Agent Einstein — Crypto & Market Intelligence

MEV Detection and Protection

detect_mev

Read-onlyIdempotent

Detect sandwich attacks and MEV extraction against a token or wallet, or get a protected routing recommendation for a pending transaction. [Paid: $0.50–$0.60 per call from your Einstein credit balance. Free alternatives exist for several of these — see list_einstein_capabilities.]

Input Schema

Name	Required	Description	Default
`kind`	No	detection = historical MEV · protection = protected routing advice.	detection
`chain`	No	Blockchain network.	base
`timeframe`	No	Lookback window.	24h
`tokenAddress`	No	Token to inspect, when relevant.

Output Schema

Name	Required	Description
`skill`	No	Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.
`reason`	No	Why there is no analysis, when `available` is false.
`analysis`	No	The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.
`available`	No	True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the market.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 15, 2026

changedInput schema / properties / kind / description

Previous value: -"detection = historical MEV · mempool = live mempool watch · protection = protected routing advice."New value: +"detection = historical MEV · protection = protected routing advice."

changedInput schema / properties / kind / enum

Previous value: -[
-  "detection",
-  "mempool",
-  "protection"
-]New value: +[
+  "detection",
+  "protection"
+]

Changed1 schema field changedSep 4, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "analysis": {
+      "description": "The written answer, identical to the result's text block. This is the field to read: the rest of the payload is whichever capability answered, and its shape varies by tool and by argument.",
+      "type": "string"
+    },
+    "available": {
+      "description": "True when the analysis ran. False when it did not — no capability matched the arguments, the caller is out of credit, billing was unavailable, or the skill produced nothing. NOT a statement about the market.",
+      "type": "boolean"
+    },
+    "reason": {
+      "description": "Why there is no analysis, when `available` is false.",
+      "type": "string"
+    },
+    "skill": {
+      "description": "Which Einstein capability answered. These tools route onto one of many skills by an enum argument, so this names the branch that actually ran.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

AddedAug 17, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover readOnlyHint, destructiveHint=false, idempotentHint and openWorldHint, so the safety profile is set. The description adds value by disclosing the per-call cost and the credit-balance billing source, which is behavioral context absent from the annotations. It does not mention rate limits or return shape, keeping it below a 5.

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

Conciseness5/5

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

Two sentences with the core purpose front-loaded and the billing note bracketed at the end. Every element earns its place with no redundancy.

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

Completeness4/5

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

With an output schema present, return values need no explanation, and all four parameters are documented. The description adequately covers both operating modes and the billing caveat; only the detection-vs-protection selection nuance is left entirely to the schema.

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% with 3 enums whose values are documented (kind, chain, timeframe) and a described tokenAddress. The description adds no parameter-level syntax or format detail beyond what the schema already provides, 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?

The description uses a specific verb (detect) with a concrete resource (sandwich attacks and MEV extraction against a token or wallet) and also covers the second mode, protected routing recommendations. It maps cleanly onto the `kind` enum values of detection/protection, letting an agent understand both functions without opening the schema.

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

Usage Guidelines4/5

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

It discloses paid cost ($0.50–$0.60 per call) and points to list_einstein_capabilities for free alternatives, which is genuine when-to-use guidance. It does not explicitly state when to prefer detection vs protection (that is left to the schema enum descriptions), so it stops short of full alternative routing.

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

All Agent Einstein — Crypto & Market Intelligence 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.