What is exa.ai's AI agent readiness grade?

exa.ai publishes 4 agent-facing standards across 2 of 9 lifecycle steps (grade B, checked 2026-10-25).

Which AI agent discovery manifests and crawler policies does exa.ai publish?

exa.ai publishes 4 observed agentic-web standards (llms.txt, Agentic Resource Discovery, AI Catalog well-known file, Markdown for Agents). Preferred agent routing mode: mcp.

exa.ai agentic web readiness

B Manifest validity: 100% (3/3 valid, 0 errors, 5 warnings) · Surface score 41 (coverage 20 + breadth 6 + conformance 15). 4 standards observed across 2 of 9 steps; 3 manifests present (+ robots.txt), 0 errors, 5 warnings. Checked 2026-10-25 13:30:19 UTC. This grades the agent-facing files published at exa.ai, not the organisation's products.

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

Coverage by step

01 DiscoverARD, AI Catalog well-known file 02 Identifynothing observed 03 Permitnothing observed 04 Readllms.txt, Markdown for Agents 05 Actnothing observed 06 Coordinatenothing observed 07 Paynothing observed 08 Presentnothing observed 09 Accountnothing observed

Manifests

Manifest	Result	Findings
Agentic Resource Discovery `/.well-known/ard.json`	valid	host block missing (displayName, identifier, documentationUrl help clients name the publisher)
AI Catalog well-known file `/.well-known/ai-catalog.json`	valid	host block missing (displayName, identifier, documentationUrl help clients name the publisher)
MCP Server Cards (SEP-2127) `/mcp/server-card`	absent HTTP 404
Agent2Agent Protocol `/.well-known/agent-card.json`	absent HTTP 404
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`	no AI tokens	no AI crawler token named (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, ...); the policy for them is whatever User-agent: * says (partial) no Agentmap: line (optional convention pointing agents at /.well-known/ard.json) no Content-Signal: line (optional; states ai-train / search / ai-input preferences)
security.txt (RFC 9116) `/.well-known/security.txt`	absent HTTP 404
auth.md `/auth.md`	absent HTTP 404
Open Knowledge Format `/okf/index.md`	absent HTTP 404

What an agent can call

MCP endpoint https://mcp.exa.ai/mcp (streamable-http) — from /.well-known/ard.json
MCP endpoint https://mcp.exa.ai/mcp (streamable-http) — from /.well-known/ai-catalog.json
API description https://api.exa.ai/openapi.json (application/vnd.oai.openapi+json)
API description https://api.exa.ai/openapi.json (application/vnd.oai.openapi+json)
llms.txt: Exa, 77 links, llms-full.txt present
robots.txt AI policy: no AI crawler tokens named; unlisted crawlers allowed on public paths (subpaths disallowed under User-agent: *)
ARD bridge (/.well-known/ard.json): 0/3 valid, 0 legacy, 0 dead/broken

Standards observed

llms.txt https://exa.ai/llms.txt
Agentic Resource Discovery https://exa.ai/.well-known/ard.json
AI Catalog well-known file https://exa.ai/.well-known/ai-catalog.json
Markdown for Agents https://exa.ai/

Cheapest next steps

AGENTS.md: instructions for coding agents working on or with the site

Generate starter /AGENTS.md for exa.ai

# Exa for agents

Exa and what it offers to agents

## Read the data, not the HTML
- Index: https://exa.ai/llms.txt
- API description: https://exa.ai/openapi.json
- Discovery catalog: https://exa.ai/.well-known/ard.json

## Calling
- MCP server (Streamable HTTP): https://exa.ai/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@exa.ai

api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs: an RFC 9727 linkset pointing at your OpenAPI description (conditional spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "api-catalog-rfc9727", "domain": "exa.ai"}))

security.txt (RFC 9116): RFC 9116 contact and expiry, read by agents and people

Generate starter /.well-known/security.txt for exa.ai

Contact: mailto:security@exa.ai
Expires: 2027-09-20T23:45:20Z
Canonical: https://exa.ai/.well-known/security.txt
Preferred-Languages: en
Policy: https://exa.ai/security-policy

Agent pre-flight & practical readiness

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

Fetch: POST https://mcp.exa.ai/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 19/20, readability 30/30, capabilities 34/35, conformance 15/15, total 98/100, 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