Aerodrome MCP for Base

Overview Schema Source Related Servers Discussions Admin

Wallet changes since last complete snapshot

aerodrome_wallet_changes

Idempotent

Detect changes in Aerodrome voting, rewards, balances, and locks by comparing snapshots with a UUID. Reuse the same ID to retrieve a saved report; use a new ID to start a new comparison.

Instructions

Compare configured voting/rewards plus bounded liquid balances and locks using a caller-generated UUID requestId. Old snapshots without assets initialize the new sections without inferred changes. Reuse the SAME ID for retries: returns the saved report without RPC. A new ID advances the baseline only for a complete snapshot. Report and baseline commit atomically; partial reports are saved without replacing the baseline. This tool writes local history but never changes blockchain state. Missing reward rows are unknown, not zero or proof of claims.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`requestId`	Yes	Generate one UUID before capture. Reuse it on every retry; use a new UUID only for a new comparison.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes
`chainId`	Yes
`changes`	Yes
`findings`	Yes
`reportId`	Yes
`warnings`	Yes
`observation`	Yes
`reportSaved`	Yes
`epochChanged`	Yes
`baselineSaved`	Yes
`blockchainReadOnly`	Yes
`initializedSections`	No
`previousObservation`	Yes
`unavailableSections`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.3.0Sep 15, 2026

changedOutput schema / properties / changes / items / properties / section / enum

Previous value: -[
-  "protocol",
-  "voting",
-  "rewards"
-]New value: +[
+  "protocol",
+  "voting",
+  "rewards",
+  "balances",
+  "locks"
+]

addedOutput schema / properties / findings

Added value: +{
+  "default": [],
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "code": {
+        "enum": [
+          "BASELINE_CREATED",
+          "SECTION_UNAVAILABLE",
+          "EPOCH_CHANGED",
+          "OWNER_CHANGED",
+          "VOTING_POWER_CHANGED",
+          "REWARD_CHANGED",
+          "ROW_APPEARED",
+          "ROW_NO_LONGER_OBSERVED",
+          "VALUE_CHANGED",
+          "SECTION_BASELINE_CREATED",
+          "BALANCE_CHANGED",
+          "LOCK_CHANGED"
+        ],
+        "type": "string"
+      },
+      "decimals": {
+        "anyOf": [
+          {
+            "maximum": 36,
+            "minimum": 0,
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "deltaFormatted": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "fromBlock": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "key": {
+        "type": [
+          "string",
+          "null"
+        ]
+      },
+      "level": {
+        "enum": [
+          "INFO",
+          "ATTENTION"
+        ],
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "section": {
+        "enum": [
+          "protocol",
+          "voting",
+          "rewards",
+          "balances",
+          "locks"
+        ],
+        "type": "string"
+      },
+      "sources": {
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "toBlock": {
+        "type": "string"
+      },
+      "token": {
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "required": [
+      "code",
+      "level",
+      "section",
+      "key",
+      "message",
+      "fromBlock",
+      "toBlock",
+      "token",
+      "decimals",
+      "deltaFormatted",
+      "sources"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / initializedSections

Added value: +{
+  "items": {
+    "enum": [
+      "balances",
+      "locks"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}

changedOutput schema / properties / unavailableSections / items / enum

Previous value: -[
-  "voting",
-  "rewards"
-]New value: +[
+  "voting",
+  "rewards",
+  "balances",
+  "locks"
+]

changedOutput schema / required

Previous value: -[
-  "status",
-  "chainId",
-  "blockchainReadOnly",
-  "observation",
-  "previousObservation",
-  "reportId",
-  "reportSaved",
-  "baselineSaved",
-  "epochChanged",
-  "changes",
-  "unavailableSections",
-  "warnings"
-]New value: +[
+  "status",
+  "chainId",
+  "blockchainReadOnly",
+  "observation",
+  "previousObservation",
+  "reportId",
+  "reportSaved",
+  "baselineSaved",
+  "epochChanged",
+  "changes",
+  "findings",
+  "unavailableSections",
+  "warnings"
+]

First observedv0.1.1Sep 13, 2026

TDQS

A5/5.0

Behavior5/5

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

Although annotations indicate idempotentHint=true and openWorldHint=true, the description adds valuable context beyond these: it explains the atomic commit of report and baseline, partial report saving behavior, and that the tool writes local history but does not mutate blockchain state. This aligns with annotations (idempotent, open world) and adds specific nuances around retries and snapshot baselines.

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?

The description is dense but highly informative, with each sentence adding key operational detail. It front-loads the core comparison function and then efficiently covers retry semantics, snapshot initialization, atomicity, and interpretational caveats. No filler or redundant content.

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?

Given the tool's complexity (state comparison, idempotency, atomic commits) and that it has an output schema, the description covers all necessary operational aspects: how to use requestId, what happens on retries, baseline behavior, local vs blockchain state, and how to interpret missing data. It is complete for an agent to correctly select and invoke the tool.

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

Parameters5/5

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

The description significantly enriches the parameter semantics beyond the schema. While the schema specifies 'requestId' as a UUID with format/pattern, the description explains the functional role: generate a new UUID for a new comparison and reuse it for retries to fetch the saved report. This is critical for correct usage and goes far beyond the schema's type/format information.

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 clearly identifies the tool's purpose: comparing wallet state (voting/rewards, liquid balances, locks) since the last complete snapshot. It distinguishes itself from siblings by focusing on 'changes since last snapshot' and mentions a caller-generated UUID for idempotent retries, which is unique among the sibling tools.

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?

The description provides explicit usage guidance: use the same UUID for retries to avoid re-running RPC calls, and use a new UUID for a new comparison. It also clarifies the behavior for old snapshots without assets and emphasizes that missing reward rows are 'unknown, not zero', which guides interpretation of results.

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

Deploy Server