agent-ready-mcp 0.7.0 → 0.7.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/LICENSE CHANGED
@@ -1,193 +1,6 @@
1
- The MCP project is undergoing a licensing transition from the MIT License to the Apache License, Version 2.0 ("Apache-2.0"). All new code and specification contributions to the project are licensed under Apache-2.0. Documentation contributions (excluding specifications) are licensed under CC-BY-4.0.
2
-
3
- Contributions for which relicensing consent has been obtained are licensed under Apache-2.0. Contributions made by authors who originally licensed their work under the MIT License and who have not yet granted explicit permission to relicense remain licensed under the MIT License.
4
-
5
- No rights beyond those granted by the applicable original license are conveyed for such contributions.
6
-
7
- ---
8
-
9
- Apache License
10
- Version 2.0, January 2004
11
- http://www.apache.org/licenses/
12
-
13
- TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
14
-
15
- 1. Definitions.
16
-
17
- "License" shall mean the terms and conditions for use, reproduction,
18
- and distribution as defined by Sections 1 through 9 of this document.
19
-
20
- "Licensor" shall mean the copyright owner or entity authorized by
21
- the copyright owner that is granting the License.
22
-
23
- "Legal Entity" shall mean the union of the acting entity and all
24
- other entities that control, are controlled by, or are under common
25
- control with that entity. For the purposes of this definition,
26
- "control" means (i) the power, direct or indirect, to cause the
27
- direction or management of such entity, whether by contract or
28
- otherwise, or (ii) ownership of fifty percent (50%) or more of the
29
- outstanding shares, or (iii) beneficial ownership of such entity.
30
-
31
- "You" (or "Your") shall mean an individual or Legal Entity
32
- exercising permissions granted by this License.
33
-
34
- "Source" form shall mean the preferred form for making modifications,
35
- including but not limited to software source code, documentation
36
- source, and configuration files.
37
-
38
- "Object" form shall mean any form resulting from mechanical
39
- transformation or translation of a Source form, including but
40
- not limited to compiled object code, generated documentation,
41
- and conversions to other media types.
42
-
43
- "Work" shall mean the work of authorship, whether in Source or
44
- Object form, made available under the License, as indicated by a
45
- copyright notice that is included in or attached to the work
46
- (an example is provided in the Appendix below).
47
-
48
- "Derivative Works" shall mean any work, whether in Source or Object
49
- form, that is based on (or derived from) the Work and for which the
50
- editorial revisions, annotations, elaborations, or other modifications
51
- represent, as a whole, an original work of authorship. For the purposes
52
- of this License, Derivative Works shall not include works that remain
53
- separable from, or merely link (or bind by name) to the interfaces of,
54
- the Work and Derivative Works thereof.
55
-
56
- "Contribution" shall mean any work of authorship, including
57
- the original version of the Work and any modifications or additions
58
- to that Work or Derivative Works thereof, that is intentionally
59
- submitted to the Licensor for inclusion in the Work by the copyright
60
- owner or by an individual or Legal Entity authorized to submit on behalf
61
- of the copyright owner. For the purposes of this definition, "submitted"
62
- means any form of electronic, verbal, or written communication sent
63
- to the Licensor or its representatives, including but not limited to
64
- communication on electronic mailing lists, source code control systems,
65
- and issue tracking systems that are managed by, or on behalf of, the
66
- Licensor for the purpose of discussing and improving the Work, but
67
- excluding communication that is conspicuously marked or otherwise
68
- designated in writing by the copyright owner as "Not a Contribution."
69
-
70
- "Contributor" shall mean Licensor and any individual or Legal Entity
71
- on behalf of whom a Contribution has been received by Licensor and
72
- subsequently incorporated within the Work.
73
-
74
- 2. Grant of Copyright License. Subject to the terms and conditions of
75
- this License, each Contributor hereby grants to You a perpetual,
76
- worldwide, non-exclusive, no-charge, royalty-free, irrevocable
77
- copyright license to reproduce, prepare Derivative Works of,
78
- publicly display, publicly perform, sublicense, and distribute the
79
- Work and such Derivative Works in Source or Object form.
80
-
81
- 3. Grant of Patent License. Subject to the terms and conditions of
82
- this License, each Contributor hereby grants to You a perpetual,
83
- worldwide, non-exclusive, no-charge, royalty-free, irrevocable
84
- (except as stated in this section) patent license to make, have made,
85
- use, offer to sell, sell, import, and otherwise transfer the Work,
86
- where such license applies only to those patent claims licensable
87
- by such Contributor that are necessarily infringed by their
88
- Contribution(s) alone or by combination of their Contribution(s)
89
- with the Work to which such Contribution(s) was submitted. If You
90
- institute patent litigation against any entity (including a
91
- cross-claim or counterclaim in a lawsuit) alleging that the Work
92
