OpenZeppelin Contracts MCP Server

Official

Overview Schema Source Related Servers Discussions Admin

Solidity RWA

solidity-rwa

Generate a Solidity contract for a real-world asset token using ERC-20 standard. Returns the source code in a Markdown block without writing to disk.

Instructions

Make a real-world asset token that uses the ERC-20 standard. This contract type does not support upgradeability. Experimental, some features are not audited and are subject to change.

Returns the source code of the generated contract, formatted in a Markdown code block. Does not write to disk.

Input Schema

TableJSON Schema

Name	Required	Description
`info`	No	Metadata about the contract and author
`name`	Yes	The name of the contract
`votes`	No	Whether to keep track of historical balances for voting in on-chain governance. Voting durations can be expressed as block numbers or timestamps.
`access`	No	The type of access control to provision. Ownable is a simple mechanism with a single account authorized for all privileged actions. Roles is a flexible mechanism with a separate role for each privileged action. A role can have many authorized accounts. Managed enables a central contract to define a policy that allows certain callers to access certain functions.
`permit`	No	Whether without paying gas, token holders will be able to allow third parties to transfer from their account.
`symbol`	Yes	The short symbol for the token
`premint`	No	The number of tokens to premint for the deployer.
`burnable`	No	Whether token holders will be able to destroy their tokens
`callback`	No	Whether to include support for code execution after transfers and approvals on recipient contracts in a single transaction.
`decimals`	No	The number of decimals used to represent token amounts. Defaults to 18.
`mintable`	No	Whether privileged accounts will be able to create more supply or emit more tokens
`pausable`	No	Whether privileged accounts will be able to pause specifically marked functionality. Useful for emergency response.
`flashmint`	No	Whether to include built-in flash loans to allow lending tokens without requiring collateral as long as they're returned in the same transaction.
`freezable`	No	Whether authorized accounts can freeze and unfreeze accounts for regulatory or security purposes. This feature is experimental, not audited and is subject to change.
`upgradeable`	No	Upgradeability is not available for Stablecoin or RWA.
`chainlinkAce`	No	Chainlink ACE (Automated Compliance Engine) adds token policy enforcement through a separately deployed and configured policy engine (integration guide: https://docs.openzeppelin.com/chainlink-ccip-ace; Chainlink docs: https://docs.chain.link/ace). Defaults to false (disabled). Requires ownable or roles access; combining ACE with CCIP requires roles. This integration does not support ACE together with managed access, Callback (ERC-1363), Flash Minting, a nonzero premint, or bridge modes other than CCIP. Configure policies and register the token with the engine before use; this does not establish legal compliance. Enabling ACE makes the generated contract use BUSL-1.1, overriding info.license. Review the ACE license (https://github.com/smartcontractkit/chainlink-ace/blob/v1.2.0/LICENSE) and additional use grants (https://github.com/smartcontractkit/chainlink-ace/blob/v1.2.0/chainlink-ace-License-grants) before production use.
`restrictions`	No	Whether to restrict certain users from transferring tokens, either via allowing or blocking them. This feature is experimental, not audited and is subject to change.
`premintChainId`	No	The chain ID of the network on which to premint tokens.
`namespacePrefix`	No	The prefix for ERC-7201 namespace identifiers. It should be derived from the project name or a unique naming convention specific to the project. Used only if the contract includes storage variables and upgradeability is enabled. Default is "myProject".
`crossChainBridging`	No	Whether to allow authorized bridge contracts to mint and burn tokens for crosschain transfers. Options are custom bridges on any chain, Chainlink CCIP with a separately configured BurnMintTokenPool (integration guide: https://docs.openzeppelin.com/chainlink-ccip-ace; Chainlink docs: https://docs.chain.link/ccip), to embed an ERC-7786 based bridge directly in the token contract, or to use the SuperchainERC20 standard with the predeployed SuperchainTokenBridge. CCIP requires role-based access control, granting the configured pool MINTER_ROLE on each supported chain, and BURNER_ROLE when Burnable is disabled. With Burnable enabled, any holder can burn their own tokens, including the pool, and burnFrom requires an allowance. The SuperchainERC20 feature is only available on chains in the Superchain, and requires deploying your contract to the same address on every chain in the Superchain.
`crossChainLinkAllowOverride`	No	Whether to allow replacing a crosschain link that has already been registered. Only used if crossChainBridging is set to "erc7786native".

