AgentGateway

AgentGateway is an open-source, AI-native proxy and gateway for routing, observing, and governing traffic to and from AI agents, LLM providers, and MCP servers. Built on the A2A and MCP protocols, it provides a unified gateway for LLM consumption, MCP tool federation, agent-to-agent communication, security, and observability. AgentGateway supports multi-provider LLM routing across OpenAI, Anthropic, Google Gemini, AWS Bedrock, and Azure OpenAI with built-in RBAC, JWT authentication, rate limiting, and OpenTelemetry integration.

AgentGateway publishes 7 API contracts indexed on the APIs.io network, including Config API, Debug API, Lifecycle API, and 4 more. Tagged areas include AI Gateway, API Gateway, MCP, LLM, and A2A.

The AgentGateway catalog on APIs.io includes 1 JSON-LD context and 1 Spectral governance ruleset.

AgentGateway’s developer surface includes API reference, code examples, CLI, authentication, changelog, sandbox, developer portal, and 43 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

52.9/100 developing ▬ flat Agent 28/100 agent aware Front door AI 6/6 dominant Heartbeat 84/100 alive self hosted · Apache-2.0 Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

AccessOpen

1 published contract 3 Agent Skills 10 Features 6 Use Cases

AI Gateway API Gateway MCP LLM A2A Open Source CNCF Observability Security

Kin Score

Kin Score How this is scored →
scored 2026-11-06 · rubric v0.27.0

Composite quality — 52.9/100 · developing

Contract Quality 8.4 / 16

Developer Ergonomics 9.5 / 13

Access Clarity 2.7 / 13

Operational Transparency 3.8 / 8

Contract Governance 3.3 / 8

Discoverability 4.2 / 7

Regulatory Posture 4.2 / 15

Open Source Surface 7.5 / 10

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 28/100 · agent aware

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 8 / 8

Request/Response Examples 7 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 6 / 6

Agent Skills 5 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Pagination 5 / 5

Distinct Operations 3 / 3

MCP Tool Quality 6 / 6

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.

Open Source Surface applies to this provider. This product is open source and we read its repository directly, so Open Source Surface carries 10 points of the composite. It is scored from what the repository actually publishes — a security policy, a contribution guide, a release history, a code of conduct — read live from the provider rather than inferred from our own catalog pointers. This facet adds; nothing was taken away to make room for it. An open-source project is not excused from the commercial facets, because exemption would strip it of the points it does earn. If we have the wrong repository, or this product is not open source, say so on your provider repo and we will drop the facet rather than have you publish against 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 65 points between them, because both conditional facets apply and carry 35 points together. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 65% 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/agentgateway/"><img src="https://apis.io/badge/agentgateway/card.svg" alt="AgentGateway 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):

MCP Server +12 pts — deployment.mode + probe verdict on the mcp/ manifest, not the pointer; an unprobed slug falls back to authorship
Idempotency +9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card +8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0
Registration Without a Human +6 pts — a `registration_endpoint` in the served RFC 8414 / OIDC discovery document
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)
Documented Reversibility +6 pts — a reversal operation in the contract, graded up when a window is documented too

5 more unmet checks in the Agent Readiness table above.

Kin Score — facets with the most composite points still available (weight × headroom):

Access Clarity scores 21.1 — up to +15.8 composite points
Contract Quality scores 51.7 — up to +12.1 composite points
Operational Transparency scores 44.7 — up to +7.2 composite points

Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from the provider profile at artifacts.apis.io/agentgateway/apis.yml: open an issue on github.com/api-evangelist/agentgateway to ask a question or point us at an artifact you publish. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Markets this provider is in provisional

The Kin Score Market layer reads a provider inside its market: its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted: not part of the Kin Score or agent readiness.

Market	Position	Depth	Registered MCP server	Declares compatibility
API Management (gateways, portals, service mesh, proxies)	standard	61.8	-	1
OpenSSF Best Practices Badge Holders	standard	61.8	-	1

Registered MCP server and declares compatibility are report only — not weighted. Undeclared means we found nothing we can read, so there is no number: we never infer integrations.

Standards implemented 3

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.

Agent2Agent

tagged — the provider's own APIs.json carries the standard as a tag; implementation not verified

Model Context Protocol (MCP)

tagged — the provider's own APIs.json carries the standard as a tag; implementation not verified

OpenAPI

measured — observed by APIs.io (published)

APIs 7

Individual APIs this provider publishes, each with its own machine-readable definition.

