lists, aggregate exposure, and optional all-chain net worth. Set include_token_balances=true to also return DeBank's complete cross-chain wallet token list. Set include_token_lists=false for a compact balance and debt summary without nested position tokens. This covers substantially more protocols and chains than the block-accurate get_defi_positions tool. Use raw-RPC tools for liquidation, swap quotes, or other transaction-critical questions. Use when: Use for broad wallet discovery, portfolio allocation, protocol exposure, or cross-chain position questions. Set include_token_balances=true when complete wallet token discovery is required; otherwise the response only includes tokens attached to protocol positions. Set include_token_lists=false when only protocol balances, debt, or aggregate exposure are needed. Use get_defi_positions when the user needs a block-accurate Aave, Compound, Uniswap, or Lido snapshot. Limitations: DeBank portfolio data is third-party analytics and may be stale, including occasional long refresh delays. It is read-only, EVM wallet oriented, and does not prove current liquidation or execution state. include_token_balances adds a separate billable DeBank request; include_token_lists only changes response detail. Alternatives: get_defi_positions, get_wallet_portfolio, get_token_approvals

  • get_yield_ratesFree

    Get DeFi yield pool rates from DeFiLlama across 1,000+ protocols and all chains: pools sorted by APY with TVL, base/reward APY, and 7d/30d mean APY context, filterable by protocol, chain, min TVL, min/max APY, and symbol. Returns up to 50 pools. For protocol-specific lending comparisons (Aave vs Compound) prefer get_lending_rates. Use when: Use for broad cross-protocol yield discovery. Call at most once per request — filter with min_apy, max_apy, min_tvl_usd, and symbols_any in a single call, then sort client-side rather than re-calling. For protocol-specific rate questions use get_lending_rates. Limitations: Third-party DeFiLlama analytics; up to 50 pools per call. The `symbol` field lists underlying tokens (e.g. 'ETH-USDC') — filter client-side instead of re-calling with different arguments. Reward APY indicates reward-dependent yield; do not present spot APY as durable. Alternatives: get_lending_rates, get_protocol_tvl, get_token_price

  • http_fetchFree

    Fetch a web page and return its main text content, cleaned of markup. Use to read articles, documentation, and other resources referenced by URL. Blocks private and cloud-metadata addresses and re-validates every redirect hop. Use when: Use when a known URL's content is needed and structured tools cannot answer — e.g. reading a linked document or API docs. For general factual lookup prefer web_search; for token prices prefer get_token_price. Limitations: Read-only GET-style extraction returning cleaned text, not raw HTML or binary content. JS-heavy pages may yield little content; private/internal network targets are deliberately unreachable. Alternatives: web_search, get_token_price

  • read_contractFree

    Call any view/pure function on a smart contract and return the decoded result, using a supplied ABI fragment. Supports historical reads via block_identifier and caller_address context for msg.sender-dependent views. Read-only: state-changing functions are rejected. Use when: Use when a protocol question needs a contract read that no higher-level tool covers — e.g. a niche view function or a protocol outside the standard tool set. Prefer purpose-built tools (get_defi_positions, get_lending_rates) for supported protocols. Limitations: Requires a valid ABI fragment; payable/nonpayable functions are rejected. Ethereum mainnet and Base only, with bounded RPC timeout and retry. Alternatives: get_defi_positions, get_lending_rates, get_token_approvals

  • record_predictionsFree

    Record a complete structured prediction document for downstream evaluation. Call once with the exact machine-readable prediction; the human-readable report is provided separately. Use when: Use at the end of a scheduled analysis run to persist the machine-readable prediction for later scoring. Call exactly once with the complete prediction document — never partially or repeatedly. Limitations: Internal sink for scheduled analysis, not a caller-facing marketplace tool. Stores the prediction as given; no validation of prediction quality or deduplication across calls. Alternatives: get_datetime

  • resolve_ensFree

    Resolve an ENS name (e.g. 'vitalik.eth') to an Ethereum address, or an address to its primary ENS name, with avatar text record when available. Mainnet only. Use when: Use only when no 0x address is available and a name must become an address (or vice versa for attribution). If a 0x address is already present in the task or session, use it directly — resolution is redundant and adds latency. Limitations: Ethereum mainnet ENS only — no other chains or naming services. Reverse records are optional on ENS, so a valid address may legitimately have no primary name. Alternatives: get_wallet_portfolio, get_wallet_history

  • validate_opportunityFree

    Return a decision-ready yield-opportunity verdict before capital is deployed. The result branches to sustainable, caution, unsustainable, or insufficient_data and gives the calling agent the evidence needed to proceed, pause, or reject the opportunity. Use when: Delegate this check before deploying capital into a DeFi yield pool or staking opportunity when the caller needs an independent sustainability and liquidity decision. Limitations: Heuristic economic assessment based on DeFiLlama analytics and CoinGecko pricing. Does not audit smart contract bytecode, protocol governance, or admin key security. Alternatives: get_yield_rates, get_protocol_tvl, get_lending_rates, assess_counterparty_risk

  • web_searchFree

    Real-time web search via Tavily for current events, fact-checking, and research. Use search_depth='advanced' for complex queries (higher quality, higher cost) and topic='news' or 'finance' for headlines or market information. Use when: Choose when the task needs current, external, or factual information not available from on-chain or local data — e.g. news, prices, documentation, or fact-checking. Limitations: Returns web snippets, not raw page bodies; results depend on Tavily coverage. Advanced depth costs more. Not a substitute for on-chain tools like get_token_price. Alternatives: get_token_price, http_fetch

Public scan report

scanner v0.1.10 · 2026-10-13 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1247ms20/20
  • Tool poisoning35 tool descriptions checked15/15
  • Auth qualityopen endpoint, read-only tools10/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identitynamespace and repository owner differ4/10
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Teardrop compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
85/100
higher than 70% of 48,255 servers
Tools
35
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Uptime
100%
of our recent checks; the typical remote server answers 100%
Response time
582 ms
faster than 25% of 30,031 servers

What its tools let an agent do: 35 read

Install Teardrop in Claude Code, Cursor or VS Code

claude mcp add --transport http teardrop https://api.teardrop.dev/tools/mcp
Add to Cursor

What the publisher says

From the Teardrop repository's README, as published. We do not edit it. Read it on GitHub

████████╗███████╗ █████╗ ██████╗ ██████╗ ██████╗  ██████╗ ██████╗
╚══██╔══╝██╔════╝██╔══██╗██╔══██╗██╔══██╗██╔══██╗██╔═══██╗██╔══██╗
   ██║   █████╗  ███████║██████╔╝██║  ██║██████╔╝██║   ██║██████╔╝
   ██║   ██╔══╝  ██╔══██║██╔══██╗██║  ██║██╔══██╗██║   ██║██╔═══╝
   ██║   ███████╗██║  ██║██║  ██║██████╔╝██║  ██║╚██████╔╝██║
   ╚═╝   ╚══════╝╚═╝  ╚═╝╚═╝  ╚═╝╚═════╝ ╚═╝  ╚═╝ ╚═════╝ ╚═╝

Teardrop is a streaming API for applications and software agents to run tool-using AI workflows. Clients submit a message or task; Teardrop orchestrates a configured LLM (Anthropic, OpenAI, Google, or OpenRouter) and available tools, then streams structured results and UI events over Server-Sent Events (SSE). It supports AG-UI for streaming interaction, A2A for agent discovery and delegation, MCP for tool access, and optional x402 pay-per-request USDC settlement on Base.

Core Features

Agent-to-Agent (A2A) Delegation

Agents can discover opt-in specialists with the zero-cost discoveragents tool, including active published tool names, and securely delegate tasks via delegatetoagent (both invoked during /agent/run). Features include allowlist control, JWT forwarding, per-run quotas, destination cost caps, optional advertised atomic-USDC task prices, and optional credit billing with org-level and caller-principal pause/24-hour spend-limit enforcement. A price above the effective allowlist cap returns errortype=advertisedpriceexceedscap before funding; lower prices are rechecked against live budgets. Definitive non-delivery of a newly linked credit-funded delegation creates a reversal-linked refund, restoring the refunded amount to both rolling spend-cap calculations; ambiguous possiblydelivered calls remain held for explicit resolution. Refund rows created before migration 103 may be unlinked and restore balance without rolling-cap headroom.

For the full protocol specification, environment variables, allowlists, and billing event payloads, see docs/a2a-delegation.md.

Platform Tool Marketplace

Teardrop exposes 31 caller-facing built-in, metered tools through the marketplace catalog. Callers can invoke them:

  • Via the MCP gateway at GET /tools/mcp (direct tool invocation, billed per call).
  • As tools called during agent runs (via POST /agent/run when the agent decides to use them; billed in the run's usage cost).

For the complete list of tools, detailed descriptions, and their per-call prices, please refer to the docs/tools-catalog.md.

Enable with MARKETPLACEENABLED=true. When enabled, tools appear in GET /marketplace/catalog with qualifiedname = "platform/{toolname}" and tooltype = "platform". Catalog discovery supports category filtering, sort=popularity, single-tool detail pages, an author index at GET /marketplace/authors, author profiles, LLM-friendly discovery at GET /marketplace/llms.txt, and current effective prices at GET /marketplace/quote?tool={qualified_name}. The public catalog is the complete active published inventory for an author; authenticated agents can inspect their current org inventory at GET /agent/tools. The author index reports active published authors and aggregate call counts, then links clients to the existing author profile for tool details; it is not a list of remote A2A delegation URLs. Aggregate quality metrics are available at GET /.well-known/reputation.json. Marketplace authors can register external MCP servers and publish discovered tools as listings via POST /marketplace/import/preview and POST /marketplace/import/publish (organization admins or org-bound machine credentials).

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Teardrop: common questions

Is Teardrop MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Teardrop safety report
How do I install Teardrop?
It runs remotely at api.teardrop.dev. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Teardrop need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Teardrop maintained?
The last commit was 22 days ago (2026-10-13). The latest release is v1.0.0.
Is Teardrop up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
How does Teardrop compare with other MCP servers?
safety score 85/100 (higher than 70% of 48,255 servers); tools 35 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.