Readwise ReaderSAFE
A Model Context Protocol (MCP) server for the Readwise Reader API, built with TypeScript and the official Claude SDK.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server for the Readwise Reader API, built with TypeScript and the official Claude SDK.
Features
- Secure Authentication: Uses environment variables for token storage
- Document Management: Save, list, update, and delete documents with complete metadata
- Tag Management: List and filter by tags
- Rich Filtering: Filter documents by location, category, tags, and more
- Pagination Support: Handle large document collections
- LLM-Friendly Content: HTML content automatically converted to clean text using r.jina.ai
- Complete Data Access: Returns full document information including content, metadata, and timestamps
API Documentation
For detailed information about the Readwise Reader API endpoints, parameters, and examples, please refer to the official API documentation:
📖 [Readwise Reader API Documentation](https://readwise.io/reader_api)
This MCP server implements all the core endpoints described in the official documentation.
Installation
npm install npm run build
Configuration
With Claude Desktop
- Build the MCP server:
npm install npm run build
- Get your Readwise access token from: https://readwise.io/access_token
- Add the server to your Claude Desktop configuration. Open your Claude Desktop settings and add this to your MCP servers configuration:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"readwise-reader": {
"command": "node",
"args": ["/path/to/your/reader_readwise_mcp/dist/index.js"],
"env": {
"READWISE_TOKEN": "your_readwise_access_token_here"
}
}
}
}Replace:
/path/to/your/reader_readwise_mcpwith the actual path to this project directoryyour_readwise_access_token_herewith
a3348b30649dOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add readwise-reader-mcp --env READWISE_TOKEN=${READWISE_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"readwise-reader-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"READWISE_TOKEN": "${READWISE_TOKEN}"
}
}
}
}Exposed tools (6)
3 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
readwise_delete_document | destructive | Delete a document from Readwise Reader |
readwise_list_documents | read | List documents from Readwise Reader with optional filtering |
readwise_list_tags | read | List all tags from Readwise Reader |
readwise_save_document | write | Save a document (URL or HTML content) to Readwise Reader |
readwise_topic_search | read | Search documents in Readwise Reader by topic using regex matching on title, summary, notes, and tags |
readwise_update_document | write | Update a document in Readwise Reader |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
readwise_delete_document
@modelcontextprotocol/sdk, dotenv, node-html-parser, @types/jest, @types/node, jest, ts-jest, tsx
Gates applied: no_behavioural_pass.
a3348b30649dfull audit observations/trust-audit/mcp-server/edricgsh__readwise-reader.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | a3348b30649d | SAFE | B | 89 | first audit |
Questions
What is the Readwise Reader MCP server?
A Model Context Protocol (MCP) server for the Readwise Reader API, built with TypeScript and the official Claude SDK.
What tools does Readwise Reader expose?
6 in total: 3 read-only, 2 that write, and 1 that can delete or overwrite (readwise_delete_document). Every one is listed on this page with its risk.
Is Readwise Reader safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Readwise Reader need?
It reads READWISE_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Readwise Reader run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as readwise-reader-mcp at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (a3348b30649d), read on 2026-10-08. The repository is watched and re-audited when it changes.