AgentGateway

AgentGateway provides AI-native gateway capabilities for routing LLM traffic, federating MCP tools, enabling agent-to-agent communication, and applying security and observabilit...

AgentGateway Config API

The Config API from AgentGateway — 1 operation(s) for config.

AgentGateway Debug API

The Debug API from AgentGateway — 2 operation(s) for debug.

AgentGateway Lifecycle API

The Lifecycle API from AgentGateway — 1 operation(s) for lifecycle.

AgentGateway Logging API

The Logging API from AgentGateway — 1 operation(s) for logging.

AgentGateway Memory API

The Memory API from AgentGateway — 1 operation(s) for memory.

AgentGateway Profiling API

The Profiling API from AgentGateway — 2 operation(s) for profiling.

Scroll for all 7

Open Collections 7

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

AgentGateway Admin / Debug Config API

OPEN COLLECTION

AgentGateway Admin / Config Debug API

OPEN COLLECTION

AgentGateway Admin / Debug Config Lifecycle API

OPEN COLLECTION

AgentGateway Admin / Debug Config Logging API

OPEN COLLECTION

AgentGateway Admin / Debug Config Memory API

OPEN COLLECTION

AgentGateway Admin / Debug Config Profiling API

OPEN COLLECTION

AgentGateway Admin / Debug API

OPEN COLLECTION

Scroll for all 7

Agent Skills 3

Packaged agent skills for driving this provider's APIs from an AI assistant.

agentgateway-change-log-level

AGENT SKILL

agentgateway-inspect-running-config

AGENT SKILL

agentgateway-trace-and-profile

AGENT SKILL

AgentGateway API pricing

Pricing Plans 1

Published pricing tiers and plan structures.

Agentgateway Plans Pricing

0 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Agentgateway Rate Limits

0 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Agentgateway Finops

FINOPS

Features 10

Notable capabilities this provider offers.

LLM Gateway

Routes traffic to OpenAI, Anthropic, Google Gemini, AWS Bedrock, and Azure OpenAI through a unified API with model aliasing, failover, and load balancing.

MCP Gateway

Connects LLMs to tools via Model Context Protocol with static and dynamic routing, tool federation, and stateful MCP sessions.

Agent-to-Agent (A2A) Gateway

Enables secure, governed communication between AI agents using the A2A protocol for multi-agent orchestration.

Inference Routing

Intelligently routes requests to self-hosted models based on GPU utilization and request priority.

Security and Authentication

Provides JWT, OAuth2, API key management, CORS, CSRF protection, MCP authentication, and external authorization support.

Traffic Management

Supports request routing and matching, header manipulation, rate limiting, retries, gRPC routing, traffic splitting, and direct responses.

Observability

Integrates with OpenTelemetry for metrics, traces, and access logging with a built-in Admin UI and debugging tools.

Guardrails

Applies prompt guards, content filtering, regex filters, moderation policies, and custom webhooks for AI safety.

Cost Controls

Tracks budget and spend limits per user, team, or application with RBAC-based controls on LLM consumption.

Prompt Enrichment

Supports prompt templates and enrichment for standardizing and augmenting requests before routing to LLM providers.

Scroll for all 10

Semantic Vocabularies 1

JSON-LD contexts and semantic vocabularies used across these APIs.

Agentgateway Context

5 classes · 21 properties

JSON-LD

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

AgentGateway — jsonschema rules

5 rules · 3 warnings 2 info

SPECTRAL

OpenAPI Overlays 6

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.

Agentgateway Config Api Overlay

3 actions · documentation · agentgateway-config-api-openapi.yml

GENERATED

Agentgateway Debug Api Overlay

4 actions · documentation · agentgateway-debug-api-openapi.yml

GENERATED

Agentgateway Lifecycle Api Overlay

3 actions · documentation · agentgateway-lifecycle-api-openapi.yml

GENERATED

Agentgateway Logging Api Overlay

4 actions · documentation · agentgateway-logging-api-openapi.yml

GENERATED

Agentgateway Memory Api Overlay

3 actions · documentation · agentgateway-memory-api-openapi.yml

GENERATED

Agentgateway Profiling Api Overlay

4 actions · documentation · agentgateway-profiling-api-openapi.yml

GENERATED

JSON Schema 4

Standalone JSON Schema definitions for this provider's data models.

LocalConfig

14 properties

JSON SCHEMA

LLMBackend

8 properties

JSON SCHEMA

MCPTarget

6 properties

JSON SCHEMA

Route

5 properties

JSON SCHEMA

JSON Structure 3

JSON Structure definitions describing this provider's data shapes.

Agentgateway Llm Backend Structure

8 properties

JSON STRUCTURE

Agentgateway Mcp Target Structure

6 properties

JSON STRUCTURE

Agentgateway Route Structure

5 properties

JSON STRUCTURE

Examples 3

Example request and response payloads for these APIs.

Agentgateway Llm Backend Example

8 fields

EXAMPLE

Agentgateway Mcp Target Example

6 fields

EXAMPLE

Agentgateway Route Example

5 fields

EXAMPLE

Security Posture 3

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Agentgateway Authentication

0 schemes

SECURITY

Agentgateway Domain Security

TLSv1.3

SECURITY

Agentgateway Vulnerability Disclosure

Hackerone

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Agentgateway Agentic Access

9 operations · 2 acting · 1 human-in-the-loop

9 operations · 2 acting

AGENTIC

Use Cases 6

What developers build with this provider.

Unified LLM Routing

Route requests across multiple LLM providers with a single API, enabling failover, load balancing, and cost optimization without changing client code.

MCP Tool Federation

Aggregate tools from multiple MCP servers behind a single gateway endpoint, enabling agents to discover and invoke tools from any connected MCP server.

Enterprise AI Governance

Apply organization-wide security policies, rate limits, budget controls, and content filters to all AI agent traffic through a centralized gateway.

REST API to MCP Conversion

Convert existing REST APIs into MCP-native tool endpoints that AI agents can discover and invoke through the Model Context Protocol.

Multi-Agent Orchestration

Enable secure agent-to-agent communication using the A2A protocol, allowing specialized agents to delegate tasks to each other through the gateway.

Observability and Debugging

Collect unified telemetry across all AI agent and LLM interactions to monitor cost, latency, and behavior at scale.

Integrations 9

Pre-built integrations with other platforms and tools.

OpenAI

Route to OpenAI GPT models through the AgentGateway LLM backend with model aliasing and budget controls.

Anthropic

Connect to Anthropic Claude models via the unified LLM gateway with failover and load balancing.

Google Gemini

Route traffic to Google Gemini models through the AgentGateway multi-provider backend.

AWS Bedrock

Integrate with AWS Bedrock for managed LLM access via the AgentGateway routing layer.

Azure OpenAI

Route requests to Azure-hosted OpenAI models through the unified gateway API.

Ollama

Connect to locally hosted Ollama models for self-hosted inference routing.

vLLM

Route to vLLM inference servers with GPU utilization-aware routing for optimal performance.

OpenTelemetry

Export metrics, traces, and logs to any OpenTelemetry-compatible observability backend.

Kubernetes Gateway API

Deploy and configure AgentGateway on Kubernetes using the standard Gateway API for dynamic configuration.

Scroll for all 9

Resources

Get Started 3

Portal, sign-up, and the first successful call

Sandbox

Sandbox

Portal

Portal

GettingStarted

GettingStarted

Documentation 7

Reference material describing how the API behaves

APIReference

APIReference

Configuration Schema (LocalConfig) - first-party, JSON Schema draft 2020-12, 302 definitions

JSONSchema

Configuration Schema (LocalConfig) - verbatim capture of https://agentgateway.dev/schema/config

JSONSchema

LLM Backend Schema

JSONSchema

MCP Target Schema

JSONSchema

Route Schema

JSONSchema

Documentation

Documentation

Scroll for all 7

Agent Surfaces 6

MCP servers, agent skills, and machine-readable catalogs

AgentSkill

AgentSkill

LLMsTxt

LLMsTxt

WellKnown-probe

WellKnown-probe

X-MCPServerCandidate

X-MCPServerCandidate

AgenticAccess

AgenticAccess

LlmsText

LlmsText

Design & Contract 10

Pagination, idempotency, versioning, errors, and events

JSONStructure

SpectralRules

Conventions

Conformance

ErrorCatalog

Lifecycle

DataModel

Webhooks

JSONLD

Vocabulary

Scroll for all 10

Build 5

SDKs, sample code, and the tooling you integrate with

Examples

Packages

CLI

CodeOfConduct

GitHubOrganization

GitHubOrganization

Access & Security 5

Authentication, authorization, and security posture

Authentication

Authentication

Security

Security

VulnerabilityDisclosure

VulnerabilityDisclosure

SecurityPolicy

SecurityPolicy

DomainSecurity

DomainSecurity

Operate 6

Status, limits, changes, and where to get help

RateLimits

Deprecation

ChangeLog

IssueTracker

Releases

Support

Commercial 5

Pricing, plans, and the legal terms of use

TermsOfService

PrivacyPolicy

Plans

FinOps

License

Company 2

The organization behind the API

Website

Website

Blog

Blog

Other 1

Properties that don't map to a standard resource type

Charter

Charter

Source (apis.yml)

aid: agentgateway
name: AgentGateway
description: AgentGateway is an open-source, AI-native proxy and gateway for routing, observing, and governing traffic to
  and from AI agents, LLM providers, and MCP servers. Built on the A2A and MCP protocols, it provides a unified gateway for
  LLM consumption, MCP tool federation, agent-to-agent communication, security, and observability. AgentGateway supports multi-provider
  LLM routing across OpenAI, Anthropic, Google Gemini, AWS Bedrock, and Azure OpenAI with built-in RBAC, JWT authentication,
  rate limiting, and OpenTelemetry integration.
url: https://raw.githubusercontent.com/api-evangelist/agentgateway/refs/heads/main/apis.yml
humanURL: https://agentgateway.dev/
type: Index
deliveryModel:
  model: self-hosted
  license: Apache-2.0
  open_source: true
  commercial: false
  callable_host: false
  label: Self-hosted open source · you run it yourself
  confidence: high
  source:
  - license
  - openapi
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: open
  trial: false
  try_now: false
  public: false
  gated: none
  gated_source:
  - onboarding
  label: Open access
  confidence: medium
  try_now_blocked_by: loopback
  source:
  - authentication
  - rate-limits
  - security
  - sandbox
  generated: '2026-11-06'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/agentgateway.png
tags:
- AI Gateway
- API Gateway
- MCP
- LLM
- A2A
- Open Source
- CNCF
- Observability
- Security
tags_raw:
- AI Gateway
- API Gateway
- MCP
- LLM
- Agent-to-Agent
- Open Source
- CNCF
- Observability
- Security
- Open-Source
created: '2026-03-27'
modified: '2026-08-30'
specificationVersion: '0.23'
apis:
- aid: agentgateway:agentgateway
  name: AgentGateway
  x-base-url-note: 'agentgateway is self-hosted: there is no callable hosted API host. The five admin/debug API entries below
    carry baseURL http://127.0.0.1:15000, which is the documented default admin bind address and matches their OpenAPI servers[]
    blocks. They previously carried https://agentgateway.dev, which serves documentation only - probed 2026-08-30, https://agentgateway.dev/config_dump
    returns 404. This entry keeps the project site as its base because the data plane''s port is whatever the operator configures
    (the docs'' examples use 3000).'
  description: AgentGateway provides AI-native gateway capabilities for routing LLM traffic, federating MCP tools, enabling
    agent-to-agent communication, and applying security and observability controls across AI agent infrastructure.
  humanURL: https://agentgateway.dev/
  tags:
  - AI Gateway
  - LLM Routing
  - MCP
  - A2A
  - Security
  - Observability
  tags_raw:
  - AI Gateway
  - LLM Routing
  - MCP
  - Agent-to-Agent
  - Security
  - Observability
  properties:
  - type: Documentation
    url: https://agentgateway.dev/docs/
  - type: GettingStarted
    url: https://agentgateway.dev/docs/quickstart/
  - type: GitHubRepository
    url: https://github.com/agentgateway/agentgateway
  - type: APIReference
    url: https://agentgateway.dev/docs/standalone/latest/reference/
  - type: JSONSchema
    url: https://agentgateway.dev/schema/config
- aid: agentgateway:agentgateway-config-api
  name: AgentGateway Config API
  description: The Config API from AgentGateway — 1 operation(s) for config.
  humanURL: https://agentgateway.dev/
  baseURL: http://127.0.0.1:15000
  tags:
  - Config
  properties:
  - type: OpenAPI
    url: openapi/agentgateway-config-api-openapi.yml
  - type: Overlay
    url: overlays/agentgateway-config-api-overlay.yaml
- aid: agentgateway:agentgateway-debug-api
  name: AgentGateway Debug API
  description: The Debug API from AgentGateway — 2 operation(s) for debug.
  humanURL: https://agentgateway.dev/
  baseURL: http://127.0.0.1:15000
  tags:
  - Debug
  properties:
  - type: OpenAPI
    url: openapi/agentgateway-debug-api-openapi.yml
  - type: Overlay
    url: overlays/agentgateway-debug-api-overlay.yaml
- aid: agentgateway:agentgateway-lifecycle-api
  name: AgentGateway Lifecycle API
  description: The Lifecycle API from AgentGateway — 1 operation(s) for lifecycle.
  humanURL: https://agentgateway.dev/
  baseURL: http://127.0.0.1:15000
  tags:
  - Lifecycle
  properties:
  - type: OpenAPI
    url: openapi/agentgateway-lifecycle-api-openapi.yml
  - type: Overlay
    url: overlays/agentgateway-lifecycle-api-overlay.yaml
- aid: agentgateway:agentgateway-logging-api
  name: AgentGateway Logging API
  description: The Logging API from AgentGateway — 1 operation(s) for logging.
  humanURL: https://agentgateway.dev/
  baseURL: http://127.0.0.1:15000
  tags:
  - Logging
  properties:
  - type: OpenAPI
    url: openapi/agentgateway-logging-api-openapi.yml
  - type: Overlay
    url: overlays/agentgateway-logging-api-overlay.yaml
- aid: agentgateway:agentgateway-memory-api
  name: AgentGateway Memory API
  description: The Memory API from AgentGateway — 1 operation(s) for memory.
  humanURL: https://agentgateway.dev/
  baseURL: http://127.0.0.1:15000
  tags:
  - Memory
  properties:
  - type: OpenAPI
    url: openapi/agentgateway-memory-api-openapi.yml
  - type: Overlay
    url: overlays/agentgateway-memory-api-overlay.yaml
- aid: agentgateway:agentgateway-profiling-api
  name: AgentGateway Profiling API
  description: The Profiling API from AgentGateway — 2 operation(s) for profiling.
  humanURL: https://agentgateway.dev/
  baseURL: http://127.0.0.1:15000
  tags:
  - Profiling
  properties:
  - type: OpenAPI
    url: openapi/agentgateway-profiling-api-openapi.yml
  - type: Overlay
    url: overlays/agentgateway-profiling-api-overlay.yaml
common:
- type: Website
  url: https://agentgateway.dev/
- type: APIReference
  url: https://agentgateway.dev/docs/standalone/latest/reference/
- type: TermsOfService
  url: https://lfprojects.org/policies/terms-of-use/
- type: PrivacyPolicy
  url: https://www.linuxfoundation.org/legal/privacy-policy
- type: Charter
  url: https://github.com/agentgateway/agentgateway/blob/main/CHARTER.md
- type: JSONSchema
  url: https://agentgateway.dev/schema/config
  title: Configuration Schema (LocalConfig) - first-party, JSON Schema draft 2020-12, 302 definitions
- type: JSONSchema
  url: json-schema/agentgateway-config-schema.json
  title: Configuration Schema (LocalConfig) - verbatim capture of https://agentgateway.dev/schema/config
- type: JSONStructure
  url: json-structure/agentgateway-route-structure.json
- type: Examples
  url: https://github.com/agentgateway/agentgateway/tree/main/examples
- type: SpectralRules
  url: rules/agentgateway-jsonschema-spectral-rules.yml
- type: Plans
  url: plans/agentgateway-plans-pricing.yml
- type: RateLimits
  url: rate-limits/agentgateway-rate-limits.yml
- type: FinOps
  url: finops/agentgateway-finops.yml
- type: Packages
  url: packages/agentgateway-packages.yml
- type: CLI
  url: cli/agentgateway-cli.yml
- type: Authentication
  url: authentication/agentgateway-authentication.yml
- type: Conventions
  url: conventions/agentgateway-conventions.yml
- type: Conformance
  url: conformance/agentgateway-conformance.yml
- type: ErrorCatalog
  url: errors/agentgateway-problem-types.yml
- type