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.

MEV Intelligence

REMOTE · MEV.ADVALOREM.IO · SCANNED SEP 20

Real-time Ethereum liquidation intelligence for AI agents and MEV bots.

Available components

0 this week 81 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security74
Transport & Reachability100
Schema Quality & AI Usability72
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1559 tokens (~155/item across 10 items; 10 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
  • Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the MEV Intelligence MCP server?

MEV Intelligence is a hosted endpoint at https://mev.advalorem.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mev.advalorem.io

# add to Claude Code
claude mcp add --transport http io-advalorem-mev-intelligence 'https://mev.advalorem.io/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "io-advalorem-mev-intelligence": {
      "url": "https://mev.advalorem.io/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "io-advalorem-mev-intelligence": {
      "type": "http",
      "url": "https://mev.advalorem.io/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.io-advalorem-mev-intelligence]
url = "https://mev.advalorem.io/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-advalorem-mev-intelligence": {
      "type": "remote",
      "url": "https://mev.advalorem.io/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add io-advalorem-mev-intelligence --url 'https://mev.advalorem.io/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  io-advalorem-mev-intelligence:
    url: "https://mev.advalorem.io/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "io-advalorem-mev-intelligence": {
      "Transport": "http",
      "Url": "https://mev.advalorem.io/mcp"
    }
  }
}
# add to Vellum
assistant mcp add io-advalorem-mev-intelligence -t streamable-http -u 'https://mev.advalorem.io/mcp'
// mcp.json
{
  "mcpServers": {
    "io-advalorem-mev-intelligence": {
      "type": "http",
      "url": "https://mev.advalorem.io/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

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.

  • 7 Sept 26 0
    • Stability: 0.97 → pass security
  • 6 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.

  • 3 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.

  • 1 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.

  • 30 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

  • 28 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 26 Aug 26 +2
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

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 · Probed https://mev.advalorem.io/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_256_GCM_SHA384 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mev.advalorem.io CN=YR1,O=Let's Encrypt,C=US 16 Jul 2026 14 Oct 2026 RSA 2048 SHA256-RSA 535dee3703ca1d9f9b5b40dab97a01d494d
SANs: mev.advalorem.io
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mev.advalorem.io. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
io. present 57355 8 Verified
advalorem.io. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mev.advalorem.io/mcp Verified 200
http (plaintext) http://mev.advalorem.io/mcp HTTPS enforced 301 https://mev.advalorem.io/mcp
MCP tools · 10 exposed · ~1,559 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
build_liquidation_tx ~421

Build agent-ready calldata for a liquidation transaction. Returns the target protocol contract address, ABI-encoded calldata, suggested gas limit, value, and chain — everything an agent needs to sign and submit via submit_bundle. Supports Aave V3 (L1 + Base), Spark (L1), and Morpho Blue (L1). Returns calldata only — the agent signs and submits separately. This tool does NOT touch funds and does NOT submit anything; it is a calldata builder.

NameTypeReqDescription
borrowerstringyes0x-prefixed address of the borrower being liquidated.
chainstringyesChain to build calldata for. base only supported for aave-v3.
collateral_assetstringyes0x-prefixed address of the collateral token to seize. For Morpho, this field is ignored (market ID supplies it).
debt_assetstringyes0x-prefixed address of the debt token to repay. For Morpho, this field is ignored.
debt_to_coverstringyesAmount of debt token to repay in wei (string to avoid precision loss). Use "max" or the uint256 max value 0xff..ff to liquidate as much as possible (Aave V3 close factor applies).
morpho_market_idstringMorpho Blue market id (bytes32). Required when protocol=morpho.
morpho_repaid_sharesstringMorpho Blue only. Amount of debt shares to repay. Mutually exclusive with morpho_seized_assets.
morpho_seized_assetsstringMorpho Blue only. Amount of collateral to seize in wei. Mutually exclusive with morpho_repaid_shares.
protocolstringyesLending protocol. aave-v3 supported on ethereum + base. spark and morpho on ethereum only.
receive_a_tokenbooleanAave V3 only. If true, receive collateral as aToken (saves gas, no unwrap). If false, receive underlying. Default false.

No output schema declared.

No examples provided.

get_builder_recommendation ~69

Get the best Ethereum block builder for MEV bundle submission RIGHT NOW based on live relay acceptance rate and submission volume. Returns the top recommended builder name and acceptance percentage. Full ranked builder list with telemetry available at /intelligence/builder-recommendation with x402 payment ($0.25).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_daily_liquidation_report ~119

Get a daily intelligence report summarizing liquidation market activity: competitor count, positions we would have fired on, funnel metrics (PRE→SIM→HOTFIRE→SUBMIT→LANDED), and the top candidate right now. This is the "morning briefing" tool — call it once per session to understand market state before executing. Full accuracy archive with precision/recall metrics available at /intelligence/accuracy-archive.

NameTypeReqDescription
window_hoursintegerLookback window in hours (default 24, max 48).

No output schema declared.

No examples provided.

get_liquidation_waves ~126

Get near-liquidation borrowers ranked by health factor proximity across Aave V3, Spark, and Morpho on L1 and Base. Returns top 10 positions with full borrower addresses, health factor, debt USD, and collateral USD. Once you have a target, sign a liquidation transaction and call submit_bundle to execute atomically. For net profit estimates and the full borrower universe, call /intelligence/liquidation-waves with x402 USDC payment ($0.50).

NameTypeReqDescription
limitintegerMax results (default 10, preview max 10)

No output schema declared.

No examples provided.

get_mev_feed ~88

Get a risk-enriched MEV opportunity stream. Returns 10 positions with chain, protocol, health factor, and risk tags. Full stream with borrower addresses and expected profit available at /intelligence/feed with x402 payment ($0.10). Use submit_bundle to act on opportunities directly from this feed.

NameTypeReqDescription
min_net_usdnumberMinimum estimated net USD profit to include

No output schema declared.

No examples provided.

get_searcher_leaderboard ~75

Get top MEV searchers ranked by landed liquidation fires in the last 4 hours. Returns top 5 searchers with full addresses, landed count, total submissions, and land rate percentage. Full 25-entry leaderboard available at /intelligence/searcher-leaderboard with x402 payment ($0.25).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

monitor_crossing_candidates ~124

Get the highest-priority liquidation candidates sorted by cross probability — borrowers most likely to become liquidatable in the next price move. Each candidate includes health factor, cross probability (0–1), estimated net profit, and protocol. Use this to prioritize which positions to pre-build bundles for. Call submit_bundle when a candidate crosses HF=1.0.

NameTypeReqDescription
limitintegerMax candidates to return (default 10, max 20).
min_cross_probnumberMinimum cross probability (0–1) to include. Default 0.05.

No output schema declared.

No examples provided.

predict_liquidation_probability ~180

Get a structured liquidation probability prediction for a specific borrower or the top candidates. Returns: health_factor, cross_probability (0–1), estimated_ev_usd, lead_time_estimate_s (how long until crossing at current oracle velocity), oracle_velocity (|Δprice|/min on collateral asset), and a human-readable verdict. This is the core moat tool — it exposes the prediction layer that drives bundle decisions. Call this before submit_bundle to confirm the opportunity is still live and to size your bribe correctly. Full probability model with confidence intervals available at /intelligence/liquidation-waves with x402 payment ($0.50).

NameTypeReqDescription
borrowerstringBorrower address to get prediction for. If omitted, returns top 5 candidates by cross probability.
protocolstringOptional protocol filter when borrower is not specified.

No output schema declared.

No examples provided.

recommend_bundle_submission ~88

Get an actionable bundle submission recommendation for a specific borrower or current market conditions. Returns the best builder to target, expected inclusion probability, and a human-readable reason based on live relay telemetry. Pair with monitor_crossing_candidates — identify a hot candidate, then call this to decide WHERE to submit your bundle.

NameTypeReqDescription
borrowerstringOptional. Borrower address to get a position-specific recommendation for.

No output schema declared.

No examples provided.

submit_bundle ~269

Submit a signed Ethereum bundle directly to MEV SearcherNet rbuilder for inclusion. Use this after get_liquidation_waves or get_mev_feed to act on a liquidation opportunity. Bundles are forwarded to rbuilder and fanned out to Flashbots, Titan, Beaver, BuilderNet, and bloXroute relays. Free with API key attribution (X-Api-Key header). Inclusion rate, sim pass rate, and per-builder acceptance available at /orderflow/analytics with provenance. Returns a tracking_id you can use to check submission status at /orderflow/submissions/{tracking_id}. Tip: pair with get_liquidation_waves — identify a borrower near liquidation, construct the liquidation tx, sign it, then call this tool.

NameTypeReqDescription
api_keystringOptional. API key for attribution and leaderboard tracking. Assign at mev.advalorem.io.
blockNumberstringyesTarget block number as hex string (e.g. "0x1400000"). Bundle will only be included in this exact block.
revertingTxHashesarrayOptional. Tx hashes that are allowed to revert without invalidating the bundle.
txsarrayyesArray of hex-encoded signed transactions (0x-prefixed RLP). Max 10 per bundle.

No output schema declared.

No examples provided.

Common questions

What is the MEV Intelligence MCP server?

MEV Intelligence is an MCP server listed in the public MCP registry as io.advalorem.mev/intelligence. Real-time Ethereum liquidation intelligence for AI agents and MEV bots. This page covers its hosted endpoint (https://mev.advalorem.io/mcp).

Is the MEV Intelligence MCP server safe to use?

MEV Intelligence scores 81 out of 100 on VerifyMCP. 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 MEV Intelligence MCP server expose?

MEV Intelligence exposes 10 tools: get_liquidation_waves, get_searcher_leaderboard, get_builder_recommendation, get_mev_feed, submit_bundle, and 5 more. Their descriptions and schemas cost roughly 1,559 tokens of context every time the server is loaded.

Does the MEV Intelligence MCP server require authentication?

No. We connected to MEV Intelligence without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the MEV Intelligence MCP server still maintained?

MEV Intelligence 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.