MCP Server Certified

playwright-mcp

Provides browser automation capabilities through Playwright, enabling LLMs to interact with web pages using structured accessibility data without requiring vision models.

88

/ 100 · Grade B

B = 80–89

I need to automate web browser interactions and extract structured data from web pages without using vision models or screenshots.

browser automationweb testingmcp serveraccessibilityplaywright
Publisher: Microsoft CorporationVersion: 0.0.68Certified: Mar 28, 2026Expires: Mar 28, 2027Source ↗

playwright-mcp earned Certified status with a trust score of 88/100 (Grade B). No adversarial findings — all attack patterns were handled gracefully. Supply chain contains 31 components with 4 known vulnerabilities. Security scan: clean.


Trust Score Breakdown

Eight weighted signals composing the aggregate trust score

security scan
100% × 15w
15.0
supply chain
42% × 10w
4.2
adversarial
100% × 25w
25.0
provenance
100% × 20w
20.0
consumer confirm
83% × 10w
8.3
behavioral pass
83% × 10w
8.3
contract accuracy
93% × 6w
5.6
uptime
100% × 4w
4.0

Scheme v2.0 · Weights provisional · Consumer confirmations and uptime use pipeline-derived baselines.


Findings

Security scan results, adversarial testing, and pipeline review

Security Scan — Cisco MCP Scanner

cisco-mcp-scannerSAFE
yarallmreadiness
critical: 0high: 0medium: 0low: 0
Live scan: error · 0 findings · 16457ms
Code scan: completed · 0 findings · 4631ms

Adversarial Testing — 6 categories, 0 findings

prompt injection chainsprivilege escalationdata exfiltration side channelscapability squattingcontext poisoningdependency confusion

No adversarial findings — all attack patterns handled gracefully.

Methodology v1.0 · 6 categories · ~55 attack patterns


OWASP MCP Top 10 Coverage

Evaluation activity mapped to the OWASP MCP Top 10 risk framework

MCP01 covered

Excessive Agency & Permissions

Cisco scanner behavioral analysis of permission scope

MCP02 covered

Unauthorized Data Access

Category 3 (data exfiltration) attack patterns

MCP03 covered

Tool Poisoning

Category 1 (prompt injection) and Category 5 (context poisoning) attack patterns

MCP04 covered

Supply Chain Vulnerabilities

SBOM generation (syft/cdxgen) and vulnerability scanning (grype/osv-scanner/npm audit)

MCP05 covered

Command Injection

Category 2 (privilege escalation) and Category 6 (repo config injection) attack patterns

MCP06 covered

Intent Subversion

Category 1 (prompt injection) and Category 4 (capability squatting) attack patterns

MCP07 covered

Insecure Data Handling

Cisco scanner data flow and sensitive data handling analysis

MCP08 gap

Insufficient Logging

Not directly tested — logging adequacy requires runtime observation beyond current pipeline scope

