Skip to content
ai-supply.store
探索分类排行榜社区Agent APIFAQ
登录免费注册
catalog / Marketing / WhatsApp MCP Server
◇MCP serverMarketingFree

WhatsApp MCP Server

Read, search, and send your personal WhatsApp messages and media from an AI assistant.

@ai-supply
安装量7.6k
↗ 源代码仓库
← More MarketingMarketing leaderboard →How we grade security →Source ↗

WhatsApp MCP Server

whatsapp-mcp is a Model Context Protocol server that connects your personal WhatsApp account to AI assistants like Claude.

It lets the agent search and read your messages (including images, videos, documents, and audio), search contacts, and send messages and media to individuals or groups. It connects through the WhatsApp Web multidevice API using the whatsmeow library and stores messages locally in SQLite — data is only sent to the LLM when the agent explicitly accesses it via tools.

It is intended for individuals who want an AI assistant that can read and send their WhatsApp messages. As the README notes, like many messaging MCP servers it carries prompt-injection / data-exfiltration risks.

Rating rank
#1
of 13 in Marketing
Install rank
#12
of 13 in Marketing
Security score
100/100 · A
safe
Security rank
#1
of 13 in Marketing
Installs
7.6k
cat avg 80k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Marketing leaderboard →
✓ Security: Safe · 100100/100 · grade Ascanned 39m ago
✓ no compromise signals7 risk-surface · 7/20 OWASP controls flagged

Only compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score. Dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to the OWASP control it belongs to below.

What this capability can do · high confidence (static)
Tools (12)
search_contactslist_messageslist_chatsget_chatget_direct_chat_by_contactget_contact_chatsget_last_interactionget_message_contextsend_messagesend_filesend_audio_messagedownload_media
⚑ filesystem⚑ shell⚑ network
egress → docs.google.com, simonwillison.net, astral.sh, www.msys2.org, code.visualstudio.com, modelcontextprotocol.io, mmg.whatsapp.net

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not.

OWASP Top 10 for LLM Applications
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Vulnerable dependencies — 104 known vulnerabilities in: filippo.io/edwards25519@1.1.0, golang.org/x/crypto@0.36.0, golang.org/x/net@0.37.0, golang.org/x/sys@0.31.0, stdlib@1.24.1, h11@0.14.0, idna@3.10, mcp@1.6.0 (CWE-1395)risk surface
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · lharries-whatsapp-mcp-7d6a06d/README.md (CWE-77)risk surface
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — pipe-to-shell install · lharries-whatsapp-mcp-7d6a06d/README.md (CWE-494)risk surface
•Path traversal sequences — '../' present in content or name · lharries-whatsapp-mcp-7d6a06d/whatsapp-bridge/main.go (CWE-22)risk surface
•Suspicious code patterns — OS command execution · lharries-whatsapp-mcp-7d6a06d/whatsapp-mcp-server/audio.py (CWE-78)risk surface
⚠LLM06Excessive Agencylow
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 7 distinct host(s) · lharries-whatsapp-mcp-7d6a06d/README.mdrisk surface
•External endpoints declared — 1 distinct host(s) · lharries-whatsapp-mcp-7d6a06d/whatsapp-bridge/main.gorisk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
◷LLM10Unbounded ConsumptionRuntime-enforced
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
✓LLM02Sensitive Information DisclosurePassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM07System Prompt LeakagePassed
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Vulnerable dependencies — 104 known vulnerabilities in: filippo.io/edwards25519@1.1.0, golang.org/x/crypto@0.36.0, golang.org/x/net@0.37.0, golang.org/x/sys@0.31.0, stdlib@1.24.1, h11@0.14.0, idna@3.10, mcp@1.6.0 (CWE-1395)risk surface
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · lharries-whatsapp-mcp-7d6a06d/README.md (CWE-77)risk surface
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — pipe-to-shell install · lharries-whatsapp-mcp-7d6a06d/README.md (CWE-494)risk surface
•Path traversal sequences — '../' present in content or name · lharries-whatsapp-mcp-7d6a06d/whatsapp-bridge/main.go (CWE-22)risk surface
•Suspicious code patterns — OS command execution · lharries-whatsapp-mcp-7d6a06d/whatsapp-mcp-server/audio.py (CWE-78)risk surface
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (5) · hygiene / uncategorized
•Unrecognized file type — '.gitignore' is not on the allowlist · lharries-whatsapp-mcp-7d6a06d/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · lharries-whatsapp-mcp-7d6a06d/LICENSErisk surface
•Unrecognized file type — '.mod' is not on the allowlist · lharries-whatsapp-mcp-7d6a06d/whatsapp-bridge/go.modrisk surface
•Unrecognized file type — '.sum' is not on the allowlist · lharries-whatsapp-mcp-7d6a06d/whatsapp-bridge/go.sumrisk surface
•Unrecognized file type — '.python-version' is not on the allowlist · lharries-whatsapp-mcp-7d6a06d/whatsapp-mcp-server/.python-versionrisk surface
✔ verified source · pinned lharries-whatsapp-mcp-7d6a06d · changed since last scan · +egress docs.google.com, simonwillison.net, astral.sh, www.msys2.org, code.visualstudio.com, modelcontextprotocol.io
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/whatsapp-mcp-server/check). Click a policy:

Consume WhatsApp MCP Server programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/whatsapp-mcp-server

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/whatsapp-mcp-server/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add whatsapp-mcp-server

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/whatsapp-mcp-server/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "whatsapp-mcp-server" })
OpenAPI spec →
vlatest
✓ Security: Safe · 1005h ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

免费、经过安全审核的 AI 能力——技能、MCP、插件、agent、数据集等一应俱全，每一项都经过安全评级与时效追踪，为人类与 agent 共同打造。

api · v3.1status · all green
联系
support@ai-supply.storesecurity@ai-supply.store
目录
  • 探索
  • 分类
  • 排行榜
  • 基准测试
  • 安全
社区
  • 社区
  • FAQ
面向智能体
  • 快速入门 (60s)
  • 授权智能体
  • Agent API
  • OpenAPI 规范
面向开发者
  • 发布
  • 控制台
账户
  • 创建账户
  • 登录
  • 设置
法律条款
  • 条款
  • 发布者协议
  • 可接受使用政策
  • 隐私政策