What is memgraph.com's AI agent readiness grade?

memgraph.com publishes 3 agent-facing standards across 3 of 9 lifecycle steps (grade A, checked 2026-10-25).

Which AI agent discovery manifests and crawler policies does memgraph.com publish?

memgraph.com publishes 3 observed agentic-web standards (llms.txt, Agentic Resource Discovery, Model Context Protocol). Preferred agent routing mode: mcp.

memgraph.com agentic web readiness

A Manifest validity: 100% (2/2 valid, 0 errors, 5 warnings) · Surface score 48 (coverage 30 + breadth 3 + conformance 15). 3 standards observed across 3 of 9 steps; 2 manifests present (+ robots.txt), 0 errors, 5 warnings. Checked 2026-10-25 23:10:57 UTC. This grades the agent-facing files published at memgraph.com, not the organisation's products.

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

Coverage by step

01 DiscoverARD 02 Identifynothing observed 03 Permitnothing observed 04 Readllms.txt 05 Act 06 Coordinatenothing observed 07 Paynothing observed 08 Presentnothing observed 09 Accountnothing observed

Manifests

Manifest	Result	Findings
Agentic Resource Discovery `/.well-known/ard.json`	valid
AI Catalog well-known file `/.well-known/ai-catalog.json`	absent HTTP 404
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-docs.memgraph.com (streamable-http) — from /.well-known/ard.json#urn:air:memgraph.com:server:docs
llms.txt: Memgraph, 60 links
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, 1 legacy, 1 dead/broken

Standards observed

llms.txt https://memgraph.com/llms.txt
Agentic Resource Discovery https://memgraph.com/.well-known/ard.json
Model Context Protocol

Cheapest next steps

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

Generate starter /AGENTS.md for memgraph.com

# Memgraph for agents

Memgraph and what it offers to agents

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

## Calling
- MCP server (Streamable HTTP): https://memgraph.com/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@memgraph.com

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": "memgraph.com"}))

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

Generate starter /.well-known/security.txt for memgraph.com

Contact: mailto:security@memgraph.com
Expires: 2027-09-20T23:10:57Z
Canonical: https://memgraph.com/.well-known/security.txt
Preferred-Languages: en
Policy: https://memgraph.com/security-policy

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback agent_skills). Call the MCP endpoint at https://mcp-docs.memgraph.com first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://mcp-docs.memgraph.com 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 no, render ssr_rich, HTML quality high, first content at byte 24793, HTML-to-llms.txt token ratio 21.224×.

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

Readiness subscores: reach 20/20, readability 20/30, capabilities 24/35, conformance 15/15, total 79/100, 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