- or a Contribution incorporated within the Work constitutes direct
93
- or contributory patent infringement, then any patent licenses
94
- granted to You under this License for that Work shall terminate
95
- as of the date such litigation is filed.
96
-
97
- 4. Redistribution. You may reproduce and distribute copies of the
98
- Work or Derivative Works thereof in any medium, with or without
99
- modifications, and in Source or Object form, provided that You
100
- meet the following conditions:
101
-
102
- (a) You must give any other recipients of the Work or
103
- Derivative Works a copy of this License; and
104
-
105
- (b) You must cause any modified files to carry prominent notices
106
- stating that You changed the files; and
107
-
108
- (c) You must retain, in the Source form of any Derivative Works
109
- that You distribute, all copyright, patent, trademark, and
110
- attribution notices from the Source form of the Work,
111
- excluding those notices that do not pertain to any part of
112
- the Derivative Works; and
113
-
114
- (d) If the Work includes a "NOTICE" text file as part of its
115
- distribution, then any Derivative Works that You distribute must
116
- include a readable copy of the attribution notices contained
117
- within such NOTICE file, excluding those notices that do not
118
- pertain to any part of the Derivative Works, in at least one
119
- of the following places: within a NOTICE text file distributed
120
- as part of the Derivative Works; within the Source form or
121
- documentation, if provided along with the Derivative Works; or,
122
- within a display generated by the Derivative Works, if and
123
- wherever such third-party notices normally appear. The contents
124
- of the NOTICE file are for informational purposes only and
125
- do not modify the License. You may add Your own attribution
126
- notices within Derivative Works that You distribute, alongside
127
- or as an addendum to the NOTICE text from the Work, provided
128
- that such additional attribution notices cannot be construed
129
- as modifying the License.
130
-
131
- You may add Your own copyright statement to Your modifications and
132
- may provide additional or different license terms and conditions
133
- for use, reproduction, or distribution of Your modifications, or
134
- for any such Derivative Works as a whole, provided Your use,
135
- reproduction, and distribution of the Work otherwise complies with
136
- the conditions stated in this License.
137
-
138
- 5. Submission of Contributions. Unless You explicitly state otherwise,
139
- any Contribution intentionally submitted for inclusion in the Work
140
- by You to the Licensor shall be under the terms and conditions of
141
- this License, without any additional terms or conditions.
142
- Notwithstanding the above, nothing herein shall supersede or modify
143
- the terms of any separate license agreement you may have executed
144
- with Licensor regarding such Contributions.
145
-
146
- 6. Trademarks. This License does not grant permission to use the trade
147
- names, trademarks, service marks, or product names of the Licensor,
148
- except as required for reasonable and customary use in describing the
149
- origin of the Work and reproducing the content of the NOTICE file.
150
-
151
- 7. Disclaimer of Warranty. Unless required by applicable law or
152
- agreed to in writing, Licensor provides the Work (and each
153
- Contributor provides its Contributions) on an "AS IS" BASIS,
154
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
155
- implied, including, without limitation, any warranties or conditions
156
- of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
157
- PARTICULAR PURPOSE. You are solely responsible for determining the
158
- appropriateness of using or redistributing the Work and assume any
159
- risks associated with Your exercise of permissions under this License.
160
-
161
- 8. Limitation of Liability. In no event and under no legal theory,
162
- whether in tort (including negligence), contract, or otherwise,
163
- unless required by applicable law (such as deliberate and grossly
164
- negligent acts) or agreed to in writing, shall any Contributor be
165
- liable to You for damages, including any direct, indirect, special,
166
- incidental, or consequential damages of any character arising as a
167
- result of this License or out of the use or inability to use the
168
- Work (including but not limited to damages for loss of goodwill,
169
- work stoppage, computer failure or malfunction, or any and all
170
- other commercial damages or losses), even if such Contributor
171
- has been advised of the possibility of such damages.
172
-
173
- 9. Accepting Warranty or Additional Liability. While redistributing
174
- the Work or Derivative Works thereof, You may choose to offer,
175
- and charge a fee for, acceptance of support, warranty, indemnity,
176
- or other liability obligations and/or rights consistent with this
177
- License. However, in accepting such obligations, You may act only
178
- on Your own behalf and on Your sole responsibility, not on behalf
179
- of any other Contributor, and only if You agree to indemnify,
180
- defend, and hold each Contributor harmless for any liability
181
- incurred by, or claims asserted against, such Contributor by reason
182
- of your accepting any such warranty or additional liability.
183
-
184
- END OF TERMS AND CONDITIONS
185
-
186
- ---
187
-
188
1
  MIT License
189
2
 
190
- Copyright (c) 2024-2025 Model Context Protocol a Series of LF Projects, LLC.
3
+ Copyright (c) 2026 Agent Ready
191
4
 
192
5
  Permission is hereby granted, free of charge, to any person obtaining a copy
193
6
  of this software and associated documentation files (the "Software"), to deal
@@ -206,11 +19,3 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
206
19
  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
207
20
  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
208
21
  SOFTWARE.
209
-
210
- ---
211
-
212
- Creative Commons Attribution 4.0 International (CC-BY-4.0)
213
-
214
- Documentation in this project (excluding specifications) is licensed under
215
- CC-BY-4.0. See https://creativecommons.org/licenses/by/4.0/legalcode for
216
- the full license text.
package/README.md CHANGED
@@ -1,153 +1,139 @@
1
- # MCP Registry
1
+ # agent-ready-mcp
2
2
 
3
- The MCP registry provides MCP clients with a list of MCP servers, like an app store for MCP servers.
3
+ MCP 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). 69 checks across four spec families — 38 against the Vercel spec (15 site-wide + 23 per-page), 10 against llmstxt.org, and 21 against agent-protocol manifests — each with per-check fix guidance, plus a separate accessibility sub-score from 23 WCAG 2.2 / layout-stability checks.
4
4
 
5
- [**📤 Publish my MCP server**](docs/modelcontextprotocol-io/quickstart.mdx) | [**⚡️ Live API docs**](https://registry.modelcontextprotocol.io/docs) | [**👀 Ecosystem vision**](docs/design/ecosystem-vision.md) | 📖 **[Full documentation](./docs)**
5
+ Hosted 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).
6
6
 
7
- ## Development Status
7
+ ## Features
8
8
 
9
- **2025-10-24 update**: The Registry API has entered an **API freeze (v0.1)** 🎉. For the next month or more, the API will remain stable with no breaking changes, allowing integrators to confidently implement support. This freeze applies to v0.1 while development continues on v0. We'll use this period to validate the API in real-world integrations and gather feedback to shape v1 for general availability. Thank you to everyone for your contributions and patience—your involvement has been key to getting us here!
9
+ - **`scan_site`** fresh agent-readability scan on any URL. Works without a key on the anonymous free tier (3 scans/30 days per IP, 25-page depth, synchronous); with a Pro key it scans up to 250 pages, polling the hosted API up to 60s.
10
+ - **`get_scan`** — fetch a previously-run scan by id (Pro key required — scan history is account-scoped).
11
+ - **`ask`** — natural-language (NLWeb) search over Agent Ready's own methodology, checks, and specs. Public, no API key required; returns Schema.org-typed results.
12
+ - **`validate_structured_data`** — validate a page's (or a pasted) JSON-LD against Agent Ready's structured-data checks. Public, no API key required; paste mode needs no network, so an agent can check JSON-LD it just authored.
13
+ - **Three discovery prompts** — `scan`, `interpret_scan`, `remediation_plan`. End-to-end workflows from URL → score → fix-it plan.
14
+ - **`SKILL.md`** — Claude Skill descriptor included under `skills/agent-ready/` for activation routing.
10
15
 
