Lighthouse & Accessibility Audit MCP server
Commit Nov 16, 2026Performs website audits for Lighthouse scores, Core Web Vitals, and axe accessibility issues using the median of three runs.
Also known as faithdrivencreator/apify-agent-tools, lighthouse-gate
- Stars
- 0
- Tools
- 5
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 16, 2026
- License
- MIT
What is Lighthouse & Accessibility Audit MCP?
Lighthouse & Accessibility Audit performs website audits for Lighthouse scores, Core Web Vitals, and axe accessibility issues using the median of three runs. It exposes 5 tools, such as fluidfaith--lighthouse-gate, get-actor-run, get-dataset-items.
Summary generated from the project's README
About Lighthouse & Accessibility Audit MCP server
Auditing website performance and accessibility directly through an AI agent is possible with this remote MCP server. It provides developers and QA engineers with detailed reports on Lighthouse scores, Core Web Vitals, and axe accessibility issues. To ensure accuracy, the server calculates results based on the median of three separate runs for every URL provided.
Users connect to the service via a streamable HTTP transport, making it compatible with Claude Code, Cursor, and VS Code. Setting up the connection requires an Apify token passed through an authorization header. The service operates on a usage-based model costing $0.02 per URL per form factor, though it includes a guarantee that failed items are free and charges per run will never exceed a specific maximum.
Integration is straightforward for various workflows, including Python and JavaScript environments using the Apify client or LangChain. By providing specific URLs and form factors like mobile, an agent can receive PASS/FAIL statuses and a list of top fixes to improve site health.
What you can do with it
- 1Verify website accessibility complianceAsk your AI agent to identify axe accessibility issues on a specific webpage.
- 2Analyze Core Web VitalsRequest a report on how a site performs regarding Core Web Vitals metrics.
- 3Get actionable performance fixesHave an AI client list the most important improvements needed to raise a Lighthouse score.
- 4Ensure data accuracy through repetitionInstruct an agent to perform an audit that uses the median of multiple runs to avoid outliers.
Written from the project's README. Every use case is checked against a quote from it.
How to install Lighthouse & Accessibility Audit MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Lighthouse & Accessibility Audit MCP in Claude Code
$ claude mcp add --transport http lighthouse-gate 'https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate'Install Lighthouse & Accessibility Audit MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"lighthouse-gate": {
"url": "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate"
}
}
}Install Lighthouse & Accessibility Audit MCP in VS Code
.vscode/mcp.json
{
"servers": {
"lighthouse-gate": {
"type": "http",
"url": "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate"
}
}
}Install Lighthouse & Accessibility Audit MCP in VS Code CLI
$ code --add-mcp '{"name":"lighthouse-gate","type":"http","url":"https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate"}'Install Lighthouse & Accessibility Audit MCP in Codex
$ codex mcp add lighthouse-gate --url 'https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate'Install Lighthouse & Accessibility Audit MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.lighthouse-gate] url = "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate"
Install Lighthouse & Accessibility Audit MCP in Gemini CLI
$ gemini mcp add -s user --transport http lighthouse-gate 'https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate'Install Lighthouse & Accessibility Audit MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"lighthouse-gate": {
"url": "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate",
"type": "http"
}
}
}Lighthouse & Accessibility Audit MCP tools 5
Read from the server with tools/listfluidfaith--lighthouse-gateActionThis tool calls the Actor "fluidfaith/lighthouse-gate" and retrieves its output results. Actor description: Lighthouse scores, Core Web Vitals and axe-core accessibility violations for any URL, on mobile and desktop in one call, as the median of 3 runs. Returns PASS/FAIL against your thresholds and the top 5 fixes in plain language. Built for AI agents and MCP.
get-actor-runRead-onlyGet detailed information about a specific Actor run. Returns run result: status, storages (datasets/keyValueStores alias map), stats, summary, nextStep. - summary describes the past (e.g. "SUCCEEDED in 22s. 47 items; 3 fields available."). - nextStep prescribes one primary follow-up action with identifiers interpolated (e.g. "Use get-dataset-items with datasetId=..."). - waitSecs (0–45, default 30) waits up to that many seconds for terminal status before returning. USAGE: - Use to check the status of a run started by any Actor-running tool. - Pass waitSecs > 0 to block until terminal (or until the cap elapses). USAGE EXAMPLES: - user_input: Show details of run y2h7sK3Wc - user_input: Wait for run y2h7sK3Wc to finish
get-dataset-itemsRead-onlyGet items (rows) from a dataset — the output/results produced by an Actor run. Returns the rows themselves, not dataset metadata, counts, or a schema. When the user provides a datasetId and asks to retrieve results, output, data, or rows, call this tool directly. Default limit is 20. Use clean=true to skip empty items and hidden fields. USAGE: - Use when you need to read data from a dataset (all items or only selected fields). USAGE EXAMPLES: - user_input: Retrieve results from dataset abc123 - user_input: Get only metadata.url and title from dataset username~my-dataset
get-key-value-store-recordRead-onlyGet the value stored under a specific key in a key-value store — a single record, not a listing of all keys. Requires the exact key name. The response preserves the original Content-Encoding; most clients handle decompression automatically. A record over 262144 bytes is returned as a link to download it, not as its value. USAGE: - Use when you need to retrieve a specific record (JSON, text, or binary) from a store. USAGE EXAMPLES: - user_input: Get record INPUT from store abc123 - user_input: Get record data.json from store username~my-store
