Skip to main content
Glama
enesjakozh
JohanCodinha

nREPL MCP Server

by JohanCodinha
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Servidor MCP nREPL

Un servidor de Protocolo de Contexto de Modelo (MCP) diseñado para clientes MCP, como Claude Desktop o CLine en VSCode. Este servidor se puede usar con cualquier LLM cuando se usa con CLine. Este servidor permite la interacción con una instancia nREPL de Clojure en ejecución, lo que permite la evaluación del código de Clojure, la inspección de espacios de nombres y otras utilidades mediante MCP.

Características

  • Conéctese a un servidor nREPL en ejecución especificando el host y el puerto.

  • Evalúa el código de Clojure en un espacio de nombres determinado o en el actual.

  • Enumere los espacios de nombres del proyecto utilizando tools.namespace .

  • Recupere el estado de la conexión nREPL , incluidos los detalles del host, el puerto y la sesión.

  • Inspeccione las variables públicas en cualquier espacio de nombres de Clojure, mostrando metadatos como cadenas de documentación y valores.

Related MCP server: mcp-nrepl

Instalación y configuración

Instalación en CLine (VSCode) o Claude Desktop

Para utilizar este servidor con CLine o Claude Desktop , siga estos pasos:

  1. Abra CLine en VSCode o Claude Desktop .

  2. Vaya a Configuración de MCP .

  3. Agregue un nuevo servidor MCP con la siguiente configuración:

    {
  "mcpServers": {
    "nrepl-mcp-server": {
      "command": "npx",
      "args": [
        "nrepl-mcp-server"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

  4. Guarde y reinicie el cliente para aplicar los cambios.

Esto permitirá que el cliente se comunique con el servidor MCP nREPL a través de entrada/salida estándar.

Instalar mediante npx

Para ejecutar rápidamente el servidor sin clonar el repositorio:

npx nrepl-mcp-server

Instalación manual

  1. Clonar el repositorio

  2. Instalar dependencias

    npm install

  3. Construir el proyecto (transpila TypeScript a JavaScript)

    npm run build

  4. Ejecutar el servidor

    • Modo de producción : se ejecuta desde la salida compilada.

      npm start

    • Modo de desarrollo : utiliza ts-node para cambios en vivo.

      npm run dev

Esto inicia el servidor, que escucha en STDIO las solicitudes MCP. El cliente MCP iniciará el servidor automáticamente.

Comportamiento

Conexión a nREPL

Permite establecer una conexión a un servidor nREPL especificando un host y un puerto .

Evaluación del código Clojure

Ejecuta expresiones Clojure arbitrarias en el espacio de nombres predeterminado o en un espacio de nombres especificado .

Recuperación de información del espacio de nombres

Enumera todos los espacios de nombres en el directorio del proyecto actual usando tools.namespace .

Inspección de variables públicas

Obtiene metadatos y valores actuales para todas las variables públicas en un espacio de nombres especificado.

Obteniendo el estado de la conexión nREPL

Proporciona detalles sobre la conexión nREPL actual, incluido el host, el puerto, la ID de sesión y el último error (si lo hubo).

Recursos

nrepl://status

Proporciona información sobre la conexión nREPL actual, incluyendo:

  • Host y puerto

  • Estado de la conexión

  • ID de sesión activa

nrepl://namespaces

Enumera todos los espacios de nombres detectados en el directorio del proyecto.

Contribuyendo

¡Agradecemos sus contribuciones! Si tiene sugerencias sobre funciones o reportes de errores, abra un problema o una solicitud de incorporación de cambios.

Licencia

Este proyecto está licenciado bajo la Licencia MIT . Puede modificarlo y distribuirlo libremente según sus términos.

Available Tools

3 tools
connectB

Connect to an nREPL server. Example: (connect {:host "localhost" :port 1234})

ParametersJSON Schema
NameRequiredDescriptionDefault
hostYesnREPL server host
portYesnREPL server port

TDQS

B3.4/5.0
Behavior2/5

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 ('Connect') but does not disclose behavioral traits such as whether this is a one-time or persistent connection, error handling, authentication needs, or what happens upon successful connection. The example adds minimal context but leaves key operational details unspecified.

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 extremely concise and front-loaded, with the first sentence stating the purpose clearly and the second providing a practical example. Every sentence earns its place by reinforcing understanding without unnecessary elaboration.

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

Completeness2/5

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

Given the complexity of a connection tool with no annotations and no output schema, the description is incomplete. It lacks information about what the tool returns upon success or failure, connection persistence, or error conditions, which are critical for an agent to use it effectively in a workflow.

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?

The schema description coverage is 100%, with both parameters ('host' and 'port') well-documented in the schema. The description adds an example that illustrates parameter usage but does not provide additional semantic meaning beyond what the schema already specifies, such as format constraints or default values.

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 states the specific action ('Connect to') and target resource ('an nREPL server'), with an example that reinforces the purpose. It distinguishes itself from sibling tools like 'eval_form' and 'get_ns_vars' by focusing on establishing a connection rather than evaluating code or retrieving namespace variables.

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

Usage Guidelines3/5

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

The description implies usage when needing to establish a connection to an nREPL server, but it does not provide explicit guidance on when to use this tool versus alternatives or any prerequisites. The example suggests typical usage scenarios but lacks context about timing or dependencies.

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

eval_formA

Evaluate Clojure code in a specific namespace or the current one. Examples:

  • Define and call a function: {"code": "(defn greet [name] (str "Hello, " name "!"))(greet "World"))"}

  • Reload code: {"code": "(clj-reload.core/reload)"}

  • Evaluate in a specific namespace: {"code": "(clojure.repl.deps/sync-deps)", "ns": "user"}

ParametersJSON Schema
NameRequiredDescriptionDefault
codeYesClojure code to evaluate
nsNoOptional namespace to evaluate in. Changes persist for subsequent evaluations.

TDQS

A3.9/5.0
Behavior3/5

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 that namespace changes 'persist for subsequent evaluations,' which is useful behavioral context. However, it lacks details on error handling, side effects, or performance implications, leaving gaps for a mutation tool.

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 appropriately sized and front-loaded, starting with a clear purpose statement followed by specific examples. Each sentence earns its place by illustrating use cases without unnecessary elaboration, making it efficient and easy to understand.

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

Completeness3/5

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

Given the tool's complexity (evaluating code with potential side effects), no annotations, and no output schema, the description is moderately complete. It covers purpose and usage examples but lacks details on return values, error formats, or security considerations, which are important for a code evaluation tool.

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%, so the schema already documents both parameters ('code' and 'ns'). The description adds value by providing examples that illustrate parameter usage, such as showing code snippets and namespace context, but does not add new semantic details beyond what the schema provides.

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 states the tool's purpose: 'Evaluate Clojure code in a specific namespace or the current one.' It specifies the verb ('evaluate'), resource ('Clojure code'), and scope ('specific namespace or the current one'), distinguishing it from sibling tools like 'connect' and 'get_ns_vars' which likely serve different functions.

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?

The description provides clear context for usage through examples, such as defining functions, reloading code, and evaluating in a namespace. However, it does not explicitly state when to use this tool versus alternatives like 'get_ns_vars' or any exclusions, leaving some ambiguity in tool selection.

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

get_ns_varsB

Get all public vars (functions, values) in a namespace with their metadata and current values. Example:

  • List main namespace vars: (get_ns_vars {:ns "main"}) Returns a map where keys are var names and values contain:

  • :meta - Metadata including :doc string, :line number, :file path

  • :value - Current value of the var

ParametersJSON Schema
NameRequiredDescriptionDefault
nsYesNamespace to inspect

TDQS

B3.4/5.0
Behavior3/5

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 describes the return format (a map with keys as var names and values containing metadata and current values), which is helpful, but doesn't cover aspects like permissions needed, rate limits, error conditions, or whether it's a read-only operation (though 'Get' implies reading).

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?

The description is appropriately sized and front-loaded with the core purpose in the first sentence. The example and return format details are useful but could be slightly more streamlined. Overall, it's efficient with minimal waste.

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

Completeness3/5

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

Given the tool's moderate complexity (1 parameter, no output schema, no annotations), the description is somewhat complete but has gaps. It explains the return structure well, but lacks information on usage context, error handling, and behavioral traits like safety or performance considerations.

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%, so the schema already documents the single parameter 'ns' as 'Namespace to inspect'. The description adds an example usage with {:ns "main"} but doesn't provide additional semantic context beyond what the schema states, such as namespace format or scope limitations.

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 states the verb 'Get' and resource 'all public vars (functions, values) in a namespace with their metadata and current values', which is specific and comprehensive. It distinguishes from sibling tools (connect, eval_form) by focusing on namespace inspection rather than connection or evaluation operations.

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?

The description provides no guidance on when to use this tool versus alternatives. It includes an example usage but doesn't mention prerequisites, constraints, or compare it to sibling tools like eval_form, which might also interact with namespace variables.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updates
    • First observedconnect
    • First observedeval_form
    • First observedget_ns_vars
Deploy Server
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

TDQS

A3.5/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: connect establishes a connection, eval_form evaluates code, and get_ns_vars inspects namespace variables. There is no overlap or ambiguity between these three functions.

Naming Consistency4/5

The naming follows a consistent snake_case pattern (connect, eval_form, get_ns_vars), with all tools using descriptive verb-noun combinations. The minor deviation is that 'connect' is a single verb while others are compound, but this is reasonable given its action.

Tool Count3/5

With only 3 tools, the set feels thin for an nREPL server, which typically involves more operations like disconnecting, listing sessions, or handling side effects. However, it covers basic connectivity, evaluation, and inspection, which are core functions.

Completeness2/5

The tool surface has significant gaps for an nREPL server: there is no way to disconnect or manage sessions, handle errors or interrupts, load files, or perform other common REPL operations. This limits agents to basic tasks and may cause failures in more complex workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • mcp-nrepl

    conao3
    A
    license
    Not graded
    quality
    D
    maintenance
    Connects to nREPL servers to evaluate Clojure code interactively, enabling AI assistants like Claude to run Clojure code in real-time.
    Apache 2.0

  • Claude Code Manager WAN

    medelmouhajir
    F
    license
    Not graded
    quality
    C
    maintenance
    Enables ISLI agents and MCP clients to dispatch natural-language coding and terminal tasks to a locally-installed Claude Code CLI, supporting both one-shot execution and persistent sessions with workspace and security controls.
    -

Appeared in Searches