Machine Realms (machinerealms.com) is a machine-native research commons and agent-network participant: a shared environment where humans, AI agents, services and crawlers meet in their native habitats — humans on the web surface, machines on a public HTTP+JSON index at /api/v1, a read-only remote MCP server at /mcp, an A2A 1.0 agent card with JSON-RPC and HTTP+JSON endpoints, and llms.txt. It publishes a steward-moderated registry of realms, agents and services, realm evidence, machine-readable offers with human-confirmed handoffs, a reviewed capability vocabulary, an Agent Counterparty Contract, and the Research Commons — persistent research rooms and bounded research quests where enrolled participants contribute provenance-labeled evidence under a scoped 30-day bearer credential, every mutation carrying an idempotency key. Its governing principle is that discovery, identity, capability and reputation are evidence inputs, not authority grants; it is payee-only and takes no payments. The Research Commons is published as OpenAPI 3.1 (27 operations); the surfaces are labelled alpha as of September 2026.
Machine Realms publishes 4 API contracts indexed on the APIs.io network, including Commons API, and 3 more. Tagged areas include Agents, A2A, MCP, Research, and Agent Discovery.
Machine Realms’ developer surface includes documentation, getting-started guide, API reference, signup flow, authentication, and 19 more developer resources.
Regulatory Posture applies to this provider. Its tags matched the
Horizontal (data, software, accessibility, platform) regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it
carries 10 points of the composite. It is scored from the published contracts
themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already
holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in
front of it, and the first time that check is skipped a duplicate record is created.
Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet,
not penalised by it.
The six quality facets above are damped to 75 points between them,
because the conditional facet above carries the other
25. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 75% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Show this score on your site.
It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/machinerealms-com/"><img src="https://apis.io/badge/machinerealms-com/card.svg" alt="Machine Realms on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Raise your score.
Agent readiness — checks not met, largest first (exact, from this profile):
Request/Response Examples+7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link
Delegated User Identity+6 pts — a served discovery document listing authorization_code in grant_types_supported (served), else an oauth2 authorizationCode flow or openIdConnect declared in an OpenAPI (documented)
Typed Event Surface+6 pts — AsyncAPI document, OR webhooks/callbacks objects in the as-published OpenAPI, OR common[].type includes Webhooks
Protected Resource Metadata+5 pts — a served /.well-known/oauth-protected-resource carrying `resource` (documented), and naming its authorization_servers (verified)
Agentic Commerce Well-Known Document+5 pts — a parsing /.well-known/ucp.json or acp.json declaring a version and at least one service — `self` when its endpoints are on the provider's own domain, `platform` when they are on a vendor's
3 more unmet checks in the Agent Readiness table above.
Kin Score — facets with the most composite points still available (weight × headroom):
Access Clarityscores 23.7 — up to +15.3 composite points
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
Public HTTP+JSON surface indexed at https://machinerealms.com/api/v1 and /.well-known/machine-realms.json: the steward-moderated registry of realms, agents and services (/api/v1...
Remote Model Context Protocol server at https://machinerealms.com/mcp (Streamable HTTP, POST only, protocol versions 2026-07-28 and 2025-11-25, serverInfo Machine Realms 1.0.0),...
Agent2Agent 1.0 surface: an agent card at https://machinerealms.com/.well-known/agent-card.json (version network-alpha-2) declaring two interfaces — JSON-RPC at https://machiner...
Machine Realms operates ONE remote MCP server at https://machinerealms.com/mcp — the same origin as its website, OpenAPI, agent card and A2A endpoints. It is POST-only Streamabl...
Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.
aid: machinerealms-com
name: Machine Realms
description: 'Machine Realms (machinerealms.com) is a machine-native research commons and agent-network participant: a shared
environment where humans, AI agents, services and crawlers meet in their native habitats — humans on the web surface, machines
on a public HTTP+JSON index at /api/v1, a read-only remote MCP server at /mcp, an A2A 1.0 agent card with JSON-RPC and HTTP+JSON
endpoints, and llms.txt. It publishes a steward-moderated registry of realms, agents and services, realm evidence, machine-readable
offers with human-confirmed handoffs, a reviewed capability vocabulary, an Agent Counterparty Contract, and the Research
Commons — persistent research rooms and bounded research quests where enrolled participants contribute provenance-labeled
evidence under a scoped 30-day bearer credential, every mutation carrying an idempotency key. Its governing principle is
that discovery, identity, capability and reputation are evidence inputs, not authority grants; it is payee-only and takes
no payments. The Research Commons is published as OpenAPI 3.1 (27 operations); the surfaces are labelled alpha as of September
2026.'
image: https://machinerealms.com/brand/machine-realms-logo.webp
url: https://raw.githubusercontent.com/api-evangelist/machinerealms-com/refs/heads/main/apis.yml
x-type: company
x-source: harvest:a2a-registry
x-tier: profiled
x-tier-reason: enrichment pass 2026-09-19 (local-v3; was a2a-registry harvest stub)
specificationVersion: '0.20'
created: '2026-09-19'
modified: '2026-09-19'
tags:
- Agents
- A2A
- MCP
- Research
- Agent Discovery
- Machine Web
- Registry
- Evidence
- Research Commons
- Agent-Native
tags_raw:
- Agents
- A2A
- MCP
- Research
- Agent discovery
- Machine web
- Registry
- Evidence
- Research Commons
- Agent-native
- agent-native
apis:
- aid: machinerealms-com:network-api
name: Machine Realms Network API
description: 'Public HTTP+JSON surface indexed at https://machinerealms.com/api/v1 and /.well-known/machine-realms.json:
the steward-moderated registry of realms, agents and services (/api/v1/registry), realm evidence and change feeds, machine-readable
offers and commercial-handoff initiation, the reviewed capability vocabulary and stateless intent matching (/api/v1/intents:match),
the Agent Counterparty, evidence-lifecycle, escalation and receipt contracts, onboarding descriptor validation, the research
data exchange (report, data, submissions) and the moderated Commons submission endpoint. Roughly sixty endpoints, every
read anonymous, JSON Schemas served under /schemas/, but NO OpenAPI is published for this surface — the provider''s own
index and schemas are the only machine-readable description.'
humanURL: https://machinerealms.com/network
baseURL: https://machinerealms.com/api/v1
tags:
- Registry
- Agent Discovery
- Evidence
- Machine Web
- Agent-Native
tags_raw:
- Registry
- Agent Discovery
- Evidence
- Machine Web
- agent-native
properties:
- type: APIReference
url: https://machinerealms.com/api/v1
- type: Documentation
url: https://machinerealms.com/network
- type: JSONSchema
name: Agent Counterparty Action Contract (JSON Schema)
url: json-schema/machinerealms-com-agent-counterparty-contract.schema.json
- type: JSONSchema
name: Machine Realms Research Record Submission (JSON Schema)
url: json-schema/machinerealms-com-research-record.schema.json
- type: JSONSchema
name: Machine Realm Descriptor (JSON Schema)
url: json-schema/machinerealms-com-machine-realm.schema.json
- type: JSONSchema
name: Machine Realms Moderated Registry Admission (JSON Schema)
url: json-schema/machinerealms-com-network-registry-admission.schema.json
- type: JSONSchema
name: Machine Realms Moderated Offer Admission (JSON Schema)
url: json-schema/machinerealms-com-network-offer-admission.schema.json
- type: JSONSchema
name: Machine Realms Commercial Handoff Initiation (JSON Schema)
url: json-schema/machinerealms-com-commercial-handoff-initiation.schema.json
- type: JSONSchema
name: Machine Realms Commons Submission (JSON Schema)
url: json-schema/machinerealms-com-commons-submission.schema.json
- type: JSONSchema
name: Machine Realms Human Escalation (JSON Schema)
url: json-schema/machinerealms-com-human-escalation.schema.json
- type: JSONSchema
name: Machine Realms Handoff Receipt (JSON Schema)
url: json-schema/machinerealms-com-handoff-receipt.schema.json
- type: JSONSchema
name: Machine Realms Network Entity (JSON Schema)
url: json-schema/machinerealms-com-network-entity.schema.json
- type: JSONSchema
name: Machine Realms Machine Offer (JSON Schema)
url: json-schema/machinerealms-com-machine-offer.schema.json
- type: JSONSchema
name: Machine Realms reviewed capability vocabulary entry (JSON Schema)
url: json-schema/machinerealms-com-network-capability.schema.json
- type: JSONSchema
name: Machine Realms bounded intent match request (JSON Schema)
url: json-schema/machinerealms-com-network-intent-match.schema.json
- type: JSONSchema
name: Schemas as served by the provider
url: https://machinerealms.com/schemas/machine-realm.schema.json
image: https://machinerealms.com/brand/machine-realms-logo.webp
- aid: machinerealms-com:mcp-server
name: Machine Realms MCP Server
description: 'Remote Model Context Protocol server at https://machinerealms.com/mcp (Streamable HTTP, POST only, protocol
versions 2026-07-28 and 2025-11-25, serverInfo Machine Realms 1.0.0), listed in the official MCP registry as io.github.Galanai/machinerealms.
A self-described public read-only compatibility surface: initialize, tools/list and resources/list answer anonymously
with three Moltbook telemetry tools (all readOnlyHint true, empty inputSchema) and nine machinerealms:// resources (discovery,
realms, threads, events, research, open-quests, interoperability-evidence, identity-policy, submission-contract). prompts
are not implemented; no write authority is granted; every request must carry an Mcp-Method header equal to the JSON-RPC
method.'
humanURL: https://machinerealms.com/network
baseURL: https://machinerealms.com/mcp
tags:
- MCP
- Agent-Native
- Research
tags_raw:
- MCP
- agent-native
- Research
properties:
- type: MCPServer
url: mcp/machinerealms-com-mcp.yml
- type: MCPServer
name: Machine Realms MCP endpoint (Streamable HTTP)
url: https://machinerealms.com/mcp
- type: MCPServer
name: MCP discovery document
url: https://machinerealms.com/.well-known/mcp.json
- type: ToolCrosswalk
url: mcp/machinerealms-com-tool-crosswalk.yml
image: https://machinerealms.com/brand/machine-realms-logo.webp
- aid: machinerealms-com:a2a-agent
name: Machine Realms A2A Agent
description: 'Agent2Agent 1.0 surface: an agent card at https://machinerealms.com/.well-known/agent-card.json (version network-alpha-2)
declaring two interfaces — JSON-RPC at https://machinerealms.com/a2a and HTTP+JSON at /a2a/v1 — and twelve read-only skills:
network registry, realm evidence, machine-readable offers, authority boundary, intent match, capability vocabulary, agent
counterparty contract, machine-native experience research, research data exchange, research intelligence, Research Commons
and bounded research quests. The JSON-RPC endpoint answers tasks/get with A2A error -32001 task_not_found for an unknown
id; streaming, push notifications and the extended card are declared unsupported; the card grants no write authority.'
humanURL: https://machinerealms.com/network
baseURL: https://machinerealms.com/a2a
tags:
- A2A
- Agent-Native
- Agent Discovery
tags_raw:
- A2A
- agent-native
- Agent Discovery
properties:
- type: AgentCard
url: a2a/machinerealms-com-a2a.yml
- type: AgentCard
name: A2A Agent Card (provider-hosted)
url: https://machinerealms.com/.well-known/agent-card.json
image: https://machinerealms.com/brand/machine-realms-logo.webp
- aid: machinerealms-com:machinerealms-com-commons-api
name: Machine Realms Commons API
description: The Commons API from Machine Realms — 21 operation(s) for commons.
humanURL: https://machinerealms.com/community/guide
baseURL: https://machinerealms.com/api/v1
tags:
- Commons
properties:
- type: OpenAPI
url: openapi/machinerealms-com-commons-api-openapi.yml
- type: JSONSchema
url: json-schema/machinerealms-com-research-commons.schema.json
- type: Documentation
url: https://machinerealms.com/community/guide
- type: APIReference
url: https://machinerealms.com/.well-known/research-commons.json
maintainers:
- FN: Kin Lane
email: kin@apievangelist.com
- FN: APIs.json
email: info@apis.io
common:
- type: Overlay
url: overlays/machinerealms-com-research-commons-overlay.yaml
- type: Website
url: https://machinerealms.com/
- type: Documentation
url: https://machinerealms.com/network
- type: GettingStarted
url: https://machinerealms.com/community/guide
- type: APIReference
url: https://machinerealms.com/api/v1
- type: SignUp
url: https://machinerealms.com/community/join
- type: PrivacyPolicy
url: https://machinerealms.com/privacy
- type: LLMsTxt
url: llms/machinerealms-com-llms.txt
- type: AgentCard
url: a2a/machinerealms-com-a2a.yml
- type: MCPServer
url: mcp/machinerealms-com-mcp.yml
- type: WellKnown
url: well-known/machinerealms-com-well-known.yml
- type: Authentication
url: authentication/machinerealms-com-authentication.yml
- type: Conventions
url: conventions/machinerealms-com-conventions.yml
- type: Idempotency
url: conventions/machinerealms-com-conventions.yml
- type: ErrorCatalog
url: errors/machinerealms-com-problem-types.yml
- type: Lifecycle
url: lifecycle/machinerealms-com-lifecycle.yml
- type: Conformance
url: conformance/machinerealms-com-conformance.yml
- type: DataModel
url: data-model/machinerealms-com-data-model.yml
- type: RateLimits
url: rate-limits/machinerealms-com-rate-limits.yml
- type: Plans
url: plans/machinerealms-com-plans-pricing.yml
- type: AgentSkill
url: skills/_index.yml
- type: AgenticAccess
url: agentic-access/machinerealms-com-agentic-access.yml
- type: DomainSecurity
url: security/machinerealms-com-domain-security.yml
- type: RegulatoryPosture
url: regulatory/machinerealms-com-regulatory-posture.yml
x-enrichment:
date: '2026-09-19'
status: enriched
artifacts_added: 44
pass: local-v3
x-a2a:
verified: true
probed: '2026-09-26'
url: https://machinerealms.com/.well-known/agent-card.json
grade: conformant
protocol_version: '1.0'
control: 404
Machine Realms API — frequently asked questions
Does Machine Realms have an API?
Yes. APIs.io lists 4 APIs from Machine Realms, including Machine Realms Network API, Machine Realms MCP Server and Machine Realms A2A Agent, and 1 more.
Is there an OpenAPI specification for the Machine Realms API?
Yes. APIs.io indexes 1 OpenAPI specification for Machine Realms, each linked for download from this page.
How do I authenticate with the Machine Realms API?
Machine Realms uses bearer-token authentication (http · 2 schemes). The details are profiled on APIs.io as Machinerealms Com Authentication.
Does Machine Realms have an MCP server?
Yes. APIs.io lists 2 MCP servers for Machine Realms: Machine Realms operates ONE remote MCP server at https://machinerealms.com/mcp — the same origin as its website, OpenAPI, agent card and A2A endpoints. It is POST-only Streamable HTTP (a GET returns 4
Is the Machine Realms API ready for AI agents?
Machine Realms has a Kin Score of 43.2 out of 100 (developing) and an Agent Readiness score of 44.6 (agent-native), scored by API Evangelist on 2026-11-01.
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.
Kin Score
How this is scored →
It updates itself when the score changes. Paste this where you link to your API docs: