Skip to main content
Glama
readwiseio

Readwise MCP

Official
by readwiseio

Readwise MCP (Deprecated)

This MCP server is deprecated. Please use the new Readwise MCP server instead: readwise.io/mcp

The new server is hosted — no local installation needed. It supports both Readwise and Reader data, and works with Claude Desktop, ChatGPT, Claude Code, Cursor, and any MCP-compatible app.


Migration

Replace your existing claude_desktop_config.json entry with the new server. Setup instructions for all clients are at readwise.io/mcp.

If you also want CLI access and agent skills, see readwise.io/cli.


Related MCP server: Reader MCP Server

Installation in Claude

  1. Please make sure you have Node installed.

  2. Open Claude desktop app.

  3. Navigate to Settings > Developer.

  4. Click Edit Config.

  5. Add the following entry to the claude_desktop_config.json file, replacing ACCESS_TOKEN value with your Readwise Access Token.

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

Troubleshooting

For general troubleshooting guidance, please refer to the official Model Context Protocol Claude Desktop Troubleshooting section.

"Could not attach to MCP server Readwise MCP"

A very likely reason for this to happen is that you have an incorrect npx/Node version set up. If you're using nvm, try running nvm use 18 in your terminal. If not, consider reinstalling Node.

Errors when calling Readwise tools

When using this MCP server, you may occasionally encounter MCP errors during your conversations with Claude. If you experience such errors, we recommend trying to switch between different Claude models (e.g., from Claude 3.5 Haiku to Claude 3.7 Sonnet) as this often resolves the issue.

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. Dates show when Glama detected each change.

  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

TDQS

D1.8/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools, making disambiguation perfect. The single tool's purpose is inherently distinct by default.

Naming Consistency5/5

A single tool cannot exhibit inconsistency in naming patterns, so it is trivially consistent. The name 'search_readwise_highlights' follows a clear verb_noun format.

Tool Count2/5

One tool is too few for a server named 'Readwise MCP', which suggests a broader scope for interacting with Readwise services (e.g., highlights, books, tags). A single search tool feels thin and incomplete for this domain.

Completeness2/5

The tool surface is severely incomplete for a Readwise integration. It only offers search for highlights, lacking basic operations like creating, updating, or deleting highlights, or accessing other Readwise resources such as books or tags, which are essential for full coverage.

Maintenance

ActivityInactive
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/readwiseio/readwise-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server