What is composio.dev's AI agent readiness grade?

composio.dev publishes 6 agent-facing standards across 4 of 9 lifecycle steps (grade A+, checked 2026-10-27).

Which AI agent discovery manifests and crawler policies does composio.dev publish?

composio.dev publishes 6 observed agentic-web standards (llms.txt, Content Signals Policy, AI Catalog well-known file, api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs, Markdown for Agents, Model Context Protocol). Preferred agent routing mode: mcp.

composio.dev agentic web readiness

A+ Manifest validity: 100% (3/3 valid, 0 errors, 23 warnings) · Surface score 67 (coverage 40 + breadth 12 + conformance 15). 6 standards observed across 4 of 9 steps; 3 manifests present (+ robots.txt, security.txt), 0 errors, 23 warnings. Checked 2026-10-27 02:14:18 UTC. This grades the agent-facing files published at composio.dev, not the organisation's products.

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

Coverage by step

01 DiscoverAI Catalog well-known file, RFC 9727 02 Identifynothing observed 03 PermitContent Signals Policy 04 Readllms.txt, Markdown for Agents 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`	absent HTTP 404
AI Catalog well-known file `/.well-known/ai-catalog.json`	valid	entries[0].identifier is not a urn:air: identifier entries[0] has no description; registries index on it entries[1].identifier is not a urn:air: identifier entries[2].identifier is not a urn:air: identifier entries[3].identifier is not a urn:air: identifier entries[3] has no description; registries index on it entries[4].identifier is not a urn:air: identifier entries[4] has no description; registries index on it entries[5].identifier is not a urn:air: identifier entries[5] has no description; registries index on it entries[6].identifier is not a urn:air: identifier entries[6] has no description; registries index on it entries[7].identifier is not a urn:air: identifier entries[7] has no description; registries index on it entries[8].identifier is not a urn:air: identifier entries[8] has no description; registries index on it entries[9].identifier is not a urn:air: identifier entries[9] has no description; registries index on it no entry has representativeQueries; ARD registries use 2-5 example queries to index entries served only at deprecated /.well-known/ai-catalog.json; ARD v0.91+ expects /.well-known/ard.json (serve both during migration)
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`	valid
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)
security.txt (RFC 9116) `/.well-known/security.txt`	valid
auth.md `/auth.md`	timeout	not fetched: timeout
Open Knowledge Format `/okf/index.md`	absent HTTP 404

What an agent can call

MCP endpoint https://connect.composio.dev/mcp (streamable-http) — from /mcp/server-card.json
API description https://composio.dev/.well-known/api-catalog (application/linkset+json)
API description https://docs.composio.dev/reference (text/html)
API description https://docs.composio.dev/docs/composio-connect (text/html)
API description https://composio.dev/mcp/server-card.json (application/mcp-server-card+json)
llms.txt: Composio, 83 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/ai-catalog.json): 4/10 valid, 0 legacy, 1 dead/broken (served at deprecated path only)

Standards observed

llms.txt https://composio.dev/llms.txt
Content Signals Policy https://composio.dev/robots.txt
AI Catalog well-known file https://composio.dev/.well-known/ai-catalog.json
api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://composio.dev/.well-known/api-catalog
Markdown for Agents https://composio.dev/
Model Context 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 (emerging spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "ard", "domain": "composio.dev"}))

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

Generate starter /AGENTS.md for composio.dev

# Composio for agents

Composio and what it offers to agents

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

## Calling
- MCP server (Streamable HTTP): https://composio.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@composio.dev

MCP Server Cards (SEP-2127): if you run an MCP server, a SEP-2127 card at <mcp-url>/server-card lets clients configure themselves (conditional spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "mcp-server-cards", "domain": "composio.dev"}))

Agent pre-flight & practical readiness

Preferred mode: mcp (fallback llms_txt). Call the MCP endpoint at https://connect.composio.dev/mcp first. Do not scrape the HTML when a tool can answer.

Fetch: POST https://connect.composio.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 21/35, conformance 15/15, total 86/100, 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