DeFade MCP server

Which servers in the official MCP registry are DeFade's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-20

← Back to DeFade

Whose server it is

Registry nameorg.defade/defadeverified in the MCP registry

The registry name sits under defade.org. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-20

Stateanswerschecked 2026-10-20
Tools15
Server calls itselfdefade
Server version1.1.8
Protocol version2025-06-18

On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 111 ms.

Measured dailydaily checks: 1, the first on 2026-10-20

Answeredmeasuring1 of the 7 daily checks it takes to print a share
Median first answer84 ms
Space in an agent's context≈ 7,297 tokensthe definitions of all its tools (15), which an agent carries on every turn
Tool definitionsA · 100 of 100

Every tool passes all six checks.

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The state of vendors' MCP servers: method and numbers →

Tools it offers15 tools · read 2026-10-20

get_token_scan
Run a full DeFade scan on one token contract. On Solana: token metadata, holder distribution, creator history (wallet age, previous token launches) and the headline risk verdict. On an EVM chain: the contract and market read only (token…
get_rug_score
Rug pull probability for one token: a 0-100 score where HIGHER MEANS MORE DANGEROUS, a verdict label, and the individual signals that drove it. This is the opposite direction from get_token_scan's safety score. Call this tool ONLY when…
get_holders
Holder distribution for one token, with liquidity pools, burn addresses, lockers, exchange wallets and contracts classified out, so the top-holder list reflects actual holders. Returns the classified top holders with each wallet's supply…
get_whales
Wallets holding at least 1% of supply once pools, lockers, treasuries and custodial accounts are removed. Each row carries the balance, share of supply, any attribution label (known KOL, dev-linked stash, exchange), the 24-hour…
get_liquidity
Liquidity pool analysis for one token: which DEX holds the deepest pool, its depth in USD, and whether the LP tokens are burned, locked or still in someone's hands. lpStatus is the verdict — LP BURNED, LP LOCKED, LP UNLOCKED, PARTIALLY…
get_launch_bundles
Bundle detection for one token: coordinated buys in the launch window plus delayed sweeps, accounted on peak net exposure rather than raw buy count, so wallets that bought and flipped are not counted as holders. Heavy bundling that is…
get_launch_snipers
Bots that bought in the first block or first seconds of this token's launch, and whether they are connected to the deployer. The window is the first 120 seconds after the first transaction; at most 30 rows are returned and…
get_wallet_links
The graph of proven on-chain links between wallets around one token — who funded whom, who transferred to whom, and coordinated timing — typically the deployer's supply fanned out to look like organic demand. Use it when the holder list…
get_smart_money
Wallets with a track record of profitable entries that are holding or trading this token, classified from their historical trade win rates — a "verified" smart-money tag requires a known win rate of 50% or better. Computed live from the…
get_dev_tracker
What the token's creator has done with their supply: the share they still hold, what left through sales versus transfers, and where the transfers went. Read the state carefully: still holding is neutral, a dev who simply sold out is…
get_funding_sources
Multi-hop tracing of where the money behind this token's key wallets actually came from, walking each funding chain back and tiering the source by whether it is a KYC'd exchange. Use it to test whether several "unrelated" holders share…
get_lookalike_clusters
Clusters of wallets around one token that behave as a single actor — buys sized and timed alike so demand looks organic — even when no transfer or funding trail connects them. That behavioural inference is what separates it from…
get_fee_fingerprint
Wallets whose transactions pin an identical fee setting — compute-unit price or Jito tip on Solana, priority fee or legacy gas price on EVM chains — one operator's bot settings showing up across every wallet it drives. This is the…
get_token_price
Price history for one token as OHLCV candles, plus the latest price, the window's high and low with their timestamps, and the percent change across the window — prices in USD (the *Usd fields), volume as the market source quotes it…
get_usage
Report the calling API key's plan, rate limits and how much of its monthly allowance is left. Takes no arguments. Use it when a call fails on quota, or when the user asks what their DeFade plan includes. Not for anything about a token…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "defade": {
      "type": "http",
      "url": "https://api.defade.org/mcp"
    }
  }
}

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.