Website Autonomous MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_project_summaryB | Return framework, package manager, scripts and homepage summary. |
| get_project_structureB | Return a depth-limited project tree. |
| get_protected_filesC | Return protected path configuration. |
| search_project_codeC | Search safe text files in the website repository. |
| get_homepage_contextB | Return homepage source and related brand/store resources. |
| get_git_statusB | Return git status. |
| create_task_branchC | Create an ai task branch. |
| get_changed_filesC | Return changed files. |
| get_git_diffB | Return git diff. |
| validate_changed_filesB | Validate changed files against permissions and secret scan. |
| create_commitB | Create a safe commit on a task branch. |
| push_task_branchC | Push current task branch. |
| restore_task_changesB | Restore working-tree changes on a task branch. |
| run_lintC | Run website lint script when configured. |
| run_typecheckB | Run website typecheck. |
| run_unit_testsB | Run website unit/test script. |
| run_production_buildB | Run website production build. |
| run_all_validationA | Run lint, typecheck, tests and build. |
| inspect_pageB | Inspect an internal page for console, network, image and layout issues. |
| capture_responsive_screenshotsC | Capture responsive screenshots for an internal page. |
| get_console_errorsC | Return console errors for an internal page. |
| get_network_errorsC | Return network errors for an internal page. |
| detect_broken_imagesC | Return broken image URLs for an internal page. |
| detect_horizontal_overflowD | Detect horizontal overflow. |
| run_accessibility_checkC | Run deterministic accessibility checks. |
| run_homepage_browser_testA | Run configured homepage Playwright tests. |
| run_visual_analysisC | Run deterministic visual checks. |
| check_vercel_configurationB | Check Vercel preview deployment configuration. |
| create_preview_deploymentA | Create a Vercel preview deployment when configured. |
| get_preview_statusB | Get preview deployment status. |
| verify_preview_websiteC | Verify a preview URL returns a healthy response. |
| request_production_deploymentC | Request gated production deployment. |
| rollback_deploymentC | Return rollback safety status. |
| prepare_website_edit_taskC | Create and prepare a scoped website edit task. |
| finalize_website_edit_taskC | Validate, commit, optionally preview, and report a website edit task. |
| analyze_page_designC | Analyze deterministic page design issues. |
| analyze_design_consistencyC | Analyze design consistency for a page. |
| validate_brand_complianceC | Validate page design against brand resources. |
| generate_design_improvement_planD | Generate a design improvement plan. |
| run_accessibility_auditC | Run axe-core and custom accessibility checks. |
| test_keyboard_navigationC | Check keyboard navigation signals. |
| check_focus_visibilityD | Check visible focus signals. |
| check_touch_targetsC | Check mobile touch target sizes. |
| generate_accessibility_fix_planC | Generate accessibility fix recommendations. |
| audit_page_seoD | Audit page SEO. |
| audit_metadataD | Audit page metadata. |
| audit_heading_structureD | Audit heading hierarchy. |
| audit_internal_linksD | Audit internal links. |
| audit_structured_dataD | Audit structured data. |
| generate_seo_fix_planC | Generate SEO fix recommendations. |
| run_lighthouse_auditC | Run Lighthouse performance audit. |
| analyze_imagesC | Analyze image performance signals. |
| analyze_scriptsD | Analyze script performance signals. |
| analyze_fontsC | Analyze font performance signals. |
| analyze_cachingC | Analyze caching performance signals. |
| generate_performance_fix_planD | Generate performance recommendations. |
| audit_conversion_flowD | Audit conversion flow friction. |
| analyze_cta_hierarchyD | Analyze CTA hierarchy. |
| analyze_product_discoveryC | Analyze product discovery path. |
| analyze_trust_signalsC | Analyze visible trust signals. |
| generate_conversion_planD | Generate conversion recommendations. |
| run_live_diagnosticsD | Run live diagnostics. |
| inspect_browser_consoleC | Inspect browser console errors. |
| inspect_network_failuresC | Inspect failed network requests. |
| inspect_analytics_healthC | Inspect analytics loading signals. |
| inspect_auth_healthC | Inspect authentication health signals without editing protected code. |
| inspect_payment_healthC | Inspect payment health signals without editing protected code. |
| generate_diagnostic_planD | Generate diagnostic recommendations. |
| prepare_landing_page_taskD | Prepare landing page task context. |
| get_landing_page_contextC | Return landing page source context. |
| validate_landing_pageC | Validate landing page prerequisites. |
| finalize_landing_page_taskD | Finalize landing page task validation summary. |
| run_website_auditC | Run a non-destructive multi-agent website audit. |
| generate_website_improvement_planC | Generate prioritized recommendations from a saved audit report. |
| prepare_multi_agent_edit_taskB | Create branch, capture before screenshots, and lock multi-agent edit scope. |
| validate_multi_agent_editC | Validate changed files and secrets for a multi-agent task. |
| finalize_multi_agent_editC | Validate, audit, compare, commit when safe, and optionally create preview. |
| compare_before_afterC | Compare before and after screenshots for a task. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| brand-guidelines | |
| design-tokens | |
| approved-claims | |
| image-guidelines | |
| store-products | |
| homepage-content | |
| project-architecture | |
| protected-files | |
| agents-rules | |
| package-info | |
| test-requirements |
TDQS
Scored across 78 tools
Multiple tools have overlapping purposes, such as run_accessibility_check versus run_accessibility_audit, or inspect_page versus get_console_errors and get_network_errors. The lack of clear boundaries between generic audit tools and their specific variants makes it hard to select the right tool.
All tool names follow a consistent verb_noun pattern in snake_case, e.g., get_project_summary, create_commit, run_lint, audit_page_seo. The verbs vary (get, run, audit, analyze, generate) but the structure is uniform.
With 78 tools, the server far exceeds the 50+ threshold for extreme mismatch. Even for a broad 'website autonomous' purpose, the tool surface is excessively granular, with many near-duplicate audit/analysis functions.
The tool set covers the full lifecycle from project analysis, git operations, validation, testing, deployment, and extensive auditing (design, accessibility, SEO, performance, conversion, diagnostics). Minor gaps exist, such as lack of an actual rollback tool (only rollback_deployment returns safety status) and no branch listing/deleting, but these are workable.