abort-actor-runActionAbort an Actor run that is currently starting or running. For runs with status SUCCEEDED, FAILED, ABORTING, ABORTED, or TIMED-OUT, this call has no effect. The results will include the updated run details after the abort request. USAGE: - Use when you need to stop a run that is taking too long or misconfigured. USAGE EXAMPLES: - user_input: Abort run y2h7sK3Wc - user_input: Gracefully abort run y2h7sK3Wc
| fluidfaith--lighthouse-gate | This tool calls the Actor "fluidfaith/lighthouse-gate" and retrieves its output results. Actor description: Lighthouse scores, Core Web Vitals and axe-core accessibility violations for any URL, on mobile and desktop in one call, as the median of 3 runs. Returns PASS/FAIL against your thresholds and the top 5 fixes in plain language. Built for AI agents and MCP. | Action |
| get-actor-run | Get detailed information about a specific Actor run. Returns run result: status, storages (datasets/keyValueStores alias map), stats, summary, nextStep. - summary describes the past (e.g. "SUCCEEDED in 22s. 47 items; 3 fields available."). - nextStep prescribes one primary follow-up action with identifiers interpolated (e.g. "Use get-dataset-items with datasetId=..."). - waitSecs (0–45, default 30) waits up to that many seconds for terminal status before returning. USAGE: - Use to check the status of a run started by any Actor-running tool. - Pass waitSecs > 0 to block until terminal (or until the cap elapses). USAGE EXAMPLES: - user_input: Show details of run y2h7sK3Wc - user_input: Wait for run y2h7sK3Wc to finish | Read-only |
| get-dataset-items | Get items (rows) from a dataset — the output/results produced by an Actor run. Returns the rows themselves, not dataset metadata, counts, or a schema. When the user provides a datasetId and asks to retrieve results, output, data, or rows, call this tool directly. Default limit is 20. Use clean=true to skip empty items and hidden fields. USAGE: - Use when you need to read data from a dataset (all items or only selected fields). USAGE EXAMPLES: - user_input: Retrieve results from dataset abc123 - user_input: Get only metadata.url and title from dataset username~my-dataset | Read-only |
| get-key-value-store-record | Get the value stored under a specific key in a key-value store — a single record, not a listing of all keys. Requires the exact key name. The response preserves the original Content-Encoding; most clients handle decompression automatically. A record over 262144 bytes is returned as a link to download it, not as its value. USAGE: - Use when you need to retrieve a specific record (JSON, text, or binary) from a store. USAGE EXAMPLES: - user_input: Get record INPUT from store abc123 - user_input: Get record data.json from store username~my-store | Read-only |
| abort-actor-run | Abort an Actor run that is currently starting or running. For runs with status SUCCEEDED, FAILED, ABORTING, ABORTED, or TIMED-OUT, this call has no effect. The results will include the updated run details after the abort request. USAGE: - Use when you need to stop a run that is taking too long or misconfigured. USAGE EXAMPLES: - user_input: Abort run y2h7sK3Wc - user_input: Gracefully abort run y2h7sK3Wc | Action |
Automated checks
Ran Nov 16, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablefaithdrivencreator/apify-agent-tools is public and reachablegithub.com/faithdrivencreator/apify-agent-tools ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-09github.com/faithdrivencreator/apify-agent-tools ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-11-25 in 1618 ms; tools/list returned 5 tools (HostedMCP test account)Pass
README
View on GitHubLighthouse & Accessibility Audit for AI Agents
Lighthouse scores, Core Web Vitals and axe accessibility issues, median of 3 runs, PASS/FAIL and top fixes.
- Apify Store: https://apify.com/fluidfaith/lighthouse-gate
- MCP server (remote, streamable HTTP):
https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate - Price: $0.02 per URL per form factor. Failed items are free, and your maximum charge per run is never exceeded.
Claude Code, Cursor, VS Code (MCP config)
{
"mcpServers": {
"lighthouse-gate": {
"url": "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate",
"headers": { "Authorization": "Bearer ${APIFY_TOKEN}" }
}
}
}
Claude Code one-liner: claude mcp add --transport http lighthouse-gate "https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate" --header "Authorization: Bearer $APIFY_TOKEN"
Python (apify-client)
import os
from apify_client import ApifyClient
client = ApifyClient(os.environ["APIFY_TOKEN"])
run = client.actor("fluidfaith/lighthouse-gate").call(run_input={"urls": ["https://example.com/"], "formFactors": ["mobile"]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item)
LangChain
from langchain_apify import ApifyActorsTool
tool = ApifyActorsTool("fluidfaith/lighthouse-gate")
JavaScript (apify-client)
import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('fluidfaith/lighthouse-gate').call({"urls": ["https://example.com/"], "formFactors": ["mobile"]});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);
Lighthouse & Accessibility Audit MCP questions
How do I add Lighthouse & Accessibility Audit MCP to Claude Code?
Run claude mcp add --transport http lighthouse-gate 'https://mcp.apify.com/?tools=fluidfaith/lighthouse-gate' in your terminal. Add --scope user to make it available in every project.
How do I add Lighthouse & Accessibility Audit MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Lighthouse & Accessibility Audit MCP provide?
It exposes 5 tools, including fluidfaith--lighthouse-gate, get-actor-run, get-dataset-items, get-key-value-store-record, abort-actor-run.
How much does the audit cost?
The service costs $0.02 per URL per form factor, but failed items are free and there is a maximum charge per run.
What metrics does the server provide?
The server provides Lighthouse scores, Core Web Vitals, and axe accessibility issues based on the median of three runs.