speakeasy.com agentic web readiness

A+ Manifest validity: 67% (4/6 valid, 5 errors, 15 warnings) · Surface score 60 (coverage 40 + breadth 15 + conformance 5). 7 standards observed across 4 of 9 steps; 6 manifests present, 5 errors, 15 warnings. Checked 2026-10-23 14:57:37 UTC via www.speakeasy.com. This grades the agent-facing files published at speakeasy.com, not the organisation's products.

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

Coverage by step

01 DiscoverAI Catalog well-known file, RFC 9727 02 Identifynothing observed 03 PermitContent Signals Policy, AI Crawler User-Agent Tokens in robots.txt 04 Readllms.txt, Markdown for Agents 05 Actnothing observed 06 Coordinate 07 Paynothing observed 08 Presentnothing observed 09 Accountnothing observed

Manifests

Manifest	Result	Findings
Agentic Resource Discovery `/.well-known/ard.json`	absent HTTP 404
AI Catalog well-known file `/.well-known/ai-catalog.json`	valid
MCP Server Cards (SEP-2127) `/.well-known/mcp/server-card.json`	errors	$schema missing (required: https://static.modelcontextprotocol.io/schemas/v1/server-card.schema.json) name must be reverse-DNS with exactly one slash, e.g. com.example/weather Content-Type is application/json; charset=utf-8; SEP-2127 says serve application/mcp-server-card+json pre-final card shape (url/transport/tools); the final SEP-2127 card uses name, version, description and remotes[] description is over 100 characters remotes missing: a card with no remotes gives clients nothing to connect to tools/resources/prompts listed in the card; SEP-2127 excludes primitives (list them live, or under a namespaced _meta key)
Agent2Agent Protocol `/.well-known/agent.json`	errors	version missing url missing (or supportedInterfaces in the 1.0 shape) skills missing or not an array supportedInterfaces missing; A2A 1.0 cards declare interfaces there (url, protocolBinding, protocolVersion) and the top-level url is the 0.3 shape capabilities object missing (streaming, pushNotifications, stateTransitionHistory) defaultInputModes missing defaultOutputModes missing protocolVersion missing; clients cannot tell which A2A revision the card follows provider missing (organization, url) served at /.well-known/agent.json; A2A 0.3+ reads /.well-known/agent-card.json
llms.txt `/llms.txt`	valid
AGENTS.md `/AGENTS.md`	absent HTTP 404
Agent Skills `/.well-known/agent-skills/index.json`	absent HTTP 404
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs `/.well-known/api-catalog`	absent HTTP 404
AI Crawler User-Agent Tokens in robots.txt `/robots.txt`	valid	robots.txt names AI crawlers (Bytespider, Diffbot) only to Disallow: / — blocks AI agents rather than enabling them
security.txt (RFC 9116) `/.well-known/security.txt`	valid	Canonical: missing
auth.md `/auth.md`	absent HTTP 404
Open Knowledge Format `/okf/index.md`	absent HTTP 404

What an agent can call

MCP endpoint https://ai.speakeasy.com/platform-mcp (streamable-http) — from /.well-known/ai-catalog.json
API description https://www.speakeasy.com/openapi.yaml (application/openapi+yaml)
API description https://speakeasy.com/openapi.yaml (service-desc)
llms.txt: Speakeasy, 86 links, llms-full.txt present
robots.txt AI policy: blocks Bytespider, Diffbot; unlisted crawlers allowed; Agentmap https://www.speakeasy.com/.well-known/ai-catalog.json

Standards observed

llms.txt https://speakeasy.com/llms.txt
Content Signals Policy https://speakeasy.com/robots.txt
AI Catalog well-known file https://speakeasy.com/.well-known/ai-catalog.json
AI Crawler User-Agent Tokens in robots.txt https://speakeasy.com/robots.txt
Markdown for Agents https://speakeasy.com/
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://speakeasy.com/openapi.yaml
Agent2Agent Protocol

Cheapest next steps

Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch
AGENTS.md: instructions for coding agents working on or with the site

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback openapi). Call the MCP endpoint at https://ai.speakeasy.com/platform-mcp first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://ai.speakeasy.com/platform-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 34/35, conformance 5/15, total 89/100, 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