Agent Analyzer
Scan a page the way an AI agent reads it, get failing checks and fixes, then re-scan
- Pricing
- Freemium
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 1.0.0
- Listing updated
- 1 day ago
About Agent Analyzer
Agent Analyzer is a freemium MCP server for marketing and seo. It runs as a hosted remote server, so there is nothing to install locally.
Agent Analyzer is built around a fix-and-verify loop. A coding agent scans a page, reads the failing checks, applies a fix and scans again, with no copying of reports between windows. Reports can be read as a summary, in full, or as markdown written for an agent to work from, and a scan can be diffed against an earlier one.
Spending is tightly bounded because an agent can run up a bill quickly. Reading is free, a weekly free page is always used first, and a page is charged only if it could be read. Re-scanning the same URL within 14 days is free up to five times. Refusals such as quota_exceeded, rate_limited or plan_required come back as structured objects with a next step.
A site crawl follows the sitemap, most recently changed first. Authentication is a bearer key shown once and stored hashed, and the analyzer identifies itself to sites and honours a robots.txt rule that names it.
Install
Run in a terminal
claude mcp add --transport http agent-analyzer https://www.agentexperiences.com/api/mcpAdd to Settings → Connectors → Add custom connector
https://www.agentexperiences.com/api/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"agent-analyzer": {
"url": "https://www.agentexperiences.com/api/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"agent-analyzer": {
"type": "http",
"url": "https://www.agentexperiences.com/api/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"agent-analyzer": {
"serverUrl": "https://www.agentexperiences.com/api/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"agent-analyzer": {
"type": "http",
"url": "https://www.agentexperiences.com/api/mcp"
}
}
}Tools this server provides (8)
Taken from the project documentation; the running server may differ.
- scan_page
- Scan one page and return failing checks.
- get_report
- Read a scan as summary, full or markdown.
- list_scans
- List recent scans.
- list_checks
- List the catalogue of checks.
- get_balance
- Show page credits left.
- get_fix_snippet
- Get a fix for a failing check.
- scan_site
- Crawl several pages from the sitemap.
- get_crawl
- Check crawl progress and lowest-scoring pages.
What it does
- Page scanning
- Returns the failing checks for one page.
- Fix snippets
- Ready-to-paste fixes and robots.txt in four postures.
- Diffing scans
- Compare against an earlier scan id.
- Site crawl
- Scan several pages from the sitemap.
- Cost control
- Free weekly page and free re-scans within 14 days.
- Agent-ready reports
- Markdown written for an agent to act on.
Good for
- Have a coding agent fix agent-readability issues on a page
- Verify a fix by re-scanning
- Check which checks a site fails across the sitemap
- Generate a robots.txt policy for AI crawlers
Pricing
Freemium
One free page weekly; further scans use page credits
Prices change. Check agentexperiences.com before you buy.
Agent Analyzer FAQ
How are scans charged?
A page credit is spent only if the page could be read, and the weekly free page is used first.
Are re-scans free?
Yes, up to five times for the same URL within 14 days.
How do I authenticate?
With a bearer API key created on your account page.
Is Agent Analyzer free?
Agent Analyzer has a free plan, with paid plans for more usage or features.
How do I add Agent Analyzer to Claude Code?
Run this command in your terminal: claude mcp add --transport http agent-analyzer https://www.agentexperiences.com/api/mcp
What are the best alternatives to Agent Analyzer?
The closest alternatives to Agent Analyzer are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.
Alternatives to Agent Analyzer

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools

Codebase Memory
MCP serverLocal MCP server that builds a code knowledge graph for AI coding agents
Runs locally- Open source
- 48.7K GitHub stars
- Knowledge and memory

GitHub
MCP serverOfficial MCP server connecting AI assistants to GitHub repos, issues and workflows
Not checked yet- Remote
- Open source
- 34.5K GitHub stars
- Developer tools

Serena MCP: the IDE for your agent
MCP serverMCP toolkit giving coding agents symbol-level code retrieval and editing
Runs locally- Open source
- 31.5K GitHub stars
- Developer tools

XERJ
MCP serverLocal search engine for AI agents with cited answers over your code and docs
Runs locally- Open source
- 19.2K GitHub stars
- Knowledge and memory

Ouroboros
MCP serverSpec-first layer that pins requirements and verifies results of AI coding agent work
Runs locally- Open source
- 6.4K GitHub stars
- Developer tools