pydantic.dev agentic web readiness

A+ Manifest validity: 71% (5/7 valid, 3 errors, 14 warnings) · Surface score 70 (coverage 50 + breadth 15 + conformance 5). 11 standards observed across 5 of 9 steps; 7 manifests present (+ security.txt), 3 errors, 14 warnings. Checked 2026-10-25 19:16:56 UTC. This grades the agent-facing files published at pydantic.dev, not the organisation's products.

Badge for a README: ![agentic web grade](https://agenticweb.wiki/badge/pydantic.dev.svg) · JSON · Markdown · Re-check now

Coverage by step

Manifests

{
  "specVersion": "1.0",
  "host": {
    "displayName": "Pydantic",
    "identifier": "did:web:pydantic.dev",
    "documentationUrl": "https://pydantic.dev/AGENTS.md"
  },
  "entries": [
    {
      "identifier": "urn:air:pydantic.dev:mcp:pydantic",
      "displayName": "Pydantic MCP server",
      "type": "application/mcp-server-card+json",
      "url": "https://pydantic.dev/mcp/server-card",
      "description": "Pydantic and what it offers to agents. Streamable HTTP MCP server.",
      "representativeQueries": [
        "what can the Pydantic MCP server do",
        "use Pydantic tools from an agent"
      ],
      "tags": [
        "mcp",
        "mcp-server"
      ]
    },
    {
      "identifier": "urn:air:pydantic.dev:api:openapi",
      "displayName": "Pydantic API description",
      "type": "application/openapi+json",
      "url": "https://pydantic.dev/openapi.json",
      "description": "OpenAPI description of the Pydantic API.",
      "representativeQueries": [
        "Pydantic API reference"
      ],
      "tags": [
        "openapi",
        "api"
      ]
    }
  ]
}

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/v1/server-card.schema.json",
  "name": "dev.pydantic/pydantic",
  "title": "Pydantic",
  "version": "1.0.0",
  "description": "Pydantic and what it offers to agents",
  "websiteUrl": "https://pydantic.dev/",
  "icons": [
    {
      "src": "https://pydantic.dev/icon.png",
      "mimeType": "image/png",
      "sizes": [
        "180x180"
      ]
    }
  ],
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://pydantic.dev/mcp",
      "supportedProtocolVersions": [
        "2025-11-25",
        "2025-06-18",
        "2025-03-26"
      ]
    }
  ]
}

What an agent can call

• MCP endpoint https://logfire-us.pydantic.dev/mcp (streamable-http), tools: token_info, query_schema_reference, query_run, query_find_exceptions_in_file, project_list, project_logfire_link, dashboard_list, dashboard_get, dashboard_create, dashboard_update, dashboard_delete, dashboard_update_settings, dashboard_add_panel, dashboard_update_panel, dashboard_remove_panel, dashboard_update_variables, dashboard_add_variable, dashboard_update_variable, dashboard_remove_variable, dashboard_create_group — from /.well-known/mcp.json
• MCP endpoint https://logfire-us.pydantic.dev/mcp (streamable-http), tools: token_info, query_schema_reference, query_run, query_find_exceptions_in_file, project_list, project_logfire_link, dashboard_list, dashboard_get, dashboard_create, dashboard_update, dashboard_delete, dashboard_update_settings, dashboard_add_panel, dashboard_update_panel, dashboard_remove_panel, dashboard_update_variables, dashboard_add_variable, dashboard_update_variable, dashboard_remove_variable, dashboard_create_group — from /.well-known/mcp/server-card.json
• A2A agent Pydantic at https://logfire-us.pydantic.dev/mcp, skills: Query telemetry data, Manage dashboards, Manage alerts, Manage feature flags, Manage notification channels, Execute Python in a sandbox
• API description https://pydantic.dev/docs/api/openapi.json (application/openapi+json)
• API description https://pydantic.dev/.well-known/api-catalog (application/linkset+json)
• API description https://pydantic.dev/docs/logfire/get-started (text/html)
• API description https://pydantic.dev/.well-known/openapi-specs (application/json)
• API description https://pydantic.dev/docs/api/openapi.json (application/openapi+json)
• API description https://pydantic.dev/docs/llms.txt (text/plain)
• API description https://logfire-us.pydantic.dev/api/openapi.json (application/openapi+json)
• API description https://pydantic.dev/docs/logfire/get-started (text/html)
• API description https://logfire-us.pydantic.dev/.well-known/oauth-protected-resource (application/json)
• API description https://logfire-eu.pydantic.dev/api/openapi.json (application/openapi+json)
• API description https://pydantic.dev/docs/logfire/get-started (text/html)
• API description https://logfire-eu.pydantic.dev/.well-known/oauth-protected-resource (application/json)
• llms.txt: Pydantic, 78 links, llms-full.txt present
• robots.txt AI policy: allows GPTBot, ChatGPT-User, ClaudeBot, Google-Extended, PerplexityBot, CCBot, Bytespider; unlisted crawlers allowed
• OAuth protected resource https://logfire-us.pydantic.dev, authorization servers: https://logfire-us.pydantic.dev
• ARD bridge (/.well-known/ard.json): 2/4 valid, 1 legacy, 0 dead/broken

Standards observed

• Agent2Agent Protocol https://pydantic.dev/.well-known/agent-card.json
• llms.txt https://pydantic.dev/llms.txt
• Content Signals Policy https://pydantic.dev/robots.txt
• Agentic Resource Discovery https://pydantic.dev/.well-known/ard.json
• api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://pydantic.dev/.well-known/api-catalog
• AI Crawler User-Agent Tokens in robots.txt https://pydantic.dev/robots.txt
• OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization) https://pydantic.dev/.well-known/oauth-protected-resource
• Agent Skills https://pydantic.dev/.well-known/agent-skills/index.json
• Markdown for Agents https://pydantic.dev/
• MCP Server Cards (SEP-2127)
• Model Context Protocol

Cheapest next steps

1. AGENTS.md: instructions for coding agents working on or with the site
   Generate starter /AGENTS.md for pydantic.dev

   # Pydantic for agents
   
   Pydantic and what it offers to agents
   
   ## Read the data, not the HTML
   - Index: https://pydantic.dev/llms.txt
   - API description: https://pydantic.dev/openapi.json
   - Discovery catalog: https://pydantic.dev/.well-known/ard.json
   
   ## Calling
   - MCP server (Streamable HTTP): https://pydantic.dev/mcp
   - Rate limits and authentication: describe them here
   
   ## Conventions
   - How to cite or attribute content
   - What not to do (no scraping of /account/, no automated sign-ups, etc.)
   
   Contact: security@pydantic.dev
   

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback openapi). Call the MCP endpoint at https://logfire-us.pydantic.dev/mcp first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://logfire-us.pydantic.dev/mcp POST a JSON-RPC tools/list, or server/discover on the 2026-07-28 revision, before reading HTML.

Practical readability: exa_parsable yes, markdown negotiation yes, render markdown_native, HTML quality high, first content at byte 0.

AI crawler posture: open_to_all · Assistant access: OpenAI allowed, Anthropic allowed, Google allowed, Perplexity allowed, Exa allowed.

Readiness subscores: reach 20/20, readability 30/30, capabilities 35/35, conformance 5/15, total 90/100, grade A+.

How the grade is made

+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). Lifecycle grade: A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Strict 100-point composite (subscores.total_100 / subscores.grade_100): reach_and_policy (20) + readability (30) + capabilities (35) + conformance (15), where A+ >= 80, A >= 65, B >= 45, C >= 28, D >= 15. Errors are specification violations; warnings are best-practice gaps. Only public paths are fetched, without credentials, so standards that need a login (skipped in the probe) are not counted either way. The same report is the validate_manifest tool on the MCP server.

JSON · Markdown · probe rules