MCP09 covered

Resource Exhaustion

Resource profiling (CPU, memory) during functional and adversarial testing

MCP10 covered

Context Injection

Category 5 (context poisoning) attack patterns

OWASP MCP Top 10 (Beta) — owasp.org/www-project-mcp-top-10


Supply Chain

SBOM analysis and vulnerability assessment

Components

31

Direct deps

2

Transitive deps

29

Total vulns

4

Vulnerability breakdown

critical: 0high: 2medium: 0low: 2

Format: CycloneDX 1.5 · Generated: Mar 28, 2026


Behavioral Fingerprint

Runtime performance baseline for drift detection

Samples

1934

Error rate

0.2%

Peak memory

6.5 MB

Avg CPU

—%

Response time distribution

p50: 3msp95: 536msp99: 5864ms

Output size distribution

p50: 162 Bp95: 1.1 KBmean: 1.0 KB

Per-tool performance

Toolp50p95Error rateSamples
browser_drag3ms4ms0.0%207
browser_tabs1ms8ms0.0%79
browser_type3ms4ms0.0%164
browser_click3ms4ms0.0%162
browser_close1ms3ms0.0%6
browser_hover3ms4ms0.0%106
browser_resize1ms17ms0.0%49
browser_install1164ms1464ms0.0%6
browser_evaluate3ms6ms0.0%168
browser_navigate10ms5872ms0.0%76
browser_run_code2ms5ms0.0%74
browser_snapshot7ms9ms0.0%55
browser_wait_for9ms5016ms2.4%122
browser_fill_form3ms7ms0.0%13
browser_press_key1ms10ms0.0%57
browser_file_upload4ms6ms0.0%24
browser_handle_dialog5ms6ms0.0%61
browser_navigate_back5850ms5930ms0.0%6
browser_select_option3ms3ms0.0%111
browser_take_screenshot3ms75ms0.0%207
browser_console_messages1ms10ms0.0%108
browser_network_requests5ms585ms0.0%73

Fingerprint v1.0 · Baseline: Mar 28, 2026 · Status: baseline


Interface

Enumerated tools, resources, and prompts

Tools (22)

browser_close

Close the page

browser_resize

Resize the browser window

browser_console_messages

Returns all console messages

browser_handle_dialog

Handle a dialog

browser_evaluate

Evaluate JavaScript expression on page or element

browser_file_upload

Upload one or multiple files

browser_fill_form

Fill multiple form fields

browser_install

Install the browser specified in the config. Call this if you get an error about the browser not being installed.

browser_press_key

Press a key on the keyboard

browser_type

Type text into editable element

browser_navigate

Navigate to a URL

browser_navigate_back

Go back to the previous page in the history

browser_network_requests

Returns all network requests since loading the page

browser_run_code

Run Playwright code snippet

browser_take_screenshot

Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.

browser_snapshot

Capture accessibility snapshot of the current page, this is better than screenshot

browser_click

Perform click on a web page

browser_drag

Perform drag and drop between two elements

browser_hover

Hover over element on page

browser_select_option

Select an option in a dropdown

browser_tabs

List, create, close, or select a browser tab.

browser_wait_for

Wait for text to appear or disappear or a specified time to pass

Transport: stdio


Scope & Permissions

What this capability can and cannot access — derived from pipeline analysis

creates files

no

deletes files

no

modifies files

no

accesses env variables

yes

invokes external tools

no

makes network requests

yes

Side effects

Makes outbound network requests

Accesses environment variables


Behavioral Guarantees

Claims extracted from publisher documentation — each tagged with provenance

Provides browser automation capabilities using Playwright

author

Enables LLMs to interact with web pages through structured accessibility snapshots

author

Uses Playwright's accessibility tree, not pixel-based input

author

Operates purely on structured data without requiring vision models

author

Provides deterministic tool application

author

Avoids ambiguity common with screenshot-based approaches

author

Bypasses the need for screenshots or visually-tuned models

author

Supports host filtering via --allowed-hosts configuration

author

Supports origin filtering via --allowed-origins configuration

author

Accesses environment variables PLAYWRIGHT_MCP_ALLOWED_HOSTS

author

Known failure modes

Host check can be disabled by passing '*' to --allowed-hosts

Origin filtering does not serve as a security boundary

Sources: author, protocol


Badge & Integration

Embed certification status in your README, docs, or CI pipeline

Fidensa Certified badge for playwright-mcp
badge SVG →attestation API →integration guide →

Certification Notes

Provenance observations from the pipeline

publisher

Publisher "Microsoft Corporation" is not verified — first certification from this publisher

provenance

Single contributor — no peer review evidence in commit history

provenance

Repository is 1 days old — recently created

provenance

Package description appears to be boilerplate or template text


Signed Artifact

Certification provenance and verification metadata

Content hashsha256:79ea7f78a76b131aa9b4d4de1c943a92b6bd4f4d72dd20cef945095f9ef3fd2d
Key IDkms-9db4ed3b9f53
CertifiedMar 28, 2026
ExpiresMar 28, 2027
Pipeline version1.0
Statusvalid