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv1.0.10Oct 19, 2026

addedInput schema / properties / chainlinkAce

Added value: +{
+  "description": "Chainlink ACE (Automated Compliance Engine) adds token policy enforcement through a separately deployed and configured policy engine (integration guide: https://docs.openzeppelin.com/chainlink-ccip-ace; Chainlink docs: https://docs.chain.link/ace). Defaults to false (disabled). Requires ownable or roles access; combining ACE with CCIP requires roles. This integration does not support ACE together with managed access, Callback (ERC-1363), Flash Minting, a nonzero premint, or bridge modes other than CCIP. Configure policies and register the token with the engine before use; this does not establish legal compliance. Enabling ACE makes the generated contract use BUSL-1.1, overriding info.license. Review the ACE license (https://github.com/smartcontractkit/chainlink-ace/blob/v1.2.0/LICENSE) and additional use grants (https://github.com/smartcontractkit/chainlink-ace/blob/v1.2.0/chainlink-ace-License-grants) before production use.",
+  "type": "boolean"
+}

changedInput schema / properties / crossChainBridging / anyOf

Previous value: -[
-  {
-    "anyOf": [
-      {
-        "const": "custom",
-        "type": "string"
-      },
-      {
-        "const": "erc7786native",
-        "type": "string"
-      }
-    ]
-  },
-  {
-    "const": "superchain",
-    "type": "string"
-  }
-]New value: +[
+  {
+    "anyOf": [
+      {
+        "anyOf": [
+          {
+            "const": "custom",
+            "type": "string"
+          },
+          {
+            "const": "chainlink-ccip",
+            "type": "string"
+          }
+        ]
+      },
+      {
+        "const": "erc7786native",
+        "type": "string"
+      }
+    ]
+  },
+  {
+    "const": "superchain",
+    "type": "string"
+  }
+]

changedInput schema / properties / crossChainBridging / description

Previous value: -"Whether to allow authorized bridge contracts to mint and burn tokens for crosschain transfers. Options are to use custom bridges on any chain, to embed an ERC-7786 based bridge directly in the token contract, or to use the SuperchainERC20 standard with the predeployed SuperchainTokenBridge. The SuperchainERC20 feature is only available on chains in the Superchain, and requires deploying your contract to the same address on every chain in the Superchain."New value: +"Whether to allow authorized bridge contracts to mint and burn tokens for crosschain transfers. Options are custom bridges on any chain, Chainlink CCIP with a separately configured BurnMintTokenPool (integration guide: https://docs.openzeppelin.com/chainlink-ccip-ace; Chainlink docs: https://docs.chain.link/ccip), to embed an ERC-7786 based bridge directly in the token contract, or to use the SuperchainERC20 standard with the predeployed SuperchainTokenBridge. CCIP requires role-based access control, granting the configured pool MINTER_ROLE on each supported chain, and BURNER_ROLE when Burnable is disabled. With Burnable enabled, any holder can burn their own tokens, including the pool, and burnFrom requires an allowance. The SuperchainERC20 feature is only available on chains in the Superchain, and requires deploying your contract to the same address on every chain in the Superchain."

changedInput schema / properties / info / properties / license / description

Previous value: -"The license used by the contract, default is \"MIT\""New value: +"The license used by the contract, default is \"MIT\". Ignored when chainlinkAce is enabled: contracts generated with ACE always use BUSL-1.1."

addedInput schema / properties / upgradeable

Added value: +{
+  "const": false,
+  "description": "Upgradeability is not available for Stablecoin or RWA.",
+  "type": "boolean"
+}

Changed1 schema field changedv1.0.5Aug 19, 2026

changedInput schema / properties / crossChainBridging / description

Previous value: -"Whether to allow authorized bridge contracts to mint and burn tokens for cross-chain transfers. Options are to use custom bridges on any chain, to embed an ERC-7786 based bridge directly in the token contract, or to use the SuperchainERC20 standard with the predeployed SuperchainTokenBridge. The SuperchainERC20 feature is only available on chains in the Superchain, and requires deploying your contract to the same address on every chain in the Superchain."New value: +"Whether to allow authorized bridge contracts to mint and burn tokens for crosschain transfers. Options are to use custom bridges on any chain, to embed an ERC-7786 based bridge directly in the token contract, or to use the SuperchainERC20 standard with the predeployed SuperchainTokenBridge. The SuperchainERC20 feature is only available on chains in the Superchain, and requires deploying your contract to the same address on every chain in the Superchain."

Changed1 schema field changedv1.0.2Jun 18, 2026

addedInput schema / properties / decimals

Added value: +{
+  "description": "The number of decimals used to represent token amounts. Defaults to 18.",
+  "type": "string"
+}

Changed3 schema fields changedv1.0.1May 21, 2026

changedInput schema / properties / crossChainBridging / anyOf

Previous value: -[
-  {
-    "const": "custom",
-    "type": "string"
-  },
-  {
-    "const": "superchain",
-    "type": "string"
-  }
-]New value: +[
+  {
+    "anyOf": [
+      {
+        "const": "custom",
+        "type": "string"
+      },
+      {
+        "const": "erc7786native",
+        "type": "string"
+      }
+    ]
+  },
+  {
+    "const": "superchain",
+    "type": "string"
+  }
+]

changedInput schema / properties / crossChainBridging / description

Previous value: -"Whether to allow authorized bridge contracts to mint and burn tokens for cross-chain transfers. Options are to use custom bridges on any chain, or the SuperchainERC20 standard with the predeployed SuperchainTokenBridge. The SuperchainERC20 feature is only available on chains in the Superchain, and requires deploying your contract to the same address on every chain in the Superchain."New value: +"Whether to allow authorized bridge contracts to mint and burn tokens for cross-chain transfers. Options are to use custom bridges on any chain, to embed an ERC-7786 based bridge directly in the token contract, or to use the SuperchainERC20 standard with the predeployed SuperchainTokenBridge. The SuperchainERC20 feature is only available on chains in the Superchain, and requires deploying your contract to the same address on every chain in the Superchain."

addedInput schema / properties / crossChainLinkAllowOverride

Added value: +{
+  "description": "Whether to allow replacing a crosschain link that has already been registered. Only used if crossChainBridging is set to \"erc7786native\".",
+  "type": "boolean"
+}

Changed14 schema fields changedv1.0.0Jan 3, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / access / anyOf

Previous value: -[
-  {
-    "enum": [
-      "ownable",
-      "roles"
-    ],
-    "type": "string"
-  },
-  {
-    "const": "managed",
-    "type": "string"
-  }
-]New value: +[
+  {
+    "anyOf": [
+      {
+        "const": "ownable",
+        "type": "string"
+      },
+      {
+        "const": "roles",
+        "type": "string"
+      }
+    ]
+  },
+  {
+    "const": "managed",
+    "type": "string"
+  }
+]

addedInput schema / properties / crossChainBridging / anyOf

Added value: +[
+  {
+    "const": "custom",
+    "type": "string"
+  },
+  {
+    "const": "superchain",
+    "type": "string"
+  }
+]

removedInput schema / properties / crossChainBridging / enum
```
Removed value: -[
-  "custom",
-  "superchain"
-]
```
removedInput schema / properties / crossChainBridging / type
```
Removed value: -"string"
```

removedInput schema / properties / custodian

Removed value: -{
-  "description": "Whether authorized accounts can freeze and unfreeze accounts for regulatory or security purposes. This feature is experimental, not audited and is subject to change.",
-  "type": "boolean"
-}

addedInput schema / properties / freezable

Added value: +{
+  "description": "Whether authorized accounts can freeze and unfreeze accounts for regulatory or security purposes. This feature is experimental, not audited and is subject to change.",
+  "type": "boolean"
+}

removedInput schema / properties / info / additionalProperties
```
Removed value: -false
```

removedInput schema / properties / limitations

Removed value: -{
-  "anyOf": [
-    {
-      "enum": [
-        false,
-        "allowlist"
-      ],
-      "type": [
-        "boolean",
-        "string"
-      ]
-    },
-    {
-      "const": "blocklist",
-      "type": "string"
-    }
-  ],
-  "description": "Whether to restrict certain users from transferring tokens, either via allowing or blocking them. This feature is experimental, not audited and is subject to change."
-}

addedInput schema / properties / namespacePrefix

Added value: +{
+  "description": "The prefix for ERC-7201 namespace identifiers. It should be derived from the project name or a unique naming convention specific to the project. Used only if the contract includes storage variables and upgradeability is enabled. Default is \"myProject\".",
+  "type": "string"
+}

addedInput schema / properties / restrictions

Added value: +{
+  "anyOf": [
+    {
+      "anyOf": [
+        {
+          "const": false,
+          "type": "boolean"
+        },
+        {
+          "const": "allowlist",
+          "type": "string"
+        }
+      ]
+    },
+    {
+      "const": "blocklist",
+      "type": "string"
+    }
+  ],
+  "description": "Whether to restrict certain users from transferring tokens, either via allowing or blocking them. This feature is experimental, not audited and is subject to change."
+}

addedInput schema / properties / votes / anyOf

Added value: +[
+  {
+    "const": "blocknumber",
+    "type": "string"
+  },
+  {
+    "const": "timestamp",
+    "type": "string"
+  }
+]

removedInput schema / properties / votes / enum

Removed value: -[
-  "blocknumber",
-  "timestamp"
-]

removedInput schema / properties / votes / type
```
Removed value: -"string"
```

First observedAug 15, 2025

TDQS

A3.5/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does a reasonable job: it discloses the return shape ('source code of the generated contract, formatted in a Markdown code block'), the side-effect boundary ('Does not write to disk'), a structural limitation (non-upgradeable), and a stability warning (experimental, partially unaudited, subject to change). It does not add anything about generation constraints or required configuration, but the core behavioral profile is covered.

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

Conciseness4/5

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

Three short sentences that are front-loaded with the core purpose, followed by the upgradeability limitation and stability caveat, then the return/output behavior. No filler or repetition, though the experimental warning could be folded more tightly into the constraint sentence.

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?

For a 21-parameter code generator there is no output schema, but the description explicitly states what is returned (Markdown code block) and that nothing is written to disk, which is exactly the information an agent needs about the result. Parameter semantics are fully carried by the schema, so the main remaining gap is the absence of selection guidance against siblings.

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% across all 21 parameters, including rich enum and constraint documentation (access modes, ACE compatibility limits, bridging options), so the schema does the heavy lifting. The description adds no parameter-level meaning beyond what is already documented, which is the expected baseline when coverage is complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Make a real-world asset token that uses the ERC-20 standard.' An agent can tell it produces an RWA token contract rather than a generic ERC-20. However, it never distinguishes itself from the sibling solidity-erc20 or solidity-stablecoin, both of which also emit ERC-20-based contracts, leaving the selection basis implicit.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance or named alternative. The note 'This contract type does not support upgradeability' is a capability constraint that implies a filtering condition, but the description never says which sibling to reach for instead when upgradeability or other features are required. Usage is left entirely to inference.

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

Solidity RWA

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools