mcp-server-weread

Provides an MCP server for WeRead (微信读书) to expose a user’s bookshelf, search results, and book notes/highlights (optionally organized by chapter), plus popular reviews, to MCP-capable LLM clients (e.g., Claude Desktop).

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ Ai Ml mcp we-read personal-data llm-integration nodejs read-it-later notes highlights
⚙ Agent Friendliness
47
/ 100
Can an agent use this?
🔒 Security
36
/ 100
Is it safe for agents?
⚡ Reliability
30
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
65
Error Messages
0
Auth Simplicity
35
Rate Limits
5

🔒 Security

TLS Enforcement
60
Auth Strength
35
Scope Granularity
10
Dep. Hygiene
45
Secret Handling
30

The integration relies on WeRead cookies (high value secrets). The README recommends passing cookies via MCP config env fields or CookieCloud, but does not document transport guarantees, logging behavior, secret redaction, or least-privilege controls. Rate limiting and error-message safety are not described. Dependency list is minimal in manifest, but no vulnerability/CVE evidence is provided.

⚡ Reliability

Uptime/SLA
0
Version Stability
50
Breaking Changes
40
Error Recovery
30
AF Security Reliability

Best When

You have legitimate access to a WeRead account and want an LLM agent to query your personal reading data via MCP.

Avoid When

You cannot safely store/manage the required cookies/credentials, or you need strong guarantees about access methods, data handling, and API stability.

Use Cases

  • Ask an LLM to summarize or analyze a user’s WeRead bookshelf
  • Retrieve and organize notes/highlights from a specific book for downstream reasoning/summarization
  • Search a user’s WeRead library by keyword and then fetch notes/highlights
  • Fetch popular reviews for a book to support recommendations or comparative analysis

Not For

  • Publishing or sharing user-specific library/content publicly without consent
  • Use as a generic book search API not tied to an individual account’s WeRead data
  • Workflows that require a formal/standard WeRead API contract (this appears to rely on cookies/scraping-like access)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Cookie-based authentication (WEREAD_COOKIE) CookieCloud-based cookie retrieval (CC_URL/CC_ID/CC_PASSWORD)
OAuth: No Scopes: No

Auth is performed by providing WeRead session cookies either directly (WEREAD_COOKIE) or via a CookieCloud service. No OAuth flows or explicit scopes are described.

Pricing

Free tier: No
Requires CC: No

Pricing not described in provided content; likely relies on your LLM client’s usage and your WeRead account access.

Agent Metadata

Pagination
supports pagination for get_book_best_reviews (description mentions paging); no general pagination style documented for other tools
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Requires valid, non-expired WeRead cookies; CookieCloud setup failure can break the MCP server
  • Tool inputs/outputs are described at a high level, but without a visible formal schema/examples of error responses, agents may need defensive parsing and retries
  • Because access is cookie-based, intermittent auth failures may occur and should be handled gracefully by the agent/client

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-server-weread.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered