Personal WhatsApp MCP server with a Go bridge and Python MCP server for searching contacts and chats, reading messages, sending messages, sending media, and downloading WhatsApp media.
WhatsApp MCP can search and read personal messages, contacts, chats, media metadata, and message context., Tools can send messages and files to individuals or groups; require human approval before every send action., Prompt injection in messages or media metadata can attempt to exfiltrate private chat data through the agent., Use only with accounts you control and understand the risks of linking third-party automation to WhatsApp., Re-authentication may be required when WhatsApp linked-device sessions expire.
Privacy notes
Personal and group messages, contacts, phone numbers, group identifiers, media metadata, downloaded media paths, attachments, and outgoing message drafts may be exposed to the MCP client and model., Message history is stored locally in SQLite databases under the bridge directory, and media can be downloaded locally on demand., Chat content may include other people's personal data, confidential business information, authentication codes, health data, financial data, or private media.
Author
Luke Harries
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
5 safety and 3 privacy notes across 5 risk areas. Review closely: credentials & tokens, network access, third-party handling.
5 areas
SafetyGeneralWhatsApp MCP can search and read personal messages, contacts, chats, media metadata, and message context.
SafetyLocal filesTools can send messages and files to individuals or groups; require human approval before every send action.
SafetyGeneralPrompt injection in messages or media metadata can attempt to exfiltrate private chat data through the agent.
SafetyThird-party handlingUse only with accounts you control and understand the risks of linking third-party automation to WhatsApp.
SafetyCredentials & tokensRe-authentication may be required when WhatsApp linked-device sessions expire.
PrivacyNetwork accessPersonal and group messages, contacts, phone numbers, group identifiers, media metadata, downloaded media paths, attachments, and outgoing message drafts may be exposed to the MCP client and model.
PrivacyNetwork accessMessage history is stored locally in SQLite databases under the bridge directory, and media can be downloaded locally on demand.
PrivacyGeneralChat content may include other people's personal data, confidential business information, authentication codes, health data, financial data, or private media.
Safety notes
WhatsApp MCP can search and read personal messages, contacts, chats, media metadata, and message context.
Tools can send messages and files to individuals or groups; require human approval before every send action.
Prompt injection in messages or media metadata can attempt to exfiltrate private chat data through the agent.
Use only with accounts you control and understand the risks of linking third-party automation to WhatsApp.
Re-authentication may be required when WhatsApp linked-device sessions expire.
Privacy notes
Personal and group messages, contacts, phone numbers, group identifiers, media metadata, downloaded media paths, attachments, and outgoing message drafts may be exposed to the MCP client and model.
Message history is stored locally in SQLite databases under the bridge directory, and media can be downloaded locally on demand.
Chat content may include other people's personal data, confidential business information, authentication codes, health data, financial data, or private media.
Prerequisites
Go for the WhatsApp bridge.
Python and uv for the MCP server.
WhatsApp mobile app with permission to link a device via QR code.
FFmpeg if you want automatic conversion for playable WhatsApp voice messages.
MCP client such as Claude Desktop, Cursor, or another compatible host.
WhatsApp MCP Server connects MCP clients to a personal WhatsApp account through
a local Go bridge and Python MCP server. It can search contacts, list chats,
read messages, retrieve context, send messages, send media files, send audio
messages, and download media from WhatsApp messages.
The Go bridge authenticates through WhatsApp's linked-device flow and stores
message history in local SQLite databases. The Python MCP server exposes the
tools to Claude Desktop, Cursor, or other MCP clients.
These sources were reviewed on 2026-06-05. Prefer the live repository for
current bridge setup, Python server requirements, Windows compatibility notes,
media behavior, and troubleshooting.
Features
Personal WhatsApp account connection through the WhatsApp web multidevice API.
Local SQLite storage for chat and message history.
Contact search, chat listing, message listing, and message context tools.
Direct and group message sending.
Image, video, document, raw audio, and voice-message support.
Media download tool for retrieving WhatsApp media locally.
Claude Desktop and Cursor setup examples.
Installation
Clone the repository and start the WhatsApp bridge:
git clone https://github.com/lharries/whatsapp-mcp.git
cd whatsapp-mcp/whatsapp-bridge
go run main.go
Scan the QR code with WhatsApp to authenticate, then configure your MCP client to
run the Python server:
Install FFmpeg if you need automatic conversion for playable WhatsApp voice
messages.
Use Cases
Search personal WhatsApp history from an assistant.
Find the last interaction with a contact or group.
Summarize recent chat context before replying.
Draft and review a message before sending it.
Send approved images, videos, documents, or audio files to a selected chat.
Safety and Privacy
WhatsApp messages are deeply personal and often include other people's private
data. Do not let an agent send messages or files without explicit review. Treat
all message content, media, contacts, group names, and phone numbers as
sensitive.
The project README warns that prompt injection can lead to private data
exfiltration. Keep high-trust chats out of automated workflows and avoid asking
the model to process untrusted messages alongside tools that can send data out.
