developers.deepgram.com agentic web readiness

A Manifest validity: 60% (3/5 valid, 3 errors, 6 warnings) · Surface score 47 (coverage 30 + breadth 12 + conformance 5). 6 standards observed across 3 of 9 steps; 5 manifests present (+ robots.txt, security.txt), 3 errors, 6 warnings. Checked 2026-10-25 03:11:15 UTC. This grades the agent-facing files published at developers.deepgram.com, not the organisation's products.

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

Coverage by step

Manifests

# Authenticating to Developers as an agent

This file is the agent-auth skill for developers.deepgram.com. It is linked from the authorization server's metadata (`agent_auth.skill`).

## Discovery
1. Call the API. A `401` carries `WWW-Authenticate: Bearer resource_metadata="https://developers.deepgram.com/.well-known/oauth-protected-resource"`.
2. Read `/.well-known/oauth-protected-resource` (RFC 9728) for `resource` and `authorization_servers`.
3. Read the authorization server's `/.well-known/oauth-authorization-server` (RFC 8414); the `agent_auth` block lists the endpoints below.

## Methods we accept
- `identity_assertion`: you hold a session for a user and can mint an ID-JAG with `aud` = our `resource`. Preferred.
- `service_auth`: you only know the user's email. A claim ceremony (6-digit code) is required.
- `anonymous`: no user. Immediate limited scopes; the user can claim later.

## Register
POST `agent_auth.identity_endpoint` with `{"type": "<method>", ...}`; exchange the returned `identity_assertion` at the token endpoint for an access token.

## Scopes
- `api.read`: read
- `api.write`: write (claimed registrations only)

## Rules
- Show the user our name and the scopes before asserting their identity.
- Keep `claim_token` in memory only.
- Revocation events arrive as Security Event Tokens at your registered events endpoint.

---
okf_version: "0.2"
title: "Developers Knowledge Bundle"
description: "Developers and what it offers to agents"
---

# Developers Knowledge Bundle

> Developers and what it offers to agents

- [Update Log](log.md)

## Concepts

- [Developers Overview](concepts/developers.md) — Developers and what it offers to agents

What an agent can call

• API description https://developers.deepgram.com/openapi/rest-api.yaml (application/yaml)
• API description https://developers.deepgram.com/reference (text/html)
• llms.txt: Deepgram's Docs, 322 links, llms-full.txt present
• OKF bundle (/okf/index.md): Page Not Found, 3 concept links
• robots.txt AI policy: no AI crawler tokens named; unlisted crawlers allowed on public paths (subpaths disallowed under User-agent: *)
• OAuth protected resource https://developers.deepgram.com, authorization servers: https://developers.deepgram.com/_mcp/oauth

Standards observed

• llms.txt https://developers.deepgram.com/llms.txt
• AGENTS.md https://developers.deepgram.com/AGENTS.md
• api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs https://developers.deepgram.com/.well-known/api-catalog
• OAuth Protected Resource and Authorization Server Metadata (as used for agent authorization) https://developers.deepgram.com/.well-known/oauth-protected-resource
• OAuth Client ID Metadata Document https://developers.deepgram.com/.well-known/oauth-authorization-server
• Markdown for Agents https://developers.deepgram.com/

Cheapest next steps

1. 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": "developers.deepgram.com"}))
2. 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": "developers.deepgram.com"}))

Agent pre-flight & practical readiness

Preferred mode: openapi (fallback llms_txt). Read the published API description and call those operations. Scraping HTML skips the interface the site already gave you.

Fetch: GET https://developers.deepgram.com/openapi/rest-api.yaml GET the API description and call the documented operations.

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 28/30, capabilities 16/35, conformance 5/15, total 68/100, 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