Un servidor de Protocolo de Contexto de Modelo (MCP) para interactuar con la cadena de bloques Ethereum.
Este servidor MCP proporciona herramientas para consultar datos de la cadena de bloques de Ethereum mediante métodos JSON-RPC estándar. Permite que los asistentes y aplicaciones de IA interactúen con la cadena de bloques de Ethereum mediante un protocolo estandarizado.
Related MCP server: Geth MCP Proxy
Este servidor MCP proporciona tres métodos clave de RPC de Ethereum como herramientas:
eth_getCode : recupera el código en una dirección específica de Ethereum
eth_gasPrice : obtiene el precio actual del gas en la red Ethereum
eth_getBalance : Consulta el saldo de una cuenta Ethereum
Nota: Vienen más
Para agregar este MCP al cursor:
Primero, clona este repositorio:
git clone https://github.com/yourusername/eth-mpc.gitVaya a Configuración del cursor → MCP → Agregar nuevo servidor MCP
Introduzca un nombre (por ejemplo, "eth-mcp")
Seleccione "comando" como tipo
Ingrese la ruta completa al script:
node /path/to/eth-mpc/index.js
Haga clic en "Agregar" para habilitar el servidor
Una vez agregadas, las herramientas Ethereum RPC estarán disponibles para usar dentro de Cursor.
El servidor utiliza el transporte stdio, lo que lo hace compatible con clientes MCP como Claude Desktop, Cursor y otros.
El Inspector MCP es una herramienta de desarrollo para probar y depurar servidores MCP. Ofrece una interfaz interactiva para probar la funcionalidad de su servidor MCP sin necesidad de un cliente de IA completo.
Para probar su servidor Ethereum RPC MCP con el Inspector:
Para ejecutar el Inspector:
npx @modelcontextprotocol/inspectorIngrese el comando y la ruta
El Inspector se conectará a su servidor MCP en ejecución y mostrará las herramientas disponibles.
El Inspector le permite:
Ver las herramientas disponibles y sus descripciones
Pruebe cada herramienta con diferentes parámetros
Vea las respuestas en un formato estructurado
Depure cualquier problema con la implementación de su servidor MCP
Por ejemplo, para probar la herramienta eth_getBalance :
Seleccione la herramienta en la interfaz del Inspector
Ingrese una dirección de Ethereum válida (por ejemplo, 0xd8dA6BF26964aF9D7eEd9e03E53415D37aA96045 - dirección de Vitalik)
Utilice el parámetro de bloque predeterminado ( latest )
Enviar la solicitud y ver la respuesta
Este servidor MCP se puede integrar con cualquier cliente compatible con MCP, incluidos:
Escritorio de Claude
Claude Code
Cursor (instrucciones anteriores)
Cline
Otras aplicaciones compatibles con MCP
Una vez integrado, la aplicación cliente puede utilizar las herramientas proporcionadas por este servidor para consultar directamente los datos de la cadena de bloques Ethereum.
El Protocolo de Contexto de Modelo (MCP) es un estándar abierto que permite a los modelos de IA interactuar con diversas herramientas y servicios. Proporciona una forma estandarizada para que los desarrolladores expongan API, fuentes de datos y funcionalidades a los asistentes de IA.
Los servidores MCP como este forman parte de un ecosistema que permite a los asistentes de IA realizar tareas complejas en múltiples servicios sin requerir una integración personalizada para cada servicio.
Documentación oficial : Descripción general del protocolo de contexto del modelo
Instituto Tecnológico de Massachusetts (MIT)
¡Agradecemos sus contribuciones! No dude en enviar una solicitud de incorporación de cambios.
Retrieves the current gas price in wei
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses the tool's behavior as a retrieval operation, which implies it's read-only and non-destructive. However, it lacks details on potential rate limits, error conditions, or response format, which would enhance transparency for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without any unnecessary words. It is appropriately sized and front-loaded, making it easy to understand quickly with zero waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no annotations, no output schema), the description is minimally adequate. It explains what the tool does but lacks details on return values or behavioral nuances. For a retrieval tool with no structured output information, it could benefit from specifying the response format to be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0 parameters with 100% coverage, so the schema fully documents the absence of inputs. The description adds no parameter information, which is appropriate here. Baseline is 4 for 0 parameters, as no compensation is needed for schema gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Retrieves') and resource ('current gas price in wei'), distinguishing it from sibling tools like eth_getBalance (which retrieves account balance) and eth_getCode (which retrieves contract code). It precisely defines what the tool does without being vague or tautological.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context by specifying 'current gas price,' suggesting it should be used when needing real-time gas price information. However, it does not explicitly state when to use this tool versus alternatives or provide any exclusions, leaving some ambiguity about optimal use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieves the balance of a given Ethereum address
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | The Ethereum address to check balance | |
| blockParameter | No | Block parameter (default: "latest") | latest |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('retrieves') but fails to add context such as read-only nature, potential rate limits, authentication needs, or error conditions. This leaves significant gaps in understanding the tool's behavior beyond basic functionality.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and efficiently conveys the core functionality, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description is incomplete for a tool with two parameters and no behavioral context. It adequately states what the tool does but lacks details on usage, behavioral traits, or return values, which are crucial for effective agent operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, meaning the input schema already fully documents the parameters (address and blockParameter). The description does not add any additional meaning or clarification beyond what the schema provides, so it meets the baseline for adequate but unenhanced parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('retrieves') and resource ('balance of a given Ethereum address'), making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like eth_gasPrice or eth_getCode, which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives or any contextual prerequisites. It lacks explicit usage scenarios, exclusions, or comparisons to sibling tools, leaving the agent without direction on tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieves the code at a given Ethereum address
| Name | Required | Description | Default |
|---|---|---|---|
| address | Yes | The Ethereum address to get code from | |
| blockParameter | No | Block parameter (default: "latest") | latest |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool retrieves code but doesn't mention whether this is a read-only operation (implied but not explicit), potential rate limits, error conditions (e.g., invalid address), or what 'code' entails (e.g., bytecode, source code). This leaves significant gaps for a tool interacting with blockchain data.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of Ethereum interactions and lack of annotations or output schema, the description is incomplete. It doesn't explain return values (e.g., hex-encoded bytecode), error handling, or behavioral traits like idempotency. For a tool with no structured safety or output information, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting both parameters (address and blockParameter). The description adds no additional meaning beyond this, such as explaining why blockParameter matters or address format nuances. Baseline 3 is appropriate since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('retrieves') and resource ('code at a given Ethereum address'), making the tool's purpose understandable. However, it doesn't differentiate from sibling tools like eth_getBalance (which retrieves balance rather than code), so it doesn't reach the highest score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like eth_getBalance or eth_gasPrice. It lacks context about typical use cases (e.g., verifying contract deployment, analyzing smart contracts) or prerequisites, leaving the agent without usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0eth_gasPriceeth_getBalanceeth_getCodeScored across 3 tools
Each tool has a clearly distinct purpose: eth_gasPrice retrieves network gas price, eth_getBalance retrieves account balance, and eth_getCode retrieves contract code. There is no overlap or ambiguity between these functions, making tool selection straightforward for an agent.
All tool names follow a consistent eth_verbNoun pattern (eth_gasPrice, eth_getBalance, eth_getCode), using snake_case and the same prefix. This predictable naming scheme enhances readability and agent usability without any deviations.
With only 3 tools, this server feels thin for an Ethereum RPC server, as it lacks core operations like sending transactions, querying blocks, or checking transaction status. The count is too low for the apparent scope of Ethereum interaction, limiting functionality.
The tool surface is severely incomplete for an Ethereum RPC domain. It includes only read-only queries (gas price, balance, code) but omits essential operations such as eth_sendTransaction, eth_getTransactionByHash, or eth_blockNumber, creating significant gaps that will cause agent failures in typical workflows.
Safety-first EVM and Bitcoin RPC tools for balances, contracts, blocks, and transactions
Provide AI agents and automation tools with contextual access to blockchain data including balance…
Read-only on-chain intelligence for AI agents on Base: balances, tokens, gas, tx status.
Read-only on-chain intelligence for AI agents on Base: balances, tokens, gas, tx status.