Duplicate Check
No lharries/whatsapp-mcp entry or source URL was found in content/mcp. This
entry is separate from general browser, messaging, or filesystem MCP servers
because it targets a personal WhatsApp account through a local bridge.
Show that WhatsApp MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/whatsapp-mcp-server)
How it compares
WhatsApp MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
Personal WhatsApp MCP server with a Go bridge and Python MCP server for searching contacts and chats, reading messages, sending messages, sending media, and downloading WhatsApp media.
Chrome extension-based MCP server that exposes an existing Chrome browser profile to AI assistants for tab management, page content, screenshots, interaction, history, bookmarks, and network inspection.
Source-install MCP server for controlling a local ComfyUI instance so Claude can generate, view, regenerate, manage, and publish image, audio, and video assets through workflow-backed tools.
✓WhatsApp MCP can search and read personal messages, contacts, chats, media metadata, and message context.
Tools can send messages and files to individuals or groups; require human approval before every send action.
Prompt injection in messages or media metadata can attempt to exfiltrate private chat data through the agent.
Use only with accounts you control and understand the risks of linking third-party automation to WhatsApp.
Re-authentication may be required when WhatsApp linked-device sessions expire.
✓BrowserMCP can navigate pages, click controls, type text, submit forms, capture screenshots, inspect accessibility snapshots, read console logs, and automate the connected tab.
Because it uses the user's real browser profile, logged-in sessions and account permissions may be available to the agent.
Require human approval before purchases, messages, account changes, destructive actions, or actions that violate a site's terms.
Use a test profile or non-production account for end-to-end testing and repetitive automation.
✓This server controls the user's existing Chrome browser profile and can reuse logged-in sessions.
Tools can navigate pages, click elements, fill forms, inspect tabs, capture screenshots, inspect network traffic, read history, manage bookmarks, and inject scripts.
Use a dedicated browser profile for agent work and avoid sensitive accounts unless the workflow explicitly requires them.
Do not allow agents to submit forms, make purchases, change account settings, or perform irreversible actions without human approval.
The project describes itself as early-stage and under active development; test carefully before relying on it for critical workflows.
✓ComfyUI MCP Server can submit prompts and workflows to a local ComfyUI instance, create generated media, poll jobs, cancel jobs, and publish assets into project directories.
Generated images, audio, and video can contain unsafe, infringing, biased, misleading, or policy-sensitive content depending on prompts, models, LoRAs, and workflows.
Publishing tools can copy, compress, convert, overwrite, and update manifest entries for assets, so verify target filenames and directories before use.
Custom workflows can expose arbitrary parameters and may run heavy GPU workloads or fail if nodes, models, or paths are missing.
Keep the server bound to local trusted clients unless you have added appropriate authentication and network controls.
Privacy notes
✓Personal and group messages, contacts, phone numbers, group identifiers, media metadata, downloaded media paths, attachments, and outgoing message drafts may be exposed to the MCP client and model.
Message history is stored locally in SQLite databases under the bridge directory, and media can be downloaded locally on demand.
Chat content may include other people's personal data, confidential business information, authentication codes, health data, financial data, or private media.
✓Connected tab content, screenshots, form fields, console logs, and page state may be exposed to the MCP client and model.
Logged-in pages can contain personal data, customer information, credentials, tokens, internal URLs, or private documents.
Although the project describes local automation, prompts and tool results still flow through the chosen AI application and model provider.
✓Open tabs, page content, screenshots, browsing history, bookmarks, cookies/session-derived page state, and network request metadata may be exposed to the MCP client and model.
Screenshots and network responses can contain credentials, personal data, customer data, tokens, and private documents.
Browser automation prompts may reveal personal browsing habits, internal applications, and authenticated service access.
✓Prompts, negative prompts, generated media, workflow parameters, model names, job IDs, asset metadata, and publish paths can appear in MCP responses, logs, and model transcripts.
Generated assets may be stored in ComfyUI output folders, the MCP asset registry, project publish directories, or manifests.
Do not feed private images, brand assets, customer materials, or regulated media into workflows unless the local model environment is approved for that data.
Review model and workflow licenses before publishing or redistributing generated assets.
Prerequisites
Go for the WhatsApp bridge.
Python and uv for the MCP server.
WhatsApp mobile app with permission to link a device via QR code.
FFmpeg if you want automatic conversion for playable WhatsApp voice messages.
Node.js installed for the MCP server.
Chrome or compatible Chromium browser.
BrowserMCP extension installed from the project site.
MCP client such as Claude, Cursor, VS Code, Windsurf, or another compatible host.
Node.js 20 or newer and npm or pnpm.
Chrome or Chromium browser.
Latest Chrome MCP extension release from the project repository.
Globally installed mcp-chrome-bridge package.
A local ComfyUI installation with required models and workflows.
Python and the repository requirements installed from the source checkout.
The MCP server launched from the cloned repository or with paths adjusted for your client.
Approved prompts, source assets, model licenses, and publish locations for generated media.
Install
git clone https://github.com/lharries/whatsapp-mcp.git && cd whatsapp-mcp/whatsapp-bridge && go run main.go