11
- **2025-09-08 update**: The registry has launched in preview 🎉 ([announcement blog post](https://blog.modelcontextprotocol.io/posts/2025-09-08-mcp-registry-preview/)). While the system is now more stable, this is still a preview release and breaking changes or data resets may occur. A general availability (GA) release will follow later. We'd love your feedback in [GitHub discussions](https://github.com/modelcontextprotocol/registry/discussions/new?category=ideas) or in the [#registry-dev Discord](https://discord.com/channels/1358869848138059966/1369487942862504016) ([joining details here](https://modelcontextprotocol.io/community/communication)).
16
+ ## Setup
12
17
 
13
- Registry Working Group:
14
- - **Tadas Antanavicius** (PulseMCP) [@tadasant](https://github.com/tadasant)
15
- - **Radoslav (Rado) Dimitrov** (Stacklok) [@rdimitrov](https://github.com/rdimitrov)
16
- - **Bob Dickinson** (TeamSpark) [@BobDickinson](https://github.com/BobDickinson)
17
- - **Preeti (Pree) Dewani** (Ravenmail) [@pree-dew](https://github.com/pree-dew)
18
+ No key is required to start: `scan_site`, `ask`, and `validate_structured_data` all work anonymously out of the box (`scan_site` on the free anonymous quota — 3 scans per 30 days per IP at 25-page depth). An Agent Ready **Pro API key** unlocks 50 scans/month, 250-page depth, scan history (`get_scan`), and weekly monitoring — sign up at [agent-ready.dev](https://agent-ready.dev) and issue a key from the [dashboard](https://agent-ready.dev/dashboard/api-keys). The `env` block in the configs below is optional; omit it to run keyless.
18
19
 
19
- ## Contributing
20
+ ### Claude Desktop
20
21
 
21
- We use multiple channels for collaboration - see [modelcontextprotocol.io/community/communication](https://modelcontextprotocol.io/community/communication).
22
+ Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):
22
23
 
23
- Often (but not always) ideas flow through this pipeline:
24
-
25
- - **[Discord](https://modelcontextprotocol.io/community/communication)** - Real-time community discussions
26
- - **[Discussions](https://github.com/modelcontextprotocol/registry/discussions)** - Propose and discuss product/technical requirements
27
- - **[Issues](https://github.com/modelcontextprotocol/registry/issues)** - Track well-scoped technical work
28
- - **[Pull Requests](https://github.com/modelcontextprotocol/registry/pulls)** - Contribute work towards issues
29
-
30
- ### Quick start:
31
-
32
- #### Pre-requisites
33
-
34
- - **Docker**
35
- - **Go 1.24.x**
36
- - **ko** - Container image builder for Go ([installation instructions](https://ko.build/install/))
37
- - **golangci-lint v2.4.0**
24
+ ```json
25
+ {
26
+ "mcpServers": {
27
+ "agent-ready": {
28
+ "command": "npx",
29
+ "args": ["-y", "agent-ready-mcp@latest"],
30
+ "env": {
31
+ "AGENT_READY_API_KEY": "ar_live_..."
32
+ }
33
+ }
34
+ }
35
+ }
36
+ ```
38
37
 
39
- #### Running the server
38
+ ### Claude Code
40
39
 
41
40
  ```bash
42
- # Start full development environment
43
- make dev-compose
41
+ claude mcp add agent-ready \
42
+ -e AGENT_READY_API_KEY=ar_live_... \
43
+ -- npx -y agent-ready-mcp@latest
44
44
  ```
45
45
 
46
- This starts the registry at [`localhost:8080`](http://localhost:8080) with PostgreSQL. The database uses ephemeral storage and is reset each time you restart the containers, ensuring a clean state for development and testing.
47
-
48
- **Note:** The registry uses [ko](https://ko.build) to build container images. The `make dev-compose` command automatically builds the registry image with ko and loads it into your local Docker daemon before starting the services.
46
+ ### Cursor / VS Code / Windsurf
47
+
48
+ `.cursor/mcp.json`, `.vscode/mcp.json`, or `~/.codeium/windsurf/mcp_config.json`:
49
+
50
+ ```json
51
+ {
52
+ "mcpServers": {
53
+ "agent-ready": {
54
+ "command": "npx",
55
+ "args": ["-y", "agent-ready-mcp@latest"],
56
+ "env": {
57
+ "AGENT_READY_API_KEY": "ar_live_..."
58
+ }
59
+ }
60
+ }
61
+ }
62
+ ```
49
63
 
