Application Launcher

MCP server documentation | Web Governance | Acquia Product Documentation

Introduction

This document provides information about the Web Governance Monsido MCP server.

Field	Value
Endpoint	https://api.monsido.com/mcp
Protocol version	`2024-11-05`
Auth	Bearer token (JWT)

Connection configuration (OpenCode and Claude)

"monsido-mcp-server": {
"type": "remote",
"url": "https://api.monsido.com/mcp",
"headers": {
"Authorization": "Bearer <JWT token>"
},
"enabled": true
}

The server advertises support for the following:

Tools (with listChanged)
Prompts (with listChanged)
Resources
Logging
UI extension (`io.modelcontextprotocol/ui`)

Tools

In the Web Governance suite,13 tools are live. These are grouped by capability area as per the following:

Tool	Area	Input mode
`html_scans`	Accessibility + full scan

Tool

Area

Input mode

html_scans

Accessibility

+ full scan

Note

Input mode pattern: Most capability areas offer three variants:

Live URL
Stored Web Governance page (through domain_id + page_id)
Raw text/HTML

Use resolve_url_to_ids to look up domain_id/page_id for any known URL.

Accessibility tools

The following sections provide information about the accessibility tools.

HTML scan

html_scan

Title: HTML Scan
Tags: accessibility, html, scan
Read-only: yes
Description: The system does a scan on the raw HTML and its page-processing-lib encoded_page for accessibility, readability, SEO, and data-protection findings. Use this tool when you already have processed page data. Use render_by_url_with_guideline for live rendered URL accessibility checks.

Input

Parameter

Note

Do not use this option for rules that require a real page URL/title, stored metadata, link graph, readability, or image records. Use run_policies_page_id for those instead.

Input

Parameter	Type	Required	Description
`policy_id`	`integer`	✅	The ID of the policy to evaluate (one per call).
`content`	`string`	✅

Note

Do not use this option for rules that are derived from crawl/database data (such as incoming/external link counts, stored metadata, readability, or image records). No domain targeting check is performed.

Input

Parameter	Type	Required	Description
`url`	`string`	✅	The URL that the scan must fetch and evaluate.
`policy_id`

Note

This option is not a live fetch. Use run_policies_url for a fresh check or run_policies_snippet for draft content.

Input

Introduction

This document provides information about the Web Governance Monsido MCP server.

Field	Value
Endpoint	https://api.monsido.com/mcp
Protocol version	`2024-11-05`
Auth	Bearer token (JWT)

Connection configuration (OpenCode and Claude)

"monsido-mcp-server": {
"type": "remote",
"url": "https://api.monsido.com/mcp",
"headers": {
"Authorization": "Bearer <JWT token>"
},
"enabled": true
}

The server advertises support for the following:

Tools (with listChanged)
Prompts (with listChanged)
Resources
Logging
UI extension (`io.modelcontextprotocol/ui`)

Tools

In the Web Governance suite,13 tools are live. These are grouped by capability area as per the following:

Tool	Area	Input mode
`html_scans`	Accessibility + full scan

Tool

Area

Input mode

html_scans

Accessibility

+ full scan

Note

Input mode pattern: Most capability areas offer three variants:

Live URL
Stored Web Governance page (through domain_id + page_id)
Raw text/HTML

Use resolve_url_to_ids to look up domain_id/page_id for any known URL.

Accessibility tools

The following sections provide information about the accessibility tools.

HTML scan

html_scan

Title: HTML Scan
Tags: accessibility, html, scan
Read-only: yes
Description: The system does a scan on the raw HTML and its page-processing-lib encoded_page for accessibility, readability, SEO, and data-protection findings. Use this tool when you already have processed page data. Use render_by_url_with_guideline for live rendered URL accessibility checks.

Input

Parameter

Note

Do not use this option for rules that require a real page URL/title, stored metadata, link graph, readability, or image records. Use run_policies_page_id for those instead.

Input

Parameter	Type	Required	Description
`policy_id`	`integer`	✅	The ID of the policy to evaluate (one per call).
`content`	`string`	✅

Note

Input

Parameter	Type	Required	Description
`url`	`string`	✅	The URL that the scan must fetch and evaluate.
`policy_id`

Note

This option is not a live fetch. Use run_policies_url for a fresh check or run_policies_snippet for draft content.

Input

Tool	Area	Input mode
`html_scans`	Accessibility + full scan

Field	Type	Description
`title`	`string`	The page title that the system extracted from the HTML.
`contents`	`object`	The general page content metadata.
`data`	`object`	Structured data that the system finds on the page.
`texts`	`object`	Text content that the system extracts from the page
`readability`	`number \| null`	The readability score.
`readability_level`	`string \| null`	The human-readable readability level.
`readability_reason`	`string \| null`	An explanation of the readability score.
`links`	`array`	Links that the system finds on the page.
`accessibility_errors`	`array`	Accessibility violations (per selected WCAG level).
`seo_issues`	`array`	SEO issues that the system finds.
`data_protection_violations`	`array`	Data protection and privacy violations.
`data_protection_violations_truncated`	`boolean`	Indicates if the system truncated the data protection list.

Usage notes

Parameter	Type	Required	Description
`url`	`string`	✅	The full URL, including protocol (for example, `https://example.com/page`). The page is rendered in a browser before the scan begins.
`accessibility_guideline`	`string \| null`	❌	The WCAG conformance level. Use `WCAG22-AA` for most cases. If omitted, accessibility result fields may be null.
`accessibility_errors_only`	`boolean`	❌	If `true`, the system returns violations only. If `false`, the system may include warnings and review checks. The default setting is `false`.
`max_errors`	`integer \| null`	❌	The maximum number of errors that the system will return. Omit for 1 error per unique check; `0` for summary only; `N` for first N errors grouped by check.

Output

This output includes rendered HTML, HTTP status, accessibility summary, and grouped errors (schema varies by guideline and the max_errors setting).

Usage notes

Preferred over html_scans when you only have a URL and no pre-processed page data.
JavaScript rendering is applied automatically. Use this for SPAs and dynamically-rendered pages.

Accessibility remediation source code

accessibility_remediation_source_code

Title: Accessibility Remediation Source Code
Tags: accessibility, remediation, source_code
Read-only: no
Description: If there are one or more HTML snippets and an accessibility check identifier, the system returns each fixed snippet with a plain-language description that explains what changed and the reason for the change.

Input

Parameter	Type	Required	Description
`check_id`	`integer`	✅	The Web Governance accessibility check identifier (from `html_scans` or `render_by_url_with_guideline` results).
`source_codes`	`array<string>`	✅	One or more HTML source code snippets to remediate.

Output

This output returns a result array, one item per input snippet:

Field	Type	Description
`original`	`string`	The original snippet as provided.
`fixed`	`string`	The remediated snippet.
`description`	`string`	Plain-language explanation of what changed and why.

Usage notes

Multiple snippets can be sent in a single call; results are returned in the same order.
Always do a new scan after you apply fixes in order to confirm a clean resolution.

Spelling tools

The platform provides tree variants. Use the one that matches your available input. All of the variants require the Spell Check (qa_spellcheck) plan feature.

Spellling text snippet

spelling_text_snippet

Title: Spelling Text Snippet
Tags: check, content, spelling
Read-only: yes
Description: The system checks for spelling errors in a plain text snippet. The system returns misspelled words and the language that they were checked against.

Input

Parameter	Type	Required	Description
`text`	`string`	✅	The text snippet that the system checks for spelling errors.
`language`	`string \| null`	❌	ISO 639-1 language code (for example, `en`, `da`). The system defaults to English if this information is not provided.

Output

This output returns a result array of spelling errors with misspelled words and language context.

Usage notes

Best for targeted checks, such as:

A specific paragraph
A flagged term from a policy violation
A sentence that is under review

Spelling URL

spelling_url

Title: Spelling URL
Tags: check, content, spelling
Read-only: yes
Description: The system checks for spelling errors on a live URL. The crawler does a scan on the page, detects the language of each text block, and returns misspelled words.

Input

Parameter	Type	Required	Description
`url`	`string`	✅	Full URL including protocol (for example, `https://example.com`)
`language`	`string \| null`	❌	ISO 639-1 language override. If omitted, the system auto-detects the language from page content.
`enable_javascript`

Output

This output returns a result array of spelling errors across the page.

Usage notes

Use these for live site monitoring or pre-publish checks when you have a URL rather than raw HTML.
Enable enable_javascript for dynamically-rendered content.

Spelling page ID

spelling_page_id

Title: Spelling Page ID
Tags: check, content, spelling
Read-only: yes
Description: The system checks for misspelled words on a stored Web Governance page using data from the last successful scan. This option is fast. The system does not do a live network request.

Input

Parameter	Type	Required	Description
`domain_id`	`integer`	✅	The ID of the domain that the page belongs to.
`page_id`	`integer`	✅	The ID of the page to check.

Output

This output returns a result array of spelling errors from the last crawl.

Usage notes

This is the fastest spelling option. The system returns stored results, it does not do a new crawl.
Use resolve_url_to_ids to get domain_id and page_id from a URL.

Readability tools

Three variants. All variants return the same core output form.

Readability text snippet

readability_text_snippet

Title: Readability Text Snippet
Tags:content, readability, score
Read-only: yes
Description: The system calculates readability by analyzing raw text directly.

Input

Parameter	Type	Required	Description
`text`	`string`	✅	Plain text to analyze.
`test_engine`	`string \| null`	❌	`lix` for multilingual content; `flesch_kincaid_re` for English only.

Output

This output returns the following:

Field	Type	Description
`score`	`number`	The Readability score
`level`	`string`	Human-readable level (such as: `"Easy"`, `"Difficult"`, `"Legal / Technical"`)
`test_engine`	`string`	The algorithm that the system used.

Readability page

readability_page

Title: Readability Page
Tags: page, readability, score
Read-only: yes
Description: The system retrieves readability for a page already stored in Web Governance. This option is fast. The system returns the results from the most recent successful scan, it does not do a new scan on the page.

Input

Parameter	Type	Required	Description
`domain_id`	`integer`	✅	Domain ID (must already be scanned in Web Governance).
`page_id`	`integer`	✅	Page ID (must exist within the scanned domain).

Field	Type	Description
`score`	`number`	Readability score
`level`	`string`	Human-readable level
`test_engine`	`string`	Algorithm used
`reason`	`string`	Explanation of the score

There are tree variants. All require the

Policies

(policies_all) plan feature. Each call evaluates one policy at a time. Loop over policy IDs to evaluate multiple rules.

Field	Type	Description
`id`	`integer`	Policy ID
`name`	`string`	Policy name
`mode`	`string`	Policy mode
`priority`	`string`	Policy priority
`subject`	`string`	What the policy evaluates
`matches`	`array`	Content that matched/violated the policy
`ignored`	`array`	Matches that were ignored
`url`	`string \| null`	Associated URL if applicable

Parameter	Type	Required	Description
`url`	`string`	✅	The URL to resolve. Exact match by default; set `partial=true` for contains matching.
`partial`	`boolean`	❌	Use contains matching instead of exact URL matching.
`domain_ids`	`array<integer>`	❌	Limit the search to specific domain IDs. Required when `include_domain_group_ids` is `true`.
`max_per_domain`	`integer`	❌	Maximum pages to return per domain. If the cap is reached, `truncated=true` in the response.
`include_domain_group_ids`	`boolean`	❌	If `true`, stamps `domain_group_ids` on each page result. Requires `domain_ids` to be set.

Output

The system groups the results by domain, each domain contains matching pages with their domain_id and page_id. If truncated=true, retry with domain_ids and/or a more specific URL.

Usage notes

This is the entry point for any workflow that starts with a URL and needs to call a _page_id tool.
Use partial=true when you have a partial URL or want to find all pages under a path.

Resources and prompts

The server currently exposes no resources and no prompts.

Example workflows

Accessibility check and fix from a URL

1. render_by_url_with_guideline(url, accessibility_guideline="WCAG22-AA")
→ Collect: accessibility errors with check_ids and source snippets
2. accessibility_remediation_source_code(check_id, source_codes)
→ Collect: fixed HTML snippets with descriptions
3. Re-run render_by_url_with_guideline to confirm clean resolution

Full content quality check on a live URL

1. render_by_url_with_guideline(url, accessibility_guideline="WCAG22-AA")
→ Accessibility errors
2. spelling_url(url)
→ Spelling errors
3. readability_url(url)
→ Readability score and flagged sentences
4. run_policies_url(url, policy_id) [repeat per policy]
→ Policy violations
5. accessibility_remediation_source_code for auto-fixable errors

Checking a draft before publish (no live URL yet)

1. html_scans(html, encoded_page, accessibility="WCAG22-AA")
→ Full scan: accessibility, SEO, readability, data protection
2. spelling_text_snippet(text)
→ Spelling errors in the draft body copy
3. run_policies_snippet(policy_id, content=html, content_type="html") [repeat per policy]
→ Policy violations against draft HTML
4. For any readability concerns: readability_text_snippet(text)
→ Targeted readability score on specific paragraphs

Bulk audit using stored Web Governance data

1. resolve_url_to_ids(url)
→ Get domain_id and page_id
2. spelling_page_id(domain_id, page_id)
→ Spelling errors from last crawl (fast, no network call)
3. readability_page(domain_id, page_id)
→ Readability score from last crawl
4. run_policies_page_id(domain_id, page_id, policy_id) [repeat per policy]
→ Policy violations from last crawl

Field	Type	Description
`title`	`string`	The page title that the system extracted from the HTML.
`contents`	`object`	The general page content metadata.
`data`	`object`	Structured data that the system finds on the page.
`texts`	`object`	Text content that the system extracts from the page
`readability`	`number \| null`	The readability score.
`readability_level`	`string \| null`	The human-readable readability level.
`readability_reason`	`string \| null`	An explanation of the readability score.
`links`	`array`	Links that the system finds on the page.
`accessibility_errors`	`array`	Accessibility violations (per selected WCAG level).
`seo_issues`	`array`	SEO issues that the system finds.
`data_protection_violations`	`array`	Data protection and privacy violations.
`data_protection_violations_truncated`	`boolean`	Indicates if the system truncated the data protection list.

Usage notes

Parameter	Type	Required	Description
`url`	`string`	✅	The full URL, including protocol (for example, `https://example.com/page`). The page is rendered in a browser before the scan begins.
`accessibility_guideline`	`string \| null`	❌	The WCAG conformance level. Use `WCAG22-AA` for most cases. If omitted, accessibility result fields may be null.
`accessibility_errors_only`	`boolean`	❌	If `true`, the system returns violations only. If `false`, the system may include warnings and review checks. The default setting is `false`.
`max_errors`	`integer \| null`	❌	The maximum number of errors that the system will return. Omit for 1 error per unique check; `0` for summary only; `N` for first N errors grouped by check.

Output

This output includes rendered HTML, HTTP status, accessibility summary, and grouped errors (schema varies by guideline and the max_errors setting).

Usage notes

Preferred over html_scans when you only have a URL and no pre-processed page data.
JavaScript rendering is applied automatically. Use this for SPAs and dynamically-rendered pages.

Accessibility remediation source code

accessibility_remediation_source_code

Title: Accessibility Remediation Source Code
Tags: accessibility, remediation, source_code
Read-only: no
Description: If there are one or more HTML snippets and an accessibility check identifier, the system returns each fixed snippet with a plain-language description that explains what changed and the reason for the change.

Input

Parameter	Type	Required	Description
`check_id`	`integer`	✅	The Web Governance accessibility check identifier (from `html_scans` or `render_by_url_with_guideline` results).
`source_codes`	`array<string>`	✅	One or more HTML source code snippets to remediate.

Output

This output returns a result array, one item per input snippet:

Field	Type	Description
`original`	`string`	The original snippet as provided.
`fixed`	`string`	The remediated snippet.
`description`	`string`	Plain-language explanation of what changed and why.

Usage notes

Multiple snippets can be sent in a single call; results are returned in the same order.
Always do a new scan after you apply fixes in order to confirm a clean resolution.

Spelling tools

The platform provides tree variants. Use the one that matches your available input. All of the variants require the Spell Check (qa_spellcheck) plan feature.

Spellling text snippet

spelling_text_snippet

Title: Spelling Text Snippet
Tags: check, content, spelling
Read-only: yes
Description: The system checks for spelling errors in a plain text snippet. The system returns misspelled words and the language that they were checked against.

Input

Parameter	Type	Required	Description
`text`	`string`	✅	The text snippet that the system checks for spelling errors.
`language`	`string \| null`	❌	ISO 639-1 language code (for example, `en`, `da`). The system defaults to English if this information is not provided.

Output

This output returns a result array of spelling errors with misspelled words and language context.

Usage notes

Best for targeted checks, such as:

A specific paragraph
A flagged term from a policy violation
A sentence that is under review

Spelling URL

spelling_url

Title: Spelling URL
Tags: check, content, spelling
Read-only: yes
Description: The system checks for spelling errors on a live URL. The crawler does a scan on the page, detects the language of each text block, and returns misspelled words.

Input

Parameter	Type	Required	Description
`url`	`string`	✅	Full URL including protocol (for example, `https://example.com`)
`language`	`string \| null`	❌	ISO 639-1 language override. If omitted, the system auto-detects the language from page content.
`enable_javascript`

Output

This output returns a result array of spelling errors across the page.

Usage notes

Use these for live site monitoring or pre-publish checks when you have a URL rather than raw HTML.
Enable enable_javascript for dynamically-rendered content.

Spelling page ID

spelling_page_id

Title: Spelling Page ID
Tags: check, content, spelling
Read-only: yes
Description: The system checks for misspelled words on a stored Web Governance page using data from the last successful scan. This option is fast. The system does not do a live network request.

Input

Parameter	Type	Required	Description
`domain_id`	`integer`	✅	The ID of the domain that the page belongs to.
`page_id`	`integer`	✅	The ID of the page to check.

Output

This output returns a result array of spelling errors from the last crawl.

Usage notes

This is the fastest spelling option. The system returns stored results, it does not do a new crawl.
Use resolve_url_to_ids to get domain_id and page_id from a URL.

Readability tools

Three variants. All variants return the same core output form.

Readability text snippet

readability_text_snippet

Title: Readability Text Snippet
Tags:content, readability, score
Read-only: yes
Description: The system calculates readability by analyzing raw text directly.

Input

Parameter	Type	Required	Description
`text`	`string`	✅	Plain text to analyze.
`test_engine`	`string \| null`	❌	`lix` for multilingual content; `flesch_kincaid_re` for English only.

Output

This output returns the following:

Field	Type	Description
`score`	`number`	The Readability score
`level`	`string`	Human-readable level (such as: `"Easy"`, `"Difficult"`, `"Legal / Technical"`)
`test_engine`	`string`	The algorithm that the system used.

Readability page

readability_page

Title: Readability Page
Tags: page, readability, score
Read-only: yes
Description: The system retrieves readability for a page already stored in Web Governance. This option is fast. The system returns the results from the most recent successful scan, it does not do a new scan on the page.

Input

Parameter	Type	Required	Description
`domain_id`	`integer`	✅	Domain ID (must already be scanned in Web Governance).
`page_id`	`integer`	✅	Page ID (must exist within the scanned domain).

There are tree variants. All require the

Policies

(policies_all) plan feature. Each call evaluates one policy at a time. Loop over policy IDs to evaluate multiple rules.

Field	Type	Description
`id`	`integer`	Policy ID
`name`	`string`	Policy name
`mode`	`string`	Policy mode
`priority`	`string`	Policy priority
`subject`	`string`	What the policy evaluates
`matches`	`array`	Content that matched/violated the policy
`ignored`	`array`	Matches that were ignored
`url`	`string \| null`	Associated URL if applicable

Parameter	Type	Required	Description
`url`	`string`	✅	The URL to resolve. Exact match by default; set `partial=true` for contains matching.
`partial`	`boolean`	❌	Use contains matching instead of exact URL matching.
`domain_ids`	`array<integer>`	❌	Limit the search to specific domain IDs. Required when `include_domain_group_ids` is `true`.
`max_per_domain`	`integer`	❌	Maximum pages to return per domain. If the cap is reached, `truncated=true` in the response.
`include_domain_group_ids`	`boolean`	❌	If `true`, stamps `domain_group_ids` on each page result. Requires `domain_ids` to be set.

Output

The system groups the results by domain, each domain contains matching pages with their domain_id and page_id. If truncated=true, retry with domain_ids and/or a more specific URL.

Usage notes

This is the entry point for any workflow that starts with a URL and needs to call a _page_id tool.
Use partial=true when you have a partial URL or want to find all pages under a path.

Resources and prompts

The server currently exposes no resources and no prompts.

Example workflows

Accessibility check and fix from a URL

Full content quality check on a live URL

Checking a draft before publish (no live URL yet)

Bulk audit using stored Web Governance data

Parameter	Type	Required	Description
`url`	`string`	✅	The full URL including protocol (for example, `https://example.com`).
`readability_test`	`string \| null`	❌	`lix` or `flesch_kincaid_re`.
`enable_javascript`	`boolean`	❌	Enable JavaScript rendering. The default is `false`.

Parameter	Type	Required	Description
`url`	`string`	✅	The full URL including protocol (for example, `https://example.com`).
`readability_test`	`string \| null`	❌	`lix` or `flesch_kincaid_re`.
`enable_javascript`	`boolean`	❌	Enable JavaScript rendering. The default is `false`.

MCP server documentation

Introduction

Connection configuration (OpenCode and Claude)

Tools

Accessibility tools

HTML scan

Input

Input

Input

Input

MCP server documentation

Introduction

Connection configuration (OpenCode and Claude)

Tools

Accessibility tools

HTML scan

Input

Input

Input

Input

MCP server documentation

Introduction

Connection configuration (OpenCode and Claude)

Tools

Accessibility tools

HTML scan

Input

Input

Input

Input

Output

Usage notes

Render by URL with guideline

Input

Output

Usage notes

Accessibility remediation source code

Input

Output

Usage notes

Spelling tools

Spellling text snippet

Input

Output

Usage notes

Spelling URL

Input

Output

Usage notes

Spelling page ID

Input

Output

Usage notes

Readability tools

Readability text snippet

Input

Output

Readability page

Input

Output

Usage notes

Policy tools

Run policy snippet

Output

Run policy URL

Output

Run policy page ID

Output

Utility tool

Resolve URL to IDs

Input

Output

Usage notes

Resources and prompts

Example workflows

Accessibility check and fix from a URL

Full content quality check on a live URL

Checking a draft before publish (no live URL yet)

Bulk audit using stored Web Governance data

Did not find what you were looking for?