{"id":50800712,"url":"https://github.com/mlava/agent-ready-mcp","last_synced_at":"2026-06-12T19:04:26.969Z","repository":{"id":357115654,"uuid":"1235442537","full_name":"mlava/agent-ready-mcp","owner":"mlava","description":"MCP server for Agent Ready — scan any URL for AI agent readability against the Vercel Agent Readability Spec, llmstxt.org, and agent protocols (MCP, A2A, agents.json, agent-permissions, UCP, x402). 59 checks with per-check fix guidance.","archived":false,"fork":false,"pushed_at":"2026-06-01T12:54:55.000Z","size":109,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-01T13:03:50.655Z","etag":null,"topics":["a2a","agent-permissions","agent-readability","agents-json","agents-md","ai-search","anthropic","claude","llms-txt","mcp","mcp-server-card","model-context-protocol","scanner","seo","ucp","validator","vercel-spec","x402"],"latest_commit_sha":null,"homepage":"https://agent-ready.dev","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mlava.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-11T10:28:09.000Z","updated_at":"2026-06-01T12:56:54.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/mlava/agent-ready-mcp","commit_stats":null,"previous_names":["mlava/agent-ready-mcp"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/mlava/agent-ready-mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlava%2Fagent-ready-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlava%2Fagent-ready-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlava%2Fagent-ready-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlava%2Fagent-ready-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mlava","download_url":"https://codeload.github.com/mlava/agent-ready-mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mlava%2Fagent-ready-mcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34258385,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-12T02:00:06.859Z","response_time":109,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["a2a","agent-permissions","agent-readability","agents-json","agents-md","ai-search","anthropic","claude","llms-txt","mcp","mcp-server-card","model-context-protocol","scanner","seo","ucp","validator","vercel-spec","x402"],"created_at":"2026-06-12T19:04:26.368Z","updated_at":"2026-06-12T19:04:26.961Z","avatar_url":"https://github.com/mlava.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# agent-ready-mcp\n\nMCP server for [Agent Ready](https://agent-ready.dev) — scan any URL for AI agent readability against the [Vercel Agent Readability Spec](https://vercel.com/kb/guide/agent-readability-spec), the [llmstxt.org](https://llmstxt.org) standard, and agent-protocol manifests (MCP server cards, A2A, agents.json, agent-permissions.json, UCP, x402, NLWeb). 60 checks across four spec families — 38 against the Vercel spec (15 site-wide + 23 per-page), 10 against llmstxt.org, and 12 against agent-protocol manifests — each with per-check fix guidance.\n\nHosted at `https://agent-ready.dev/api/v1/mcp` (Streamable HTTP); this package is a thin stdio wrapper around the same REST endpoints, distributed via npm for local MCP clients (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf).\n\n## Features\n\n- **`scan_site`** — fresh agent-readability scan on any URL. Polls the hosted API up to 60s; returns the full scan or a `running` placeholder.\n- **`get_scan`** — fetch a previously-run scan by id.\n- **`ask`** — natural-language (NLWeb) search over Agent Ready's own methodology, checks, and specs. Public, no API key required; returns Schema.org-typed results.\n- **Three discovery prompts** — `scan`, `interpret_scan`, `remediation_plan`. End-to-end workflows from URL → score → fix-it plan.\n- **`SKILL.md`** — Claude Skill descriptor included under `skills/agent-ready/` for activation routing.\n\n## Setup\n\nYou'll need an Agent Ready Pro API key. Sign up at [agent-ready.dev](https://agent-ready.dev), upgrade to Pro, then issue a key from the [dashboard](https://agent-ready.dev/dashboard/api-keys).\n\n### Claude Desktop\n\nAdd to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\\Claude\\claude_desktop_config.json` (Windows):\n\n```json\n{\n  \"mcpServers\": {\n    \"agent-ready\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"agent-ready-mcp@latest\"],\n      \"env\": {\n        \"AGENT_READY_API_KEY\": \"ar_live_...\"\n      }\n    }\n  }\n}\n```\n\n### Claude Code\n\n```bash\nclaude mcp add agent-ready \\\n  -e AGENT_READY_API_KEY=ar_live_... \\\n  -- npx -y agent-ready-mcp@latest\n```\n\n### Cursor / VS Code / Windsurf\n\n`.cursor/mcp.json`, `.vscode/mcp.json`, or `~/.codeium/windsurf/mcp_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"agent-ready\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"agent-ready-mcp@latest\"],\n      \"env\": {\n        \"AGENT_READY_API_KEY\": \"ar_live_...\"\n      }\n    }\n  }\n}\n```\n\n## Environment variables\n\n| Variable | Required | Default | Purpose |\n|---|---|---|---|\n| `AGENT_READY_API_KEY` | Yes | — | Bearer token issued from the Agent Ready dashboard. |\n| `AGENT_READY_API_URL` | No | `https://agent-ready.dev` | Override for self-hosted or staging deployments. |\n| `AGENT_READY_SCAN_TIMEOUT_MS` | No | `60000` | How long `scan_site` polls before returning a `running` placeholder. |\n| `AGENT_READY_GET_TIMEOUT_MS` | No | `5000` | Timeout for `get_scan` and per-poll fetches. |\n\n## Tools\n\n| Tool | Inputs | Returns |\n|---|---|---|\n| `scan_site` | `url` (string, required), `pageLimit` (number, optional, max 2000 — capped by your plan) | Scan object: Vercel score 0–100, llms.txt sub-score 0–100, per-check findings with `howToFix` strings. Returns `{ id, status: \"running\" }` placeholder if the scan exceeds the poll deadline. |\n| `get_scan` | `id` (string, scan id from a prior `scan_site` call) | Same scan object as `scan_site`, or `not_found` if the id is unknown or doesn't belong to the authenticated user. |\n| `ask` | `q` (string, required), `itemType` (optional corpus filter), `mode` (optional, `list` or `summarize`) | NLWeb `/ask` over Agent Ready's methodology, checks, and specs. Public — no API key required. Schema.org-typed result objects. |\n\n## Prompts\n\n| Prompt | Args | What it does |\n|---|---|---|\n| `scan` | `url` | Fresh scan + high-level summary (score, rating, top 3–5 failures, next step). |\n| `interpret_scan` | `id` | Plain-English explanation of a previous scan's findings, grouped by category. |\n| `remediation_plan` | `id`, optional `focus` (`\"seo\"` or `\"agents\"`) | Prioritised fix-it doc with Now/Next/Later buckets and per-fix check ids. |\n\n## Example workflow\n\n```\nYou: Use agent-ready to scan https://my-saas.com\nClaude: [calls scan_site] Your site scored 78/100 (Good) on the Vercel Agent\n        Readability Spec. The top 3 fixes: …\nYou: Can you build me a remediation plan?\nClaude: [calls remediation_plan with the scan id] Here's the prioritised list…\n```\n\n## Skill (Anthropic Claude Skills)\n\nA `SKILL.md` lives at `skills/agent-ready/SKILL.md` inside the package. To use it in Claude Desktop / Claude Code, copy the `skills/agent-ready/` directory into `~/.claude/skills/`.\n\nThe skill describes when to activate (URL + readability-audit intent), which tool to pick, how to surface scan results without dumping raw JSON, and when to defer to other tools (general SEO, performance profiling, code editing).\n\n## How it works\n\nThis package is a thin stdio→HTTPS wrapper:\n\n```\nMCP client (stdio) ↔ agent-ready-mcp ↔ HTTPS ↔ agent-ready.dev/api/v1/scans\n```\n\nAll scan execution, persistence, and Pro-tier quota enforcement happen on the hosted server. The npm package only translates between MCP JSON-RPC over stdio and the REST API.\n\nIf you'd rather use the hosted MCP server directly (Streamable HTTP transport, no local install), point your MCP client at `https://agent-ready.dev/api/v1/mcp` with `Authorization: Bearer ar_live_...`.\n\n## Methodology\n\nThe 60 checks, their weights, and the score formula are documented at [agent-ready.dev/methodology](https://agent-ready.dev/methodology). Both `manifest.json` and `server.json` in this repo conform to the relevant registry schemas (Glama Marketplace v0.3 and MCP registry 2025-12-11 respectively).\n\n## Development\n\n```bash\nnpm install\nnpm run build       # → dist/mcp-server.mjs\nnpm test\nnpm run typecheck\n```\n\n## Releasing\n\nTwo GitHub Actions handle CI and release publishing:\n\n- `.github/workflows/ci.yml` — runs typecheck, tests, and `npm run build` on every PR and push to `main`.\n- `.github/workflows/release.yml` — runs on every `v*` tag push. Publishes to npm (with Sigstore provenance) and to the [MCP registry](https://registry.modelcontextprotocol.io) via GitHub OIDC.\n\nTo cut a release:\n\n```bash\n# bump version in package.json, manifest.json, server.json, src/server.ts\ngit commit -am \"vX.Y.Z: ...\"\ngit tag vX.Y.Z\ngit push \u0026\u0026 git push --tags\n```\n\nThe release workflow handles npm + MCP registry automatically. Smithery republish (for the `.mcpb` bundle) and the GitHub release with custom notes are still manual — both have custom-content friction that's not worth automating today.\n\n### Required repository secret\n\n- `NPM_TOKEN` — npm automation token with publish access for `agent-ready-mcp`. Add at GitHub repo Settings → Secrets and variables → Actions.\n\nThe MCP registry publish uses GitHub OIDC (no stored secret required).\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlava%2Fagent-ready-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmlava%2Fagent-ready-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmlava%2Fagent-ready-mcp/lists"}