50
- By default, the registry seeds from the production API with a filtered subset of servers (to keep startup fast). This ensures your local environment mirrors production behavior and all seed data passes validation. For offline development you can seed from a file without validation with `MCP_REGISTRY_SEED_FROM=data/seed.json MCP_REGISTRY_ENABLE_REGISTRY_VALIDATION=false make dev-compose`.
64
+ ## Environment variables
51
65
 
52
- The setup can be configured with environment variables in [docker-compose.yml](./docker-compose.yml) - see [.env.example](./.env.example) for a reference.
66
+ | Variable | Required | Default | Purpose |
67
+ |---|---|---|---|
68
+ | `AGENT_READY_API_KEY` | No | — | Pro Bearer token from the Agent Ready dashboard. Without it, `scan_site` uses the anonymous free tier and `get_scan` is unavailable. |
69
+ | `AGENT_READY_API_URL` | No | `https://agent-ready.dev` | Override for self-hosted or staging deployments. |
70
+ | `AGENT_READY_SCAN_TIMEOUT_MS` | No | `60000` | How long `scan_site` polls before returning a `running` placeholder. |
71
+ | `AGENT_READY_GET_TIMEOUT_MS` | No | `5000` | Timeout for `get_scan` and per-poll fetches. |
53
72
 
54
- <details>
55
- <summary>Alternative: Running a pre-built Docker image</summary>
73
+ ## Tools
56
74
 
57
- Pre-built Docker images are automatically published to GitHub Container Registry. Note that the image does not bundle PostgreSQL, so you need to run your own and point the registry at it via `MCP_REGISTRY_DATABASE_URL` (see [docker-compose.yml](./docker-compose.yml) for a working example):
75
+ | Tool | Inputs | Returns |
76
+ |---|---|---|
77
+ | `scan_site` | `url` (string, required), `pageLimit` (number, optional, max 2000 — capped by your plan; fixed at 25 keyless) | Scan object: Vercel score 0–100, llms.txt sub-score 0–100, per-check findings with `howToFix` strings. Keyless runs use the anonymous free tier (3 scans/30 days per IP) and return synchronously; with a Pro key, returns `{ id, status: "running" }` placeholder if the scan exceeds the poll deadline. |
78
+ | `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. Pro key required. |
79
+ | `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. |
80
+ | `validate_structured_data` | exactly one of `url` (string) or `jsonld` (string) | D-series structured-data result: `mode`, `url`, per-check findings, and a `summary` verdict. Public — no API key required. Validates schema lint + agent-coherence the first-party validators don't. |
58
81
 
59
- ```bash
60
- # Run latest stable release
61
- docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:latest
82
+ ## Prompts
62
83
 
63
- # Run latest from main branch (continuous deployment)
64
- docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:main
84
+ | Prompt | Args | What it does |
85
+ |---|---|---|
86
+ | `scan` | `url` | Fresh scan + high-level summary (score, rating, top 3–5 failures, next step). |
87
+ | `interpret_scan` | `id` | Plain-English explanation of a previous scan's findings, grouped by category. |
88
+ | `remediation_plan` | `id`, optional `focus` (`"seo"` or `"agents"`) | Prioritised fix-it doc with Now/Next/Later buckets and per-fix check ids. |
65
89
 
66
- # Run specific release version
67
- docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:v1.0.0
90
+ ## Example workflow
68
91
 
69
- # Run development build from main branch
70
- docker run -p 8080:8080 ghcr.io/modelcontextprotocol/registry:main-20250906-abc123d
92
+ ```
93
+ You: Use agent-ready to scan https://my-saas.com
94
+ Claude: [calls scan_site] Your site scored 78/100 (Good) on the Vercel Agent
95
+ Readability Spec. The top 3 fixes: …
96
+ You: Can you build me a remediation plan?
97
+ Claude: [calls remediation_plan with the scan id] Here's the prioritised list…
71
98
  ```
72
99
 
73
- **Available tags:**
74
- - **Releases**: `latest`, `v1.0.0`, `v1.1.0`, etc.
75
- - **Continuous**: `main` (latest main branch build)
76
- - **Development**: `main-<date>-<sha>` (specific commit builds)
100
+ ## Skill (Anthropic Claude Skills)
77
101
 
78
- </details>
102
+ A `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/`.
79
103
 
80
- #### Publishing a server
104
+ The 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).
81
105
 
82
- To publish a server, we've built a simple CLI. You can use it with:
106
+ ## How it works
83
107
 
84
- ```bash
85
- # Build the latest CLI
86
- make publisher
108
+ This package is a thin stdio→HTTPS wrapper:
87
109
 
88
- # Use it!
89
- ./bin/mcp-publisher --help
90
110
  ```
91
-
92
- See [the publisher guide](./docs/modelcontextprotocol-io/quickstart.mdx) for more details.
93
-
94
- #### Other commands
95
-
96
- ```bash
97
- # Run lint, unit tests and integration tests
98
- make check
111
+ MCP client (stdio) ↔ agent-ready-mcp ↔ HTTPS ↔ agent-ready.dev/api/v1/scans
99
112
  ```
100
113
 
101
- There are also a few more helpful commands for development. Run `make help` to learn more, or look in [Makefile](./Makefile).
102
-
103
- <!--
104
- For Claude and other AI tools: Always prefer make targets over custom commands where possible.
105
- -->
114
+ All 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.
106
115
 
107
- ## Architecture
116
+ If 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_...`.
108
117
 
109
- ### Project Structure
118
+ ## Methodology
110
119
 
111
- ```
112
- ├── cmd/ # Application entry points
113
- │ └── publisher/ # Server publishing tool
114
- ├── data/ # Seed data
115
- ├── deploy/ # Deployment configuration (Pulumi)
116
- ├── docs/ # Documentation
117
- ├── internal/ # Private application code
118
- │ ├── api/ # HTTP handlers and routing
119
- │ ├── auth/ # Authentication (GitHub OAuth, JWT, namespace blocking)
120
- │ ├── config/ # Configuration management
121
- │ ├── database/ # Data persistence (PostgreSQL)
122
- │ ├── service/ # Business logic
123
- │ ├── telemetry/ # Metrics and monitoring
124
- │ └── validators/ # Input validation
125
- ├── pkg/ # Public packages
126
- │ ├── api/ # API types and structures
127
- │ │ └── v0/ # Version 0 API types
128
- │ └── model/ # Data models for server.json
129
- ├── scripts/ # Development and testing scripts
130
- ├── tests/ # Integration tests
131
- └── tools/ # CLI tools and utilities
132
- └── validate-*.sh # Schema validation tools
133
- ```
134
-
135
- ### Authentication
120
+ The 69 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).
136
121
 
137
- Publishing supports multiple authentication methods:
138
- - **GitHub OAuth** - For publishing by logging into GitHub
139
- - **GitHub OIDC** - For publishing from GitHub Actions
140
- - **DNS verification** - For proving ownership of a domain and its subdomains
141
- - **HTTP verification** - For proving ownership of a domain
122
+ ## Development
142
123
 
143
- The registry validates namespace ownership when publishing. E.g. to publish...:
144
- - `io.github.domdomegg/my-cool-mcp` you must login to GitHub as `domdomegg`, or be in a GitHub Action on domdomegg's repos
145
- - `me.adamjones/my-cool-mcp` you must prove ownership of `adamjones.me` via DNS or HTTP challenge
124
+ ```bash
125
+ npm install
126
+ npm run build # dist/mcp-server.mjs
127
+ npm test
128
+ npm run typecheck
129
+ ```
146
130
 
147
- ## Community Projects
131
+ ## Releasing
148
132
 
149
- Check out [community projects](docs/community-projects.md) to explore notable registry-related work created by the community.
133
+ See [RELEASE.md](RELEASE.md). It is the source of truth for version surfaces,
134
+ local checks, tag pushing, the GitHub Actions release workflow, and the manual
135
+ post-release steps.
150
136
 
151
- ## More documentation
137
+ ## License
152
138
 
153
- See the [documentation](./docs) for more details if your question has not been answered here!
139
+ MIT see [LICENSE](LICENSE).
@@ -31298,7 +31298,11 @@ The llmstxt.org spec treats some properties as foundational and others as option
31298
31298
 
31299
31299
  ## How are JavaScript-rendered pages handled?
31300
31300
 
31301
- P23 detects pages where the static HTML response lacks data that only appears after client-side rendering \u2014 missing H1, empty body text, JSON-LD that injects after hydration. When P23 fires, the runner marks dependent checks (P10, P11, P12, P14) as \`unreliable\` and the scorer excludes them from both numerator and denominator. Without this, a single SPA architecture choice would compound into a 4-point score drop across unrelated checks.
31301
+ P23 detects pages where the static HTML response lacks data that only appears after client-side rendering \u2014 missing H1, empty body text, JSON-LD that injects after hydration. When P23 fires, the runner marks the dependent per-page checks (P12, P13, P14, P21) as \`unreliable\` and the scorer excludes them from both numerator and denominator. Without this, a single SPA architecture choice would compound into a multi-check score drop.
31302
+
31303
+ **Only what exists is scored.** Most A-checks are conditional \u2014 "if the page has images, they need alt text" \u2014 so on a page with no images, no tables and no media there is nothing to grade. Those results are marked \`notApplicable\` and excluded from both numerator and denominator. Scoring them as passes rewarded a site for what it lacked. Checks that state a prohibition (no positive tabindex, no timed meta refresh) or a document-level requirement (a title, a language, a main landmark) always count \u2014 for those, absence is a real verdict.
31304
+
31305
+ The same gate applies to the accessibility sub-score. Most A-series checks count elements and treat "found none" as a pass; on a client-rendered page the static DOM is a skeleton, so "found none" means "could not look". When P23 fails those checks are marked \`unreliable\` and dropped from the score; if every one is, the score is \`null\` rather than 0. The checks that read \`<head>\` or \`<html>\` (A9 viewport, A10 title, A13 lang, A17 meta refresh) stay trustworthy, because a JS-only shell still serves them.
31302
31306
 
31303
31307
  ## Where is the source for each check?
31304
31308
 
@@ -31407,7 +31411,7 @@ Discover-then-validate: when the relevant well-known endpoint returns 404, the c
31407
31411
  | C20 | AP2 payment protocol support |
31408
31412
  | C21 | ACP profile (/.well-known/acp.json) |
31409
31413
 
31410
- ## Accessibility checks (9)
31414
+ ## Accessibility checks (23)
31411
31415
 
31412
31416
  Run over the homepage DOM (v1). WCAG-grounded accessibility-tree signals \u2014 image text alternatives, form labels, control names \u2014 plus a static layout-stability (CLS) proxy. Scored into a separate \`accessibilityScore\`, a distinct suite from the 69 checks above: accessibility is WCAG, not the Vercel Agent Readability Spec, so it never moves the Vercel score.
31413
31417
 
@@ -31422,10 +31426,23 @@ Run over the homepage DOM (v1). WCAG-grounded accessibility-tree signals \u2014
31422
31426
  | A7 | Heading hierarchy is well-formed |
31423
31427
  | A8 | No positive tabindex |
31424
31428
  | A9 | Pinch-zoom is not disabled |
31425
- `;
31429
+ | A10 | Page has a title |
31430
+ | A11 | Accessible name contains the visible label |
31431
+ | A12 | Content is reachable past the chrome |
31432
+ | A13 | Language tag is valid |
31433
+ | A14 | Hidden elements are not focusable |
31434
+ | A15 | Interactive controls are not nested |
31435
+ | A16 | Headings are not empty |
31436
+ | A17 | No timed meta refresh |
31437
+ | A18 | Autocomplete tokens are valid |
31438
+ | A19 | Tables declare their headers |
31439
+ | A20 | SVG images have a text alternative |
31440
+ | A21 | Media declares a captions track |
31441
+ | A22 | List structure is well-formed |
31442
+ | A23 | ARIA roles and attributes are valid |`;
31426
31443
  var LLMS_TXT = `# Agent Ready
31427
31444
 
31428
- > Agent Ready is a free tool that scores any website against the Vercel Agent Readability Spec, the llmstxt.org specification, and agent-protocol specs (MCP, A2A, agents.json). It runs 69 checks \u2014 plus a separate accessibility sub-score from 9 WCAG 2.2 / layout-stability checks \u2014 and provides actionable fix guidance for every failing check.
31445
+ > Agent Ready is a free tool that scores any website against the Vercel Agent Readability Spec, the llmstxt.org specification, and agent-protocol specs (MCP, A2A, agents.json). It runs 69 checks \u2014 plus a separate accessibility sub-score from 23 WCAG 2.2 / layout-stability checks \u2014 and provides actionable fix guidance for every failing check.
31429
31446
 
31430
31447
  This resource mirrors agent-ready.dev's own /llms.txt so MCP clients can introspect the same surface that ChatGPT, Perplexity, and other AI agents see when discovering Agent Ready as a tool.
31431
31448
 
@@ -31463,7 +31480,7 @@ Agent Ready's checks map to the specifications below. Each entry links to the ca
31463
31480
 
31464
31481
  ## Agent protocols
31465
31482
 
31466
- - **MCP Server Cards (SEP-1649)** \u2014 The Model Context Protocol discovery card at /.well-known/mcp.json \u2014 its presence (C1) and required fields (C2). Canonical: <https://github.com/modelcontextprotocol/modelcontextprotocol/issues/1649> Checks: C1, C2.
31483
+ - **MCP Server Cards (SEP-2127)** \u2014 The Model Context Protocol discovery card at /.well-known/mcp.json \u2014 its presence (C1) and required fields (C2). SEP-2127 (a server.json subset) superseded the earlier SEP-1649 proposal. Canonical: <https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2127> Checks: C1, C2.
31467
31484
  - **OAuth Protected Resource Metadata (RFC 9728)** \u2014 Protected-resource metadata an MCP server advertises so agents can locate its authorization server. Canonical: <https://datatracker.ietf.org/doc/html/rfc9728> Checks: C3.
31468
31485
  - **A2A Protocol \u2014 Agent Cards** \u2014 The agent card at /.well-known/agent-card.json that lets agents discover and call other agents \u2014 existence with correct Content-Type (C4) and required fields (C5). Canonical: <https://a2a-protocol.org/v1.0.0/specification> Checks: C4, C5.
31469
31486
  - **Wildcard agents.json** _(pre-standard)_ \u2014 An OpenAPI extension declaring which existing REST endpoints agents should call. Pre-standard (v0.1.0). Canonical: <https://github.com/wild-card-ai/agents-json> Checks: C6.
@@ -31489,8 +31506,7 @@ Agent Ready's checks map to the specifications below. Each entry links to the ca
31489
31506
 
31490
31507
  ## Accessibility
31491
31508
 
31492
- - **WCAG 2.2 + layout stability** \u2014 The accessibility tree \u2014 image text alternatives, form labels, control names, resolved ARIA references, named iframes, a clean heading outline \u2014 is what assistive tech and AI agents parse to act on a page; explicit media dimensions and enabled zoom keep it stable and usable (with a static CLS proxy). Scored as a separate accessibilityScore, not part of the Vercel score. Canonical: <https://www.w3.org/TR/WCAG22/> Checks: A1\u2013A9.
31493
- `;
31509
+ - **WCAG 2.2 + layout stability** \u2014 The accessibility tree \u2014 image text alternatives, form labels, control names, resolved ARIA references, named iframes, a page title, a valid language tag, a main landmark, accessible names that match their visible text, valid ARIA, well-formed lists and tables, and autofill tokens an agent can act on \u2014 is what assistive tech and AI agents parse to act on a page; explicit media dimensions and enabled zoom keep it stable and usable (with a static CLS proxy). Scored as a separate accessibilityScore, not part of the Vercel score. Canonical: <https://www.w3.org/TR/WCAG22/> Checks: A1\u2013A23.`;
31494
31510
 
31495
31511
  // src/resources.ts
31496
31512
  function registerResources(server) {
@@ -31844,7 +31860,7 @@ var validateStructuredDataInputShape = {
31844
31860
  // src/server.ts
31845
31861
  var SERVER_INFO = {
31846
31862
  name: "agent-ready",
31847
- version: "0.7.0"
31863
+ version: "0.7.1"
31848
31864
  };
31849
31865
  function createMcpServer(config2) {
31850
31866
  const server = new McpServer(SERVER_INFO);
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "agent-ready-mcp",
3
- "version": "0.7.0",
3
+ "version": "0.7.1",
4
4
  "mcpName": "io.github.mlava/agent-ready-mcp",
5
5
  "description": "MCP server for Agent Ready — scan any URL for AI-readability against the Vercel Agent Readability Spec, the llmstxt.org standard, and agent-protocol manifests (MCP server cards, A2A, agents.json, agent-permissions.json, UCP, x402, NLWeb). 69 checks with per-check fix guidance.",
6
6
  "license": "MIT",