navigate
Navigate to a URL and take a screenshot. Pass _browserToken from a previous tool call to reuse the same browser session.
click
Click an element on the page. MUST pass _browserToken from previous tool call to click on the same page. Without it, clicks go to a blank new browser.
smart_click
Click with auto-retry and self-healing selectors. v11.8.0: Added confidence gating - only reports success if healed selector has >= 60% confidence.
dismiss_overlay
Detect and dismiss modal overlays (cookie consent, age verification, newsletter popups). Constitutional Yellow zone.
fill
Fill a form field with text. MUST pass _browserToken from previous tool call to interact with the same page.
scroll
Scroll the page. MUST pass _browserToken from previous tool call to scroll the same page.
screenshot
Take a screenshot of the current page. IMPORTANT: If you received a _browserToken from a previous tool call (navigate, cognitive_journey_init), you MUST pass it here to see the same page. Without it, you get a blank new browser.
extract
Extract data from the page. Pass _browserToken to use the same browser session.
assert
Assert a condition using natural language
analyze_page
Analyze page structure for forms, buttons, links
generate_tests
Generate test scenarios for a page
find_element_by_intent
AI-powered semantic element finding with ARIA-first selector strategy. Prioritizes aria-label > role > semantic HTML > ID > name > class. Returns selectorType, accessibilityScore (0-1), and alternatives. Use verbose=true for enriched failure responses.
ai_benchmark
Compare AI-friendliness across competitor sites. Runs agent-ready audits on each URL, ranks by AI readiness grade, and identifies what each competitor does better for AI agents. Use for competitive intelligence on AI-readiness.
save_session
Save browser session (cookies, storage) for later use
load_session
Load a previously saved session
list_sessions
List all saved sessions with metadata (name, domain, cookies count, localStorage keys, created date, size)
delete_session
Delete a saved session by name
heal_stats
Get self-healing selector cache statistics
visual_baseline
Capture a visual baseline using Wasserstein barycenter. Takes multiple screenshots, rejects outliers, computes optimal consensus reference with adaptive threshold. Robust to dynamic content, animations, and timing variations.
visual_regression
Run visual regression test against a baseline. Automatically uses smart regression (Wasserstein) if a smart baseline exists for this name, otherwise falls back to traditional comparison.
cross_browser_test
Test page rendering across multiple browsers
cross_browser_diff
Quick diff of page metrics across browsers
responsive_test
Test page across different viewport sizes
ab_comparison
Compare two URLs visually (staging vs production)
transport_map
Generate a Visual Transport Map showing WHERE visual content moved between two screenshots. Produces heatmap, flow arrows, hotspots, and SVG visualization.
attention_analysis
Analyze where a persona's visual attention goes on a page using Wasserstein saliency. Produces attention alignment, entropy, concentration, and top attention areas. Based on Klein & Frintrop W₂ on CIE-Lab distributions.
attention_compare
Compare attention patterns between two personas on the same page. Shows where they look differently and the Wasserstein divergence between their saliency maps.
nl_test_file
Run natural language test suite from a file. Returns step-level results with enriched error info, partial matches, and suggestions.
nl_test_inline
Run natural language tests from inline content. Returns step-level results with enriched error info, partial matches, and suggestions.
repair_test
AI-powered test repair for broken tests
detect_flaky_tests
Detect flaky/unreliable tests by running multiple times
coverage_map
Generate test coverage map for a site
hunt_bugs
Autonomous bug hunting - crawl and find issues. Returns bugs with severity, selector, and actionable recommendation for each issue found.
chaos_test
Inject failures and test resilience
compare_personas
Compare how different user personas experience a journey. In Claude Code sessions (no API key), use compare_personas_init and compare_personas_complete instead for the bridge workflow.
compare_personas_init
Initialize persona comparison for Claude Code bridge workflow. Returns persona profiles and instructions for running journeys without API key.
compare_personas_complete
Complete persona comparison by aggregating journey results. Call this after running all persona journeys via the bridge workflow.
cognitive_distance
Compute the Wasserstein cognitive distance between two personas. Returns W₁ distance (true cognitive distance), per-trait contributions, and Bures-Wasserstein W₂ distance. Based on optimal transport theory — transport cost = cognitive processing cost.
cognitive_coverage
Select the N most cognitively different personas from a list for maximum test coverage. Uses greedy farthest-point sampling in Wasserstein space.
cognitive_interpolate
Generate an interpolated persona between two known personas using Wasserstein geodesic. Preserves trait coupling structure — the midpoint between ADHD and power-user has intermediate trait correlations, not just averaged values.
cognitive_load_estimate
Estimate cognitive load for a specific persona on page metrics. Returns per-dimension breakdown (information, visual, attention, decision, motor, text, memory, patience) and identifies the bottleneck dimension.
cognitive_journey_init
Initialize a cognitive user journey simulation. Returns the persona's cognitive profile, initial state, and abandonment thresholds. The actual simulation is driven by the LLM using browser tools (navigate, click, fill, screenshot) while tracking cognitive state.
cognitive_journey_update_state
Update the cognitive state during a journey simulation. Call this after each action to track mental state.
list_cognitive_personas
List all available personas with their cognitive traits (includes accessibility and emotional personas)
persona_values_list
List all Schwartz's 10 Universal Values with their meanings, plus higher-order values, Self-Determination Theory needs, and Maslow levels. Use this to understand the values framework before looking up specific personas.
persona_values_lookup
Look up the values profile for a persona (Schwartz's 10 Universal Values, SDT needs, Maslow level). Values describe WHO the persona is at a deeper motivational level, informing influence susceptibility.
list_influence_patterns
List research-backed behavioral persuasion patterns (Cialdini, Kahneman) and which persona values correlate with susceptibility to each pattern.
persona_questionnaire_get
Get the persona questionnaire for building a custom persona. Returns research-backed questions that map to cognitive traits. Use comprehensive=true for all 25 traits, or leave false for 8 core traits. v16.12.0: Now includes optional category question for disability-specific value safeguards.
persona_questionnaire_build
Build a custom persona from questionnaire answers with category-aware value safeguards. Answers should be a map of trait names to values (0-1). Missing traits will use intelligent defaults based on research correlations. v16.12.0: Optionally specify category for disability-specific value handling.
persona_trait_lookup
Look up behavioral descriptions for specific trait values. Useful for understanding what a trait value means in practice.
persona_category_guidance
Get guidance for value assignment based on persona category. (v16.12.0) Explains research basis for why cognitive, physical, sensory, and emotional disability categories require different value handling approaches.
perf_baseline
Capture performance baseline for a URL
perf_regression
Detect performance regression against baseline with configurable sensitivity. Uses dual thresholds: both percentage AND absolute change must be exceeded. Profiles: strict (perf envs, FCP 10%/50ms), normal (default, FCP 20%/100ms), ci (automated pipelines, FCP 25%/150ms), lenient (dev, FCP 30%/200ms).
list_baselines
List all saved baselines (visual and performance)
agent_ready_audit
Audit a website for AI-agent friendliness. Analyzes findability, stability, accessibility, and semantics. Returns score (0-100), grade (A-F), issues, and remediation recommendations.
competitive_benchmark
Compare UX across competitor sites. Runs identical cognitive journeys on multiple sites and generates head-to-head comparison with rankings, friction analysis, and recommendations.
empathy_audit
Simulate how real users experience a site. Accepts ANY persona — disability personas get specialized barrier detection, non-disability personas get general UX analysis with a flag. Tests ONE persona per call. Disability: motor-impairment-tremor, low-vision-magnified, cognitive-adhd, dyslexic-user, deaf-user, elderly-low-vision, color-blind-deuteranopia. General: first-timer, power-user, mobile-user, elderly-user, impatient-user, or any custom persona.
webmcp_ready_audit
Audit an MCP server for Claude in Chrome / WebMCP compatibility. Uses 6-tier evaluation: Server Implementation (25%), Tool Discoverability (20%), Instrumentation (15%), Consistency (15%), Agent Optimizations (15%), Documentation (10%). Returns score (0-100), grade (A-F), tier breakdown, issues, and recommendations.
status
Get CBrowser environment status and diagnostics including data directories, installed browsers, configuration, self-healing cache statistics, and MCP tool count
browser_health
Check if the browser is healthy and responsive. Use this before operations if you suspect the browser may have crashed.
browser_recover
Attempt to recover from a browser crash by restarting the browser process. Use this when browser_health returns unhealthy.
reset_browser
Reset the browser to a clean state. Clears all cookies, localStorage, sessionStorage, and browser state. Use this when you need a fresh browser environment.
security_audit
Audit MCP tool definitions for potential prompt injection attacks. Scans tool descriptions for cross-tool instructions, privilege escalation attempts, and data exfiltration patterns. Works with: local config file (Claude Desktop), remote MCP URL (Claude.ai connectors), or self-scan of current server.
remediation_patches
Generate code patches to fix agent-ready audit issues. Returns before/after code snippets with explanations, sorted by impact. Run agent_ready_audit first to get issues.
llms_txt_generate
Generate an llms.txt file from a website. Extracts title, description, and navigation structure in the llms.txt format for AI-readable site descriptions.
structured_data_suggest
Suggest Schema.org JSON-LD structured data for a page. Detects page type (article, product, organization, etc.) and generates appropriate schema markup.
llms_txt_validate
Validate an llms.txt file for format compliance and link validity. Checks for proper markdown structure, valid URLs, and optionally verifies links are reachable. Use to ensure llms.txt files follow the specification.
llms_txt_diff
Compare a site's current structure against its existing llms.txt file. Detects pages that have been added, removed, or changed. Use to keep llms.txt up to date as your site evolves.
page_understand
Analyze the current page to understand its type, available actions, form structure, and navigation. Returns a rich page model with affordances, structure, and element relationships. Useful before interacting with a page to know what's possible.
site_model_status
Show what CBrowser knows about a site from previous interactions. Returns navigation graph stats, element reliability scores, known goal paths, and failure patterns.
site_model_query
Query the site model for the best known path to achieve a goal type on a domain. Returns the most successful action sequence if one exists.
site_profile_list
List all persistent site profiles (saved browser state per domain). Shows which sites have saved cookies, localStorage, and auth state.
site_profile_delete
Delete a persistent site profile for a domain. Removes saved cookies, localStorage, and auth state.
site_profile_status
Check the health of a site profile. Shows cookie count, expiry status, auth state, and whether the profile is still usable.
persona_create_start
Start creating a custom persona. Best practice: present the choice to the user via AskUserQuestion (questionnaire vs description mode) rather than showing raw JSON.
persona_create_questionnaire_start
Start the questionnaire mode for persona creation. Each question is best presented via AskUserQuestion for interactive selection.
persona_create_questionnaire_answer
Submit an answer for the current questionnaire question. Returns instructions for the next question, or completed persona when done.
persona_create_from_description
Create a persona from a text description. Returns trait reference matrix for Claude to infer appropriate values.
persona_create_submit_traits
Submit inferred traits for a persona created from description. Use after persona_create_from_description.
persona_create_cancel
Cancel the current persona creation questionnaire session.
persona_traits_list
List all available cognitive traits with descriptions. Useful for understanding what traits can be customized.
ask_user
Create a structured prompt to ask the user a question. Returns AskUserQuestion-compatible format. Use this when you need user input before proceeding. Claude should present this to the user and return their selection.
marketing_campaign_create
Create a multi-variant × multi-persona marketing campaign for influence effectiveness testing.
marketing_personas_list
List available marketing personas with their traits.
marketing_campaign_report_result
Report the result of a cognitive journey run back to a campaign.
set_api_key
[Enterprise] Set the Anthropic API key for autonomous cognitive journeys.
clear_api_key
[Enterprise] Clear the stored API key from session memory.
api_key_status
[Enterprise] Check if an API key is currently stored in session.
get_api_key_prompt
[Enterprise] Get instructions for obtaining an Anthropic API key.
cognitive_journey_autonomous
[Enterprise] Run a fully autonomous cognitive journey with AI decision-making.
marketing_campaign_run
[Enterprise] Execute a marketing campaign with cognitive journeys.
marketing_influence_matrix
[Enterprise] Generate influence pattern effectiveness matrix.
marketing_lever_analysis
[Enterprise] Analyze psychological levers in campaign results.
marketing_funnel_analyze
[Enterprise] Compare conversion funnels across variants.
marketing_compete
[Enterprise] Compare effectiveness against competitor URLs.
marketing_audience_discover
[Enterprise] Discover who your site is optimized for using randomized cognitive journeys.
marketing_discover_status
[Enterprise] Check the status of an async audience discovery job.
stealth_status
[Enterprise] Check the current stealth mode configuration and status.
stealth_enable
[Enterprise] Enable stealth mode to evade bot detection.
stealth_check
[Enterprise] Check if an action is allowed on a URL with stealth mode.
stealth_disable
[Enterprise] Disable stealth mode.
stealth_diagnose
[Enterprise] Diagnose bot detection methods on a URL.
cloudflare_detect
[Enterprise] Detect if the current page shows a Cloudflare challenge or block.
cloudflare_wait
[Enterprise] Wait for a Cloudflare challenge to complete on the current page.
web_security_scan
[Enterprise] Passive web security vulnerability analysis for authorized domains. Checks OWASP top-10 indicators: security headers, cookie flags, form security, XSS indicators, open redirects, mixed content, CORS, clickjacking, information disclosure, and subresource integrity.