whatsapp-mcp

An MCP server that connects to WhatsApp Web (via whatsmeow), syncs messages to a local SQLite database, and exposes WhatsApp functionality (tools/prompts/resources) to MCP-compatible AI clients over an HTTP/SSE endpoint. It supports chat listing, message retrieval with pagination/sender filtering, cross-chat search, finding chats by fuzzy name, sending messages, loading older history, and retrieving the user profile info.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Communication mcp whatsapp whatsapp-web automation ai-agents go sqlite search
⚙ Agent Friendliness
56
/ 100
Can an agent use this?
🔒 Security
46
/ 100
Is it safe for agents?
⚡ Reliability
26
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
75
Documentation
70
Error Messages
0
Auth Simplicity
85
Rate Limits
20

🔒 Security

TLS Enforcement
70
Auth Strength
45
Scope Granularity
20
Dep. Hygiene
55
Secret Handling
45

Security is described as “API key authentication” and “HTTPS ready,” but details are not provided. The API key is embedded in the URL path, which increases leakage risk via logs, browser history, or intermediary proxies. Data is stored locally and includes sensitive WhatsApp content and session credentials; README warns about file permissions. Unofficial WhatsApp Web integration introduces operational and security risk beyond the typical official API threat model.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
30
Error Recovery
35
AF Security Reliability

Best When

You have a trusted environment, can secure local session/database data, and want an AI agent to interact with WhatsApp through MCP tools.

Avoid When

You cannot secure access to the MCP HTTP endpoint (API key in URL path), your threat model includes attackers who could exfiltrate WhatsApp data, or you require clearly documented rate limits/error semantics for automated agent retries.

Use Cases

  • Let an AI summarize or analyze WhatsApp conversations
  • Search for mentions or keywords across all chats
  • Find and reply to someone’s latest messages with context
  • Workflow-style chat automation via MCP prompts/resources
  • Assist with triage by pulling relevant past messages from a local store

Not For

  • Production-grade, high-assurance WhatsApp automation without due diligence
  • Environments requiring strict compliance guarantees or official WhatsApp API support
  • Use by untrusted users/agents without network isolation and strong operational controls

Interface

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

Authentication

Methods: API key in MCP endpoint URL path (e.g., /mcp/{API_KEY})
OAuth: No Scopes: No

Authentication is described as an API key placed directly in the URL path. The README does not describe fine-grained scopes, rotation, or how the server handles leaked keys (e.g., logging/redaction).

Pricing

Free tier: No
Requires CC: No

Open-source project; no pricing information provided.

Agent Metadata

Pagination
timestamp-based pagination for get_chat_messages; load_more_messages for older history
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • API key is in the URL path; agents/clients or proxies may log URLs (potential key leakage).
  • No documented rate-limit behavior; agents may need conservative retries/backoff to avoid overload.
  • WhatsApp unofficial API may be brittle (session/connection changes), which can impact tool reliability.

Alternatives

Full Evaluation Report

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

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