Skip to main content
Glama
enesjakozh
readwiseio

Readwise MCP

Official
by readwiseio
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

MCP de lectura inteligente

precompromiso

Descripción general

El Protocolo de Contexto de Modelo (MCP) estandariza cómo las aplicaciones proporcionan contexto a los Modelos de Lenguaje Grandes (LLM), lo que garantiza una separación clara entre la gestión del contexto y la interacción directa con los LLM.

Este proyecto es un servidor MCP local diseñado para actuar como puente entre los clientes LLM (como Claude ) y Readwise .

¡Mira una demostración!

Related MCP server: Reader MCP Server

Instalación en Claude

  1. Asegúrese de tener Node instalado.

  2. Abra la aplicación de escritorio de Claude.

  3. Vaya a Configuración > Desarrollador.

  4. Haga clic en Edit Config .

  5. Agregue la siguiente entrada al archivo claude_desktop_config.json , reemplazando el valor ACCESS_TOKEN con su token de acceso Readwise .

{
  "mcpServers": {
    "Readwise MCP": {
      "command": "npx",
      "args": [
        "-y",
        "@readwise/readwise-mcp"
      ],
      "env": {
        "ACCESS_TOKEN": "XXXXXXXXX"
      }
    }
  }
}

Solución de problemas

Para obtener orientación general sobre resolución de problemas, consulte la sección oficial de solución de problemas del Protocolo de contexto de modelo de Claude Desktop.

A continuación se presentan soluciones específicas a problemas comunes que hemos encontrado y resuelto.

"No se pudo conectar al servidor MCP Readwise MCP"

Una razón muy probable para que esto suceda es que tengas configurada una versión incorrecta de npx/Node. Si usas nvm , prueba a ejecutar nvm use 18 en tu terminal. De lo contrario, considera reinstalar Node.

Errores al llamar a herramientas Readwise

Al usar este servidor MCP, es posible que ocasionalmente experimente errores de MCP durante sus conversaciones con Claude. Si experimenta estos errores, le recomendamos cambiar entre diferentes modelos de Claude (por ejemplo, de Claude 3.5 Haiku a Claude 3.7 Sonnet), ya que esto suele resolver el problema.

Available Tools

1 tool
search_readwise_highlightsD
ParametersJSON Schema
NameRequiredDescriptionDefault
vector_search_termYes
full_text_queriesYes

TDQS

D1/5.0
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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. 1 tool updatev0.0.2
    • Changedsearch_readwise_highlights1 field changed
      • addedInput schema / properties / full_text_queries / maxItems
        Added value: +8
  2. 1 tool updatev1.0.0
    • First observedsearch_readwise_highlights
Deploy Server
Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

TDQS

D1.7/5.0

Scored across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusing it with other tools. Its purpose is clearly identifiable from its name despite the missing description.

Naming Consistency5/5

The single tool name follows a clear verb_noun pattern (search_readwise_highlights). With only one tool, naming consistency is inherently maintained.

Tool Count2/5

A single tool is far too limited for a Readwise MCP server, which would be expected to support listing, retrieving, tagging, or managing highlights in addition to searching.

Completeness1/5

The surface is severely incomplete: only a search operation is exposed, with no way to retrieve specific highlights, browse by tag, or perform any other meaningful Readwise actions. This creates a dead-end workflow for most use cases.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers