Shopping MCP for AI agents: search, compare, Amazon buy links. Auto-register.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 9,337–9,360 of 165,839 resultsPage 390 of 6,910
Candidate groups, not verified unique MCPs. How grouping works
Deterministic, read-only audits of repo readiness for AI coding agents and of agent context files.
Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.
Scan any URL for AI agent readability — Vercel Spec, llmstxt.org, and agent-protocol manifests.
Scan any URL for AI agent readability — Vercel Spec, llmstxt.org, and agent-protocol manifests.
Agent Ready scores any public website out of 100 for how well AI agents like Claude can use it, and tells you what to fix first. Ask "is acme.com ready for AI agents?" and Agent Ready scans the site the way an agent meets it. You get the score, a score for each of eight areas, the most important issue in each, and a link to the full report with every finding, the evidence behind it and an ordered fix plan. The eight areas: Reach (can an agent get in, or does bot protection turn it away), Comprehend (can it read what you sell and what it costs), Act (can it book, quote or buy, including WebMCP actions), Complete (does a captcha or login stop it at the last step), Delegate (can a customer's own agent act for them after sign-in), Accurate (do your hours, prices, phone and address agree everywhere), Locations (can an agent reach the right location of a multi-location brand) and Commerce (can a shopping agent buy a specific product). Agent Ready only reads public pages. It identifies itself as AgentReadyBot, obeys robots.txt, never logs in and never submits anything. It is free and needs no account. Built by Sneeze It, a marketing agency for gyms, med spas and franchises.
Agent Ready Report scans a public website and reports how ready it is for AI agents and AI search. It runs 35 checks in three groups: agent readiness (for example robots.txt rules for AI crawlers, a sitemap, markdown for agents, an MCP server card, WebMCP and DNS-AID), agentic commerce (x402, MPP, UCP, ACP and AP2, scored only for sites that sell online) and AI search foundations (for example HTTPS, AI crawler access, structured data and response time). Each result is explained in plain English and technically, and a full report adds the pass criteria, the evidence and the official sources. It is built for business owners, marketers and developers who want to know whether AI assistants can find, read and use a website. Ask about any website by its address. A scan takes 5 to 30 seconds and needs no account. Limitations: it is a diagnostic and does not change anything. It only reads what any visitor to a public website can see. It never signs in, submits forms or buys anything, and it cannot scan private networks, IP addresses or pages behind a login. When a site blocks or times out a request, that check is reported as couldn't check, not as a failure. To protect the sites being scanned, the same site can be scanned at most four times a minute, and a repeat request within 10 minutes is answered from a cache.
Buy timestamped web, company, commerce, social, document and decision data via x402.
Private Agent memory and governed shared knowledge.
Checks x402 endpoint conformance before an agent pays, and links the receipt to its settlement.
Issue & verify signed (ed25519), hash-chained, timestamped provenance receipts for agent actions.
End-to-end encrypted inbox where AI agents deliver files and request human approval.
Discuss ideas and uncertainty with LLM agents: join, browse threads, start discussions and reply.
Deterministic release gate for AI-written code and coding agents.
Testing, benchmarking and auditing autonomous AI agents — methods, harnesses, evidence
Public board where AI agents introduce themselves, ask for help and answer each other.
Complaint registry for paid agent transactions - check a seller before you pay, or file your own.
Agent reputation registry: check, register, and endorse AI agents
Find out where your AI agent gets stuck: blocked fetches and missing data, in a private report.
Cross-session idempotency, URLs as schema-validated JSON, and a record of missing capabilities.
Read-only triage for n8n, MCP, webhook, and AI agent workflow production failures.
Advisory policy preflight for AI-agent spend requests; never executes payments or accesses wallets.
Report local task-scoped test and build residue without cleaning resources.
AI agent vacation game with challenges, badges, passports, status, Palm Points and leaderboard.
What this catalog covers
- Source listings
- 167,775
- Candidate groups
- 168,195
- Setup-eligible endpoints
- 30,727
Sources observed 2026-10-24–2026-11-04. Listings can overlap across sources. Groups are identity candidates; setup eligibility is not a successful connection test.
SourcesMCP data from Glama connectorsMCP data from Glama source codeOfficial MCP RegistryClaude connector directoryAPI Tracker · publisher documentationSlack MCP directory
Default browsing excludes 2,356 specialized utility groups across the catalog. They remain available through keyword search and direct links. This editorial filter does not change the indexed totals or establish publisher quality.
Categories currently cover records matched to our reviewed catalog; other listings remain Uncategorized. Source-only projects have no generated connection option. Browse reviewed official MCPs →
- Glama connectors
API result set; pagination may cap at approximately 1,000 connectors. Not exhaustive.
- Glama source code
Complete chronological source-code catalog response; includes source-reported author classifications, not publisher attestations or ready-to-use endpoints.
- Official MCP Registry
Complete paginated registry response; registry membership is not publisher verification.
- Claude connector directory
Complete public Claude directory MCP components. Source tiers, tools, icons and sign-in hints are declarations, not publisher or runtime verification.
- API Tracker · publisher documentation
Publisher-documented remote presets, local servers and discovery-only announcements reviewed by API Tracker. Discoverability does not establish connection readiness.
- Slack MCP directory
Reviewed additions discovered through the public Slack Marketplace MCP category. Complete discovery inventory is retained separately; membership does not prove external-client compatibility.
Listings are grouped by exact public endpoints, exact package sets, or explicit reviewed identity bindings. Shared names or repositories alone do not merge implementations. Official includes publisher evidence and accepted source author classifications. It does not mean independently verified, runtime-tested or security-certified.