webability
Qué hace este MCP
Scans HTML and web pages for WCAG accessibility issues, performs visual audits and full reports, suggests and verifies fixes, and compares scan results.
Herramientas
Esquema de entrada
{'type': 'object', 'required': ['html'], 'properties': {'html': {'type': 'string', 'description': 'HTML to test for ARIA correctness'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'nodeLimit': {'type': 'number', 'description': 'Max nodes returned per rule (default 5, max 50)'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['foreground', 'background'], 'properties': {'url': {'type': 'string', 'description': 'Live URL to extract brand palette from (uses our scanner — CSS vars + dominant colors).'}, 'isBold': {'type': 'boolean', 'description': 'Whether text is bold (default false)'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'fontSize': {'type': 'number', 'description': 'Font size in px (default 16)'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'background': {'type': 'string', 'description': 'Background color (hex or rgb)'}, 'foreground': {'type': 'string', 'description': 'Foreground color (hex or rgb)'}, 'brandColors': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Pre-supplied brand palette. Skips URL extraction if provided.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL to inspect'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': [], 'properties': {'url': {'type': 'string', 'description': 'URL to scan now as the CURRENT side (deployed, staging, or http://localhost:3000). Omit when passing currentId.'}, 'wcag': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these WCAG criteria. A prefix selects the whole guideline ("1.4") or principle ("2").'}, 'rules': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these rule ids (WebAbility type such as "missing_alt" or axe rule id such as "image-alt"). See get_rules.'}, 'format': {'enum': ['json', 'compact'], 'type': 'string', 'description': '"compact" prints one line per element with rule metadata once. "json" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count.'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'viewport': {'enum': ['desktop', 'tablet', 'mobile'], 'type': 'string', 'description': 'Viewport for live scans (default: desktop). Use the same viewport the baseline used.'}, 'currentId': {'type': 'string', 'description': 'scan_history id to use as the CURRENT side instead of scanning `url`'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'minImpact': {'enum': ['critical', 'serious', 'moderate', 'minor'], 'type': 'string', 'description': 'Only findings at this severity or above (critical > serious > moderate > minor)'}, 'baselineId': {'type': 'string', 'description': 'scan_history id of the BASELINE scan (local installs only)'}, 'baselineUrl': {'type': 'string', 'description': 'Scan this URL live as the baseline (e.g. production) — use when there is no stored baseline'}, 'rootSelector': {'type': 'string', 'description': 'CSS selector to limit live scans to (optional)'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['startUrl', 'autoNavigate'], 'properties': {'wcag': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these WCAG criteria. A prefix selects the whole guideline ("1.4") or principle ("2").'}, 'rules': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these rule ids (WebAbility type such as "missing_alt" or axe rule id such as "image-alt"). See get_rules.'}, 'format': {'enum': ['json', 'compact'], 'type': 'string', 'description': '"compact" prints one line per element with rule metadata once. "json" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count.'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'maxPages': {'type': 'number', 'description': 'Max pages to scan (default 10)'}, 'startUrl': {'type': 'string', 'description': 'Starting URL of the journey'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'minImpact': {'enum': ['critical', 'serious', 'moderate', 'minor'], 'type': 'string', 'description': 'Only findings at this severity or above (critical > serious > moderate > minor)'}, 'sourceRoot': {'type': 'string', 'description': 'Local project root (local installs only) for `sourceCandidates[]` on issues without a framework `source` pointer.'}, 'autoNavigate': {'type': 'array', 'items': {'type': 'string'}, 'description': 'REQUIRED — the URLs to walk after startUrl (the MCP server is headless and cannot discover a journey interactively). For a single page, use scan_page instead.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['issue', 'html', 'framework'], 'properties': {'url': {'type': 'string', 'description': 'Page URL — also used to auto-extract brand palette for contrast issues if `brandColors` is not provided.'}, 'html': {'type': 'string', 'description': "The element's outerHTML — send at most ~600 chars"}, 'issue': {'type': ['object', 'string'], 'description': 'Issue object from scan_page (with selector, wcag, impact, message, fix.currentValue), or a plain-text issue description'}, 'context': {'type': 'string', 'description': 'Parent element outerHTML for context (~400 chars)'}, 'framework': {'enum': ['tailwind', 'bootstrap', 'mui', 'wordpress', 'nextjs', 'plain-css'], 'type': 'string', 'description': 'CSS framework — use detect_framework first'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'brandColors': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Brand palette for brand-aligned suggestions. If omitted on a contrast issue with a `url`, auto-extracted via the scanner.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'number', 'description': 'The audit id returned by start_audit'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': [], 'properties': {'rule': {'type': 'string', 'description': 'Only rules whose id contains this text (e.g. "color-contrast", "label"; case and -/_ insensitive). Also accepted: ruleId, id, query.'}, 'tags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'axe tag filter (e.g. ["wcag21aa"], ["best-practice"], ["cat.aria"]). WebAbility rules match on their WCAG criterion tag (e.g. "wcag143").'}, 'engine': {'enum': ['all', 'axe', 'webability'], 'type': 'string', 'description': "Which engine's rules to list (default all)"}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'fixability': {'enum': ['mechanical', 'contextual', 'visual'], 'type': 'string', 'description': 'Only rules of this fixability tier'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['html'], 'properties': {'html': {'type': 'string', 'description': 'HTML content to test — a full document or a fragment'}, 'tags': {'type': 'array', 'items': {'type': 'string'}, 'description': 'WCAG tags to check (default ["wcag2a","wcag2aa","wcag21aa","wcag22aa"])'}, 'wcag': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these WCAG criteria. A prefix selects the whole guideline ("1.4") or principle ("2").'}, 'rules': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these rule ids (WebAbility type such as "missing_alt" or axe rule id such as "image-alt"). See get_rules.'}, 'width': {'type': 'number', 'description': 'Viewport width (browser engine only, default 1280)'}, 'engine': {'enum': ['in-process', 'browser'], 'type': 'string', 'description': '"in-process" (default): jsdom, ms, structural rules. "browser": headless Chromium + axe-core, includes contrast.'}, 'format': {'enum': ['json', 'compact'], 'type': 'string', 'description': '"compact" prints one line per element with rule metadata once. "json" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count.'}, 'height': {'type': 'number', 'description': 'Viewport height (browser engine only, default 800)'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'minImpact': {'enum': ['critical', 'serious', 'moderate', 'minor'], 'type': 'string', 'description': 'Only findings at this severity or above (critical > serious > moderate > minor)'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL to scan (e.g. https://example.com or http://localhost:3000)'}, 'wcag': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these WCAG criteria. A prefix selects the whole guideline ("1.4") or principle ("2").'}, 'rules': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only these rule ids (WebAbility type such as "missing_alt" or axe rule id such as "image-alt"). See get_rules.'}, 'format': {'enum': ['json', 'compact'], 'type': 'string', 'description': '"compact" prints one line per element with rule metadata once. "json" returns every field (html, fix values, source). Default: JSON when it fits inline (under ~24k chars), otherwise compact plus a JSON summary of every count.'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'viewport': {'enum': ['desktop', 'tablet', 'mobile'], 'type': 'string', 'description': 'Viewport size (default: desktop)'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'minImpact': {'enum': ['critical', 'serious', 'moderate', 'minor'], 'type': 'string', 'description': 'Only findings at this severity or above (critical > serious > moderate > minor)'}, 'sourceRoot': {'type': 'string', 'description': "Local project root (local installs only). Issues without a framework `source` pointer get `sourceCandidates[]` — files whose contents match the selector's id/class/attribute tokens."}, 'rootSelector': {'type': 'string', 'description': 'CSS selector to limit scan scope (optional)'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL to audit (a public/staging URL the server can reach, or a webability-tunnel URL — not localhost)'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'includeAgent': {'type': 'boolean', 'description': 'Also run the agentic manual-audit pass (keyboard/focus/modal exploration). Slower. Default false.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['url', 'selector'], 'properties': {'url': {'type': 'string', 'description': 'URL now serving the fix (deployed, staging, or http://localhost:3000). Also accepted as `page` or `pageUrl`.'}, 'wcag': {'type': 'string', 'description': 'Optional: WCAG criterion (e.g. "1.1.1", "1.4.3") or axe rule id (e.g. "color-contrast") to verify specifically. Omit to require the element be free of ALL violations.'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'selector': {'type': 'string', 'description': 'CSS selector of the element you fixed — use the `selector` from the original scan_page issue'}, 'viewport': {'enum': ['desktop', 'tablet', 'mobile'], 'type': 'string', 'description': 'Viewport size (default: desktop). Use the same viewport the issue was found at.'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Esquema de entrada
{'type': 'object', 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'URL to audit visually'}, 'context': {'type': 'string', 'description': 'Explain in 15-25 words, in third person, why this tool is called and how it supports the user\'s goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer\'s recent orders to investigate a billing issue and help support determine the appropriate resolution."'}, 'fullPage': {'type': 'boolean', 'description': 'Capture full scrolled page instead of just viewport (default: false)'}, 'viewport': {'enum': ['desktop', 'tablet', 'mobile'], 'type': 'string', 'description': 'Viewport size (default: desktop)'}, 'llm_model': {'type': 'string', 'description': 'The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.'}, 'brandColors': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Brand hex colors for context-aware filtering'}, 'tunnel_secret': {'type': 'string', 'description': 'Secret printed by `webability-tunnel`. Required when `url` is a tunnel URL; the URL alone will be refused by the relay. Ignored otherwise.'}, 'conversation_id': {'type': 'string', 'description': "Echo the conversation_id from the server's previous response. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it."}}}
Cambios recientes en herramientas
Servidores MCP similares
Kamy
Renders, converts, edits and extracts PDFs, manages document templates and schedules, supports e-signature workflows and provides…
Spdx License
Browses SPDX open-source license metadata, approved-license lists, and complete license texts.
Licenses
Looks up SPDX open-source license metadata and retrieves complete license texts.
Clearlydefined
Finds software package coordinates and provides license, attribution, provenance, harvesting, and completeness information for ex…
SPDX license expression tokens, value discarded
Tokenizes and checks SPDX license expressions.
SPDX license id shape
Checks the shape of SPDX license identifiers.
AgentAegis
Performs cybersecurity assessments including vulnerability scans, code and dependency audits, secret detection, threat intelligen…
aribot-mcp
Performs threat modeling, code security, API and cloud security scans, compliance analysis, and governed remediation.