DeFade — Multi-Chain Memecoin Analyzer

Rug pull probability

get_rug_score

Read-onlyIdempotent

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. This is the verdict the DeFade website shows: call it, after get_token_scan, for every "is this safe", "is this a rug" or "should I buy" question, on every chain (on an EVM chain get_token_scan carries no score at all). When complete is false the score is partial: say so, and call again for the rest. Not for the evidence behind the number — it names the signals but does not list the wallets; for who is behind the risk call get_wallet_links, get_dev_tracker or get_launch_bundles. Arguments: address and chain; one API unit on Solana, five on an EVM chain, because there the score reads every module first — check get_usage before scoring many EVM tokens.

Input Schema

Name	Required	Description	Default
`chain`	No	Chain the token is deployed on: solana (default), ethereum, base, bsc, robinhood, arc, hyperevm, monad. Required for any 0x address, because the same contract address can exist on several EVM chains. Omit it for Solana. An unsupported value is rejected before any request is spent; EVM chains need a key on an All-Chains plan.	solana
`address`	Yes	The token's own contract address, exactly as an explorer shows it. Solana: the base58 mint, 32-44 characters (e.g. 6p6xgHyF7AeE6TZkSmFsko444wqoP15icUSqi2jfGiPN). EVM: 0x followed by 40 hex characters, case-insensitive (e.g. 0x6982508145454ce325ddbe47a25d4ec3d2311933). Never a pool, pair, wallet or deployer address — those come back as not found. Set `chain` to match the address: a 0x address alone cannot say which EVM chain it lives on, and a Solana mint sent with an EVM chain is rejected.

Output Schema

Name	Required	Description
`token`	No	The address that was scanned (on get_token_scan, the full token metadata object instead).
`fusion`	No	Cross-signal wallet correlation; wallets list is empty on non-Pro keys.
`pending`	No	Modules still running when the score was taken; empty when it is complete. Call the tool again for the score with them in.
`signals`	No	Each contributing signal: what fired, its weight and its explanation.
`verdict`	No	PROBABLY SAFE (<25), SOME RISK (25+), ELEVATED RISK (45+), HIGH RISK (60+), EXTREME RISK (75+); or a state that overrides the bands: RUGGED / DEAD, ABANDONED / DEAD (failed after its market cap had once passed $5,000, or with no candles to say it never did), NEVER BONDED (a launchpad coin that never left its bonding curve — no pool ever existed), NEVER TOOK OFF (off any curve, its market cap never passed $5,000); rugScore is still returned as a number.
`complete`	No	True when nothing is pending: every module the score reads is in it.
`coverage`	No	"full" when the Pro signal set contributed, "free" when only the free signals did — a "free" score has seen less evidence. "partial" when a module was still running after the 25 s this tool waits (Bundle Detection on a token nobody has scanned can take a minute or more): the modules are named in pending and keep running, so call the tool again for the complete score.
`rugScore`	No	Rug probability 0 (safe) to 100 (critical). HIGHER IS MORE DANGEROUS.
`poweredBy`	No	Always "DeFade.org".
`timestamp`	No	ISO time the response was assembled.
`scoreLabel`	No	Null normally. "NEVER BONDED" or "NEVER TOOK OFF" when the human surfaces print that state instead of the percentage; rugScore is still the number.
`bundleSubScore`	No	The bundle component of the score.
`proChecksLocked`	No	How many Pro-only checks were withheld.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 29, 2026

changedOutput schema / properties / scoreLabel / description

Previous value: -"Null normally. \"NEVER BONDED\" when the human surfaces print that state instead of the percentage; rugScore is still the number."New value: +"Null normally. \"NEVER BONDED\" or \"NEVER TOOK OFF\" when the human surfaces print that state instead of the percentage; rugScore is still the number."

changedOutput schema / properties / verdict / description

Previous value: -"PROBABLY SAFE (<25), SOME RISK (25+), ELEVATED RISK (45+), HIGH RISK (60+), EXTREME RISK (75+); or a state that overrides the bands: RUGGED / DEAD, ABANDONED / DEAD, NEVER BONDED (a launchpad coin that never left its bonding curve — no pool ever existed; rugScore is still returned as a number)."New value: +"PROBABLY SAFE (<25), SOME RISK (25+), ELEVATED RISK (45+), HIGH RISK (60+), EXTREME RISK (75+); or a state that overrides the bands: RUGGED / DEAD, ABANDONED / DEAD (failed after its market cap had once passed $5,000, or with no candles to say it never did), NEVER BONDED (a launchpad coin that never left its bonding curve — no pool ever existed), NEVER TOOK OFF (off any curve, its market cap never passed $5,000); rugScore is still returned as a number."

Changed2 schema fields changedOct 28, 2026

changedInput schema / properties / chain / description

Previous value: -"Chain the token is deployed on: solana (default), ethereum, base, bsc, robinhood, arc, hyperevm. Required for any 0x address, because the same contract address can exist on several EVM chains. Omit it for Solana. An unsupported value is rejected before any request is spent; EVM chains need a key on an All-Chains plan."New value: +"Chain the token is deployed on: solana (default), ethereum, base, bsc, robinhood, arc, hyperevm, monad. Required for any 0x address, because the same contract address can exist on several EVM chains. Omit it for Solana. An unsupported value is rejected before any request is spent; EVM chains need a key on an All-Chains plan."

changedInput schema / properties / chain / enum

Previous value: -[
-  "solana",
-  "ethereum",
-  "base",
-  "bsc",
-  "robinhood",
-  "arc",
-  "hyperevm"
-]New value: +[
+  "solana",
+  "ethereum",
+  "base",
+  "bsc",
+  "robinhood",
+  "arc",
+  "hyperevm",
+  "monad"
+]

Changed3 schema fields changedOct 20, 2026

addedOutput schema / properties / complete

Added value: +{
+  "description": "True when nothing is pending: every module the score reads is in it.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

changedOutput schema / properties / coverage / description

Previous value: -"\"full\" when the Pro signal set contributed, \"free\" when only the free signals did — a \"free\" score has seen less evidence. (\"partial\" only appears on the raw API when a caller declines to wait; this tool always waits for the complete answer.)"New value: +"\"full\" when the Pro signal set contributed, \"free\" when only the free signals did — a \"free\" score has seen less evidence. \"partial\" when a module was still running after the 25 s this tool waits (Bundle Detection on a token nobody has scanned can take a minute or more): the modules are named in pending and keep running, so call the tool again for the complete score."

addedOutput schema / properties / pending

Added value: +{
+  "description": "Modules still running when the score was taken; empty when it is complete. Call the tool again for the score with them in.",
+  "type": [
+    "array",
+    "null"
+  ]
+}

Changed2 schema fields changedOct 8, 2026

changedInput schema / properties / chain / description

Previous value: -"Chain the token is deployed on: solana (default), ethereum, base, robinhood. Required for any 0x address, because the same contract address can exist on several EVM chains. Omit it for Solana. An unsupported value is rejected before any request is spent; EVM chains need a key on an All-Chains plan."New value: +"Chain the token is deployed on: solana (default), ethereum, base, bsc, robinhood, arc, hyperevm. Required for any 0x address, because the same contract address can exist on several EVM chains. Omit it for Solana. An unsupported value is rejected before any request is spent; EVM chains need a key on an All-Chains plan."

changedInput schema / properties / chain / enum

Previous value: -[
-  "solana",
-  "ethereum",
-  "base",
-  "robinhood"
-]New value: +[
+  "solana",
+  "ethereum",
+  "base",
+  "bsc",
+  "robinhood",
+  "arc",
+  "hyperevm"
+]

Changed1 schema field changedOct 1, 2026

changedOutput schema / properties / coverage / description

Previous value: -"\"full\" when the Pro signal set contributed, \"free\" when only the free signals did — a \"free\" score has seen less evidence."New value: +"\"full\" when the Pro signal set contributed, \"free\" when only the free signals did — a \"free\" score has seen less evidence. (\"partial\" only appears on the raw API when a caller declines to wait; this tool always waits for the complete answer.)"

Changed2 schema fields changedSep 13, 2026

addedOutput schema / properties / scoreLabel

Added value: +{
+  "description": "Null normally. \"NEVER BONDED\" when the human surfaces print that state instead of the percentage; rugScore is still the number.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / properties / verdict / description

Previous value: -"PROBABLY SAFE (<25), SOME RISK (25+), ELEVATED RISK (45+), HIGH RISK (60+), EXTREME RISK (75+), or RUGGED."New value: +"PROBABLY SAFE (<25), SOME RISK (25+), ELEVATED RISK (45+), HIGH RISK (60+), EXTREME RISK (75+); or a state that overrides the bands: RUGGED / DEAD, ABANDONED / DEAD, NEVER BONDED (a launchpad coin that never left its bonding curve — no pool ever existed; rugScore is still returned as a number)."

Changed3 schema fields changedSep 5, 2026

removedOutput schema / properties / coverage / additionalProperties
```
Removed value: -true
```

changedOutput schema / properties / coverage / description

Previous value: -"Which inputs were available; a score without liquidity or holder data is weaker and says so."New value: +"\"full\" when the Pro signal set contributed, \"free\" when only the free signals did — a \"free\" score has seen less evidence."

changedOutput schema / properties / coverage / type

Previous value: -[
-  "object",
-  "null"
-]New value: +[
+  "string",
+  "null"
+]

Changed9 schema fields changedSep 5, 2026

changedOutput schema / properties / bundleSubScore / type

Previous value: -"number"New value: +[
+  "number",
+  "null"
+]

changedOutput schema / properties / coverage / type

Previous value: -"object"New value: +[
+  "object",
+  "null"
+]

changedOutput schema / properties / fusion / type

Previous value: -"object"New value: +[
+  "object",
+  "null"
+]

changedOutput schema / properties / poweredBy / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

changedOutput schema / properties / proChecksLocked / type

Previous value: -"number"New value: +[
+  "number",
+  "null"
+]

changedOutput schema / properties / rugScore / type

Previous value: -"number"New value: +[
+  "number",
+  "null"
+]

changedOutput schema / properties / signals / type

Previous value: -"array"New value: +[
+  "array",
+  "null"
+]

changedOutput schema / properties / timestamp / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

changedOutput schema / properties / verdict / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

Changed1 schema field changedSep 3, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "bundleSubScore": {
+      "description": "The bundle component of the score.",
+      "type": "number"
+    },
+    "coverage": {
+      "additionalProperties": true,
+      "description": "Which inputs were available; a score without liquidity or holder data is weaker and says so.",
+      "type": "object"
+    },
+    "fusion": {
+      "additionalProperties": true,
+      "description": "Cross-signal wallet correlation; wallets list is empty on non-Pro keys.",
+      "type": "object"
+    },
+    "poweredBy": {
+      "description": "Always \"DeFade.org\".",
+      "type": "string"
+    },
+    "proChecksLocked": {
+      "description": "How many Pro-only checks were withheld.",
+      "type": "number"
+    },
+    "rugScore": {
+      "description": "Rug probability 0 (safe) to 100 (critical). HIGHER IS MORE DANGEROUS.",
+      "type": "number"
+    },
+    "signals": {
+      "description": "Each contributing signal: what fired, its weight and its explanation.",
+      "type": "array"
+    },
+    "timestamp": {
+      "description": "ISO time the response was assembled.",
+      "type": "string"
+    },
+    "token": {
+      "description": "The address that was scanned (on get_token_scan, the full token metadata object instead)."
+    },
+    "verdict": {
+      "description": "PROBABLY SAFE (<25), SOME RISK (25+), ELEVATED RISK (45+), HIGH RISK (60+), EXTREME RISK (75+), or RUGGED.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Changed2 schema fields changedSep 3, 2026

changedInput schema / properties / address / description

Previous value: -"Token contract address. A base58 mint for Solana, or 0x-prefixed for EVM chains. Set `chain` to match — a 0x address alone cannot say which EVM chain it lives on."New value: +"The token's own contract address, exactly as an explorer shows it. Solana: the base58 mint, 32-44 characters (e.g. 6p6xgHyF7AeE6TZkSmFsko444wqoP15icUSqi2jfGiPN). EVM: 0x followed by 40 hex characters, case-insensitive (e.g. 0x6982508145454ce325ddbe47a25d4ec3d2311933). Never a pool, pair, wallet or deployer address — those come back as not found. Set `chain` to match the address: a 0x address alone cannot say which EVM chain it lives on, and a Solana mint sent with an EVM chain is rejected."

changedInput schema / properties / chain / description

Previous value: -"Which chain the address lives on. Defaults to solana."New value: +"Chain the token is deployed on: solana (default), ethereum, base, robinhood. Required for any 0x address, because the same contract address can exist on several EVM chains. Omit it for Solana. An unsupported value is rejected before any request is spent; EVM chains need a key on an All-Chains plan."

First observedSep 1, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the readOnly/idempotent annotations: it discloses that `complete: false` yields a partial score and that the correct behavior is to disclose partiality and re-call, and it states the cost differential (1 API unit on Solana vs 5 on EVM, with a pointer to get_usage before bulk EVM scoring). These are exactly the operational facts an agent needs and none are in the schema or annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and score direction are front-loaded, and almost every clause carries routing, cost, or partial-result information. A few sentences pack multiple ideas (the get_usage cost warning, the evidence-tool list), and some phrasing is clunky, which keeps it just short of a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Output schema exists, yet the description still frames what comes back (score, verdict, driving signals) and, critically, handles the incomplete-result case the schema cannot express. Combined with cost, chain scope, and sibling handoffs, nothing an agent needs to invoke this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already carries address format, chain enum values, and the 0x-requires-chain rule. The description's "Arguments: address and chain" plus the per-chain cost note adds pricing context but no new per-parameter meaning, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (rug pull probability for one token) and immediately pins the semantics: a 0-100 score where higher means more dangerous, plus a verdict label and driver signals. It explicitly distinguishes itself from get_token_scan by noting the inverse direction of that tool's safety score, so an agent can't confuse the two.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit sequencing (call after get_token_scan), the question classes that select it ("is this safe", "is this a rug", "should I buy"), the chain scope (every chain, and the EVM case where get_token_scan carries no score). It also names where not to use it — for the underlying evidence, deferring to get_wallet_links, get_dev_tracker, or get_launch_bundles.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All DeFade — Multi-Chain Memecoin Analyzer tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?