Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Agentic capability / Playwright MCP
◇MCP serverAgentic capabilityFree

Playwright MCP

Microsoft's official MCP server that gives AI agents deterministic browser control via Playwright's accessibility tree.

@ai-supply
Installs34k
⟳ upstream v0.0.79 · updated 12d ago
↗ Source repository
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗
! Grade B · 88/100 · ReviewSecurity assessment
✓No compromise signals9capabilities surfaced1known CVE7of 20 OWASP controls clear
Broad capability surfaceVulnerable dependenciesExternal endpoints declared · expectedExternal endpoints declared · expected
scanned 8d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

Playwright MCP

Playwright MCP is Microsoft's official Model Context Protocol server that lets AI agents drive a real browser through Playwright. Instead of guessing from screenshots, it exposes the page's structured accessibility tree so agents act on semantic elements — making automation fast, deterministic, and reliable without a vision model in the loop.

It is one of the most widely adopted MCP servers, used to give assistants the ability to navigate the web, fill forms, extract content, and verify UI flows.

Key features

  • MCP tools for navigation, clicking, typing, forms, tabs, file uploads, and screenshots
  • Accessibility-tree snapshots for deterministic actions (no pixel guessing required)
  • Works with Claude, VS Code, Cursor, Windsurf, and any MCP client
  • Headless or headed Chromium / Firefox / WebKit with network and console capture
  • Ships as an npx package (npx @playwright/mcp@latest) for zero-install startup

Usage note: register it in your MCP client's server config pointing at @playwright/mcp and grant the origins/actions you want the agent to reach.

Curated mirror of the open-source Playwright MCP (Apache-2.0). Get it from the source.

Rating rank
#1
of 35 in Agentic capability
Install rank
#32
of 35 in Agentic capability
Security score
88/100 · B
review
Security rank
#11
of 35 in Agentic capability
Installs
34k
cat avg 186k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Agentic capability leaderboard →
! Security: Review · 8888/100 · grade Bscanned 8d ago
✓ no compromise signals10 risk-surface · 7/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · med confidence (static)
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → aka.ms, devdiv.pkgs.visualstudio.com, api.esrp.microsoft.com, registry.npmjs.org, portal.microsofticm.com, docs.github.com, playwright.dev, www.conventionalcommits.org +25

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, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM02Sensitive Information Disclosurehigh
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: private key · microsoft-playwright-mcp-7e0457a/tests/testserver/key.pem (CWE-798)expected
⚠LLM03Supply Chainhigh
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 5 npm dependencies declared · microsoft-playwright-mcp-7e0457a/package.jsonrisk surface
•Vulnerable dependencies — 7 known vulnerabilities in: @hono/node-server@1.19.14, body-parser@2.2.2, fast-uri@3.1.4, hono@4.12.31 (CWE-1395)known CVE · -12 pts
⚠LLM07System Prompt Leakagehigh
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Embedded credentials — found: private key · microsoft-playwright-mcp-7e0457a/tests/testserver/key.pem (CWE-798)expected
⚠LLM05Improper Output Handlingmedium
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — child_process exec · microsoft-playwright-mcp-7e0457a/roll.js (CWE-78)expected
⚠LLM06Excessive Agencymedium
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 3 distinct host(s) · microsoft-playwright-mcp-7e0457a/.azure-pipelines/publish.ymlexpected
•External endpoints declared — 1 distinct host(s) · microsoft-playwright-mcp-7e0457a/.claude/skills/release.mdexpected
•External endpoints declared — 7 distinct host(s) · microsoft-playwright-mcp-7e0457a/CONTRIBUTING.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · microsoft-playwright-mcp-7e0457a/README.md (CWE-272)risk surface
•External endpoints declared — 23 distinct host(s) · microsoft-playwright-mcp-7e0457a/README.mdexpected
•External endpoints declared — 4 distinct host(s) · microsoft-playwright-mcp-7e0457a/SECURITY.mdexpected
•External endpoints declared — 2 distinct host(s) · microsoft-playwright-mcp-7e0457a/package.jsonexpected
§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.
✓LLM01Prompt InjectionPassed
✓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.
✓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 Chainhigh
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 5 npm dependencies declared · microsoft-playwright-mcp-7e0457a/package.jsonrisk surface
•Vulnerable dependencies — 7 known vulnerabilities in: @hono/node-server@1.19.14, body-parser@2.2.2, fast-uri@3.1.4, hono@4.12.31 (CWE-1395)known CVE · -12 pts
⚠ML09Output Integritymedium
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — child_process exec · microsoft-playwright-mcp-7e0457a/roll.js (CWE-78)expected
§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.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓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 · microsoft-playwright-mcp-7e0457a/.gitignorerisk surface
•Unrecognized file type — '.npmignore' is not on the allowlist · microsoft-playwright-mcp-7e0457a/.npmignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · microsoft-playwright-mcp-7e0457a/Dockerfilerisk surface
•Unrecognized file type — '.pem' is not on the allowlist · microsoft-playwright-mcp-7e0457a/tests/testserver/cert.pemrisk surface
•Unrecognized file type — '.cnf' is not on the allowlist · microsoft-playwright-mcp-7e0457a/tests/testserver/san.cnfrisk surface
✔ verified source · pinned microsoft-playwright-mcp-7e0457a · changed since last scan (-12 pts) · +egress devdiv.pkgs.visualstudio.com, api.esrp.microsoft.com
Check against a policy

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

Consume Playwright MCP 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/playwright-mcp-browser-automation

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

# CLI
npx ai-supply add playwright-mcp-browser-automation

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

# MCP tool
install_listing({ "slug": "playwright-mcp-browser-automation" })
OpenAPI spec →
vlatest
! Security: Review · 881mo 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

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy