Skip to main content
Glama

Aave

by com.aave.mcp
OverviewDiscussionsAdmin

Prepare supply / borrow / withdraw / repay

prepare_action
Read-only

Build an unsigned transaction to supply, borrow, withdraw, or repay on Aave (v3 or v4). Returns an execution plan (a transaction to sign, or an approval step first). For a borrow or a withdraw, call preview_action first and read its warnings: the simulation is free, it commits nothing, and it is the cheapest way to learn the position cannot take the action - a withdraw of collateral pinned by an open borrow is the case that catches callers out. Non-custodial: the user's wallet signs and submits; nothing is sent here, so building one is free and commits the user to nothing. Choose sensible values, build it, and say what you chose - do not stop to ask the user first, because they see the transaction before they sign it. Send only the arguments that apply and leave every other one out: v4 takes 'reserveId'; v3 takes 'market' + 'token' + 'chainId'; 'max' is for withdraw and repay; 'enableCollateral' is for supply. Never send 'permitSignature' or 'permitDeadline' on a first call: they exist only to re-issue a call after an approval step handed you a permit to sign under 'bySignature', so if you have not been handed one, leave both out. Two things that catch callers out: a supply does NOT become collateral unless you pass enableCollateral:true, and without collateral the borrowing power is zero so any later borrow is refused; and collateral pinned by an open borrow cannot be withdrawn, so a withdraw has to repay first. After sending any transaction, poll get_transaction_processed before building the dependent next one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
maxNoWithdraw/repay only: use the entire balance/debt.
tokenNov3 only: underlying token address.
actionYesWhich action to build.
amountNoAmount in MAIN units (e.g. '10.5'), never base units: 100000 base units of a 6-decimal token is '0.1', not '100'. Convert before sending if the user stated base units. Omit only if max=true.
marketNov3 only: market pool address, from a get_markets row in this session. It cannot be recalled: an Aave pool address you already recognise belongs to another deployment (v2, or another chain) and is rejected.
nativeNoUse the chain's native gas token instead of an ERC-20.
senderYesSender wallet address (0x, 40 hex): the wallet that will sign, as the user named it in this session. If no wallet has been named, ask for it; never substitute a placeholder, which is rejected.
chainIdNov3 only: chain id (positive integer).
versionNoOptional: inferred from the reserve selector ('reserveId' is v4, 'market'+'token'+'chainId' is v3). Send it to be explicit, or if you somehow set both.
reserveIdNov4 only: the opaque reserveId, copied verbatim from a get_markets row or a get_position_items item in this session (e.g. 'MTo6MHg5NGU3...Ojo1') - it cannot be constructed or recalled, so fetch one before the first call rather than after a refusal. For a withdraw or a repay take it from get_position_items for the position being acted on, not from get_markets: the same asset exists on several spokes, and the one this wallet supplied is the only one it can exit. The 'spokeId' from get_user_positions is NOT this: it is the same encoding one segment short, names the spoke rather than a reserve inside it, and is rejected. A token symbol such as 'USDC' is rejected too.
permitDeadlineNoUnix seconds, the 'deadline' from the permit message that was signed. Required with permitSignature.
permitSignatureNoSend this only to replay a call after an approval handed you a permit to sign: the user's signature (0x...) over the PermitTypedData that approval carried under 'bySignature', on either version. It replaces the approval transaction, so the action comes back in one step. Requires permitDeadline.
enableCollateralNosupply only: also enable the asset as collateral (default false). Leave it off and the supply earns yield but backs no borrowing, so a following borrow fails for exceeding a borrowing power of zero. Pass true whenever the plan is to borrow against it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / reserveId / description
      Previous value: -"v4 only: the opaque reserveId, copied verbatim from a get_markets row or a get_position_items item in this session (e.g. 'MTo6MHg5NGU3...Ojo1') - it cannot be constructed or recalled, so fetch one before the first call rather than after a refusal. The 'spokeId' from get_user_positions is NOT this: it is the same encoding one segment short, names the spoke rather than a reserve inside it, and is rejected. A token symbol such as 'USDC' is rejected too."New value: +"v4 only: the opaque reserveId, copied verbatim from a get_markets row or a get_position_items item in this session (e.g. 'MTo6MHg5NGU3...Ojo1') - it cannot be constructed or recalled, so fetch one before the first call rather than after a refusal. For a withdraw or a repay take it from get_position_items for the position being acted on, not from get_markets: the same asset exists on several spokes, and the one this wallet supplied is the only one it can exit. The 'spokeId' from get_user_positions is NOT this: it is the same encoding one segment short, names the spoke rather than a reserve inside it, and is rejected. A token symbol such as 'USDC' is rejected too."
    • changedInput schema / properties / sender / description
      Previous value: -"Sender wallet address, 0x-prefixed (40 hex chars)."New value: +"Sender wallet address (0x, 40 hex): the wallet that will sign, as the user named it in this session. If no wallet has been named, ask for it; never substitute a placeholder, which is rejected."
    • changedInput schema / properties / version / description
      Previous value: -"Protocol version (v3 or v4; required, no 'all' for actions)."New value: +"Optional: inferred from the reserve selector ('reserveId' is v4, 'market'+'token'+'chainId' is v3). Send it to be explicit, or if you somehow set both."
    • changedInput schema / required
      Previous value: -[
-  "action",
-  "version",
-  "sender"
-]New value: +[
+  "action",
+  "sender"
+]
  2. Changed2 schema fields changed
    • removedInput schema / properties / reserve
      Removed value: -{
-  "description": "v4 only: the opaque reserveId, copied verbatim from a get_markets row or a get_position_items item in this session (e.g. 'MTo6MHg5NGU3...Ojo1') - it cannot be constructed or recalled, so fetch one before the first call rather than after a refusal. The 'spokeId' from get_user_positions is NOT this: it is the same encoding one segment short, names the spoke rather than a reserve inside it, and is rejected. A token symbol such as 'USDC' is rejected too.",
-  "type": "string"
-}
    • addedInput schema / properties / reserveId
      Added value: +{
+  "description": "v4 only: the opaque reserveId, copied verbatim from a get_markets row or a get_position_items item in this session (e.g. 'MTo6MHg5NGU3...Ojo1') - it cannot be constructed or recalled, so fetch one before the first call rather than after a refusal. The 'spokeId' from get_user_positions is NOT this: it is the same encoding one segment short, names the spoke rather than a reserve inside it, and is rejected. A token symbol such as 'USDC' is rejected too.",
+  "type": "string"
+}
  3. First observed

TDQS

A4.8/5.0
Behavior4/5

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

Annotations already state readOnlyHint=true and destructiveHint=false. The description reinforces this by explaining that building is non-custodial, free, commits the user to nothing, and sends nothing. It also discloses the approval-step and permit-replay behavior, which adds meaningful context beyond the annotations.

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 long, but justified for a 13-parameter tool. It front-loads the core behavior, then flows through simulation guidance, build instructions, parameter rules, and finally the two most common gotchas. Every sentence carries operational value.

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?

For a complex prepare tool with no output schema, the description covers the execution plan return, approval-step possibility, session-context dependencies, cross-version differences, and post-transaction polling. An agent has enough to call it correctly on the first attempt.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds substantial meaning: amount must be in MAIN units with a concrete conversion example, market/reserveId must come verbatim from session data and cannot be recalled or constructed, sender cannot be a placeholder, and enableCollateral has behavioral consequences for later borrows. This is far beyond the schema.

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 opens with a specific verb and resource: "Build an unsigned transaction to supply, borrow, withdraw, or repay on Aave (v3 or v4)." This clearly separates it from sibling prepare_* tools and from preview_action, which is explicitly positioned as the simulation counterpart.

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 gives explicit when-to-use guidance: call preview_action first for borrow/withdraw, read its warnings, build without asking the user, and poll get_transaction_processed before dependent calls. It also tells the agent what not to send on first calls and when permit parameters are appropriate.

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

All Aave toolsInspect
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