io.github.thomenz/soldefi-mcp
NPM · SOLDEFI-MCP · SCANNED SEP 20
Solana DeFi risk intel over x402: rug/honeypot scans, pool analysis, wash-filtered pools.
Available components
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 161 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 46 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability70
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2799 tokens (~215/item across 13 items; 13 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 Management83
- Stability observed for 25 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 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 14 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
How do I install the io.github.thomenz/soldefi-mcp server?
io.github.thomenz/soldefi-mcp runs locally as an npm package, launched with npx -y soldefi-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 · soldefi-mcp
claude mcp add thomenz-soldefi-mcp -- npx -y soldefi-mcp
{
"mcpServers": {
"thomenz-soldefi-mcp": {
"command": "npx",
"args": [
"-y",
"soldefi-mcp"
]
}
}
} {
"servers": {
"thomenz-soldefi-mcp": {
"command": "npx",
"args": [
"-y",
"soldefi-mcp"
]
}
}
} codex mcp add thomenz-soldefi-mcp -- npx -y soldefi-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"thomenz-soldefi-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"soldefi-mcp"
],
"enabled": true
}
}
} openclaw mcp add thomenz-soldefi-mcp --command npx --arg -y --arg soldefi-mcp
mcp_servers:
thomenz-soldefi-mcp:
command: "npx"
args: ["-y", "soldefi-mcp"] {
"McpServers": {
"thomenz-soldefi-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"soldefi-mcp"
]
}
}
} assistant mcp add thomenz-soldefi-mcp -t stdio -c npx -a -y soldefi-mcp
{
"mcpServers": {
"thomenz-soldefi-mcp": {
"command": "npx",
"args": [
"-y",
"soldefi-mcp"
]
}
}
} 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 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 −3
- Security disclosure: fail → unverified ▼ functional
- Stability: pass → 0.77 functional
- 17 Sept 26 0
- Stability: 0.97 → pass security
- 16 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 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −2
- Stability: pass → 0.83 functional
- 11 Sept 26 0
- Stability: 0.97 → pass security
- 10 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.
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/soldefi-mcp@0.5.2
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 161 packages
| Packages resolved | 161 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
analyze_pools Deep Solana liquidity-pool analysis for a token ~187
Deep liquidity-pool analysis for a Solana token across Raydium, Orca, Meteora and pumpswap. Per pool: real fee APR (volume x fee / TVL), wash-trade risk (turnover + executable-depth cross-check), age and TVL. Plus a token rug/honeypot verdict and a real Jupiter slippage ladder for true liquidity depth. Recommends the best risk-adjusted pool. Paid ($0.015).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | Solana SPL token mint address (base58), e.g. EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v (USDC). |
| tradeSizesUsd | array | – | Optional USD trade sizes for the slippage ladder (default [100, 1000, 10000]). |
No output schema declared.
No examples provided.
build_guarded_swap Build a Solana swap that refuses to route you into a rug ~267
Build a ready-to-sign Solana swap (Jupiter) with a rug check in front of it. Buying a token whose verdict is critical — or that cannot be sold — returns the verdict and NO transaction, so the swap you were about to make simply does not get built. Returns an UNSIGNED versioned transaction: your wallet signs and sends it, this service never custodies funds and cannot move anything. A 0.5% platform fee applies ONLY when selling into USDC/SOL; buying is fee-free. The fee is disclosed in the response and rides inside the transaction you sign. Paid ($0.001) for the build itself.
| Name | Type | Req | Description |
|---|---|---|---|
| amount | string | yes | Amount of inputMint in ATOMIC units, as a string. 1 USDC = "1000000". Never a decimal. |
| force | boolean | – | Build even when the risk gate refuses. The verdict still ships — this only overrides the block. |
| inputMint | string | yes | Mint you are paying with. |
| outputMint | string | yes | Mint you are receiving. |
| slippageBps | integer | – | Slippage tolerance in bps (default 100 = 1%). |
| userPublicKey | string | yes | Base58 wallet that will sign and own the swap. |
No output schema declared.
No examples provided.
can_i_sell Real-time Solana sellability check at your size ~161
Simulate exiting a specific USD amount of a Solana token via a live Jupiter buy->sell round trip: whether you can actually sell, USDC recovered, real sell price impact and tax/friction loss. Answers 'can I get $X out right now, and at what cost?' — catches honeypots and thin books at your real trade size. Paid ($0.003).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | Solana SPL token mint address (base58), e.g. EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v (USDC). |
| usd | number | – | Trade size in USD to simulate exiting (default 1000). |
No output schema declared.
No examples provided.
check_changed What changed on my watchlist since last time ~193
Re-check up to 10 Solana mints and get back ONLY what moved since you last looked: risk score rises/falls and, crucially, individual signals that appeared or cleared (a freeze authority coming back barely moves the score, and is exactly what a holder needs to know). Pass the `state` object returned by your previous call as `baseline`; the response carries a fresh `state` to store for the next one. Without a baseline every mint comes back as `new`. This is the call to make on a schedule — the others answer 'what is the risk today', this one answers 'what changed'. Paid ($0.02).
| Name | Type | Req | Description |
|---|---|---|---|
| baseline | object | – | The `state` object from your previous check_changed response, verbatim, keyed by mint. Omit on the first call. |
| mints | array | yes | 1-10 Solana SPL token mints to re-check. |
No output schema declared.
No examples provided.
check_deployer Solana token deployer reputation ~132
Trace who launched a Solana token: the mint's creator wallet, how much of the token the deployer still holds, the deployer wallet's age and the token's age. Returns a 0-100 risk score + verdict flagging fresh wallets, heavy insider self-holding and brand-new tokens. Paid ($0.01).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | Solana SPL token mint address (base58), e.g. EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v (USDC). |
No output schema declared.
No examples provided.
check_exit_risk Solana exit-risk: can I get out, and at what cost? ~186
Answer 'can I actually EXIT this Solana token right now, or am I trapped?' Crosses Birdeye smart-money signals — whale net buy/sell flow (24h), bundler/sniper manipulation tags, 1h sell-pressure and holder count — with a LIVE Jupiter exit-slippage ladder at $1k and $10k. Returns an exit_risk verdict (LOW/ELEVATED/HIGH): are the whales dumping into a thin book that traps you, or is the exit clean? The sellability wedge — for exit-planning and trading agents. Paid ($0.015).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | Solana SPL token mint address (base58), e.g. EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v (USDC). |
No output schema declared.
No examples provided.
check_lp_status Solana token liquidity durability / rug-pull exposure ~159
Assess how durable a Solana token's liquidity is and whether a dev could pull it: pools (TVL, age, DEX), largest-pool depth, burned-supply share, and whether mint/freeze authority is still live. Returns a 0-100 liquidity-risk score + verdict (DURABLE/SHAKY/FRAGILE/RUG-PRONE). A durability signal, not a cryptographic LP time-lock proof. Paid ($0.005).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | Solana SPL token mint address (base58), e.g. EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v (USDC). |
No output schema declared.
No examples provided.
full_scan Full Solana token rug workup in one call ~164
One paid call that bundles the honeypot/sellability scan, liquidity-durability (LP) check, deployer reputation and live exit-risk (Birdeye smart-money x Jupiter exit-slippage) into a single verdict — cheaper than buying the four separately (~$0.035 -> $0.03). Returns each sub-report plus an aggregated `overall` {riskScore, riskLevel, verdict, topFlags}. The whole picture before you buy or exit. Paid ($0.03).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | Solana SPL token mint address (base58), e.g. EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v (USDC). |
No output schema declared.
No examples provided.
scan_honeypot Solana token rug / honeypot scan ~161
Rug & honeypot scan of a Solana SPL token by mint. On-chain: mint/freeze authority renounced?, Token-2022 transfer tax, top-holder concentration, plus a live Jupiter buy->sell round trip proving the token is sellable at scan time (catches most honeypots). Returns a 0-100 risk score, machine flags and an agent-readable verdict (AVOID/CAUTION/LOW RISK). Paid ($0.005).
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | Solana SPL token mint address (base58), e.g. EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v (USDC). |
No output schema declared.
No examples provided.
scan_honeypot_batch Batch Solana rug/honeypot scan (up to 10 mints) ~97
Scan up to 10 Solana token mints in one paid call and get the full per-token honeypot verdict (0-100 risk score, flags, sellability) for each — cheaper than scanning individually. For vetting a watchlist or a set of launch candidates at once. Paid ($0.02).
| Name | Type | Req | Description |
|---|---|---|---|
| mints | array | yes | 1-10 Solana SPL token mints to scan. |
No output schema declared.
No examples provided.
scan_wallet_risk Portfolio rug scan for a Solana wallet ~97
Read a Solana wallet's SPL holdings and run the full honeypot/rug scan on each (up to 10 positions). Returns per-token risk plus a summary of how many holdings are critical/high/medium/low and which mints to exit. For portfolio-manager and risk agents auditing exposure. Paid ($0.03).
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Solana wallet address (base58) to scan for risky holdings. |
No output schema declared.
No examples provided.
top_pools Real best Solana DEX pools (wash-filtered) ~124
The real best Solana DEX pools: the same top-pools feed a free API returns, but wash-traded and fake-volume pools are filtered out and the rest ranked by risk-adjusted fee yield (Raydium/Orca/Meteora). Returns clean, decision-ready pools plus an `excluded` list showing exactly which pools were dropped and why. Paid ($0.02).
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max pools to return (default 15). |
| minTvlUsd | number | – | Minimum pool TVL in USD (default 10000). |
No output schema declared.
No examples provided.
validate_mint Validate a Solana mint address (free) ~92
Free local base58 address-format validation of a single Solana mint. No payment required. Use it to avoid paying on a malformed mint.
| Name | Type | Req | Description |
|---|---|---|---|
| mint | string | yes | Solana SPL token mint address (base58), e.g. EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v (USDC). |
No output schema declared.
No examples provided.
What is the io.github.thomenz/soldefi-mcp server?
io.github.thomenz/soldefi-mcp is listed in the public MCP registry as io.github.thomenz/soldefi-mcp. Solana DeFi risk intel over x402: rug/honeypot scans, pool analysis, wash-filtered pools. This page covers its npm package (soldefi-mcp).
Is the io.github.thomenz/soldefi-mcp server safe to use?
io.github.thomenz/soldefi-mcp scores 81 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.thomenz/soldefi-mcp server expose?
io.github.thomenz/soldefi-mcp exposes 13 tools: scan_honeypot, analyze_pools, top_pools, check_lp_status, check_deployer, and 8 more. Their descriptions and schemas cost roughly 2,020 tokens of context every time the server is loaded.
Is the io.github.thomenz/soldefi-mcp server still maintained?
io.github.thomenz/soldefi-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.thomenz/soldefi-mcp server under?
io.github.thomenz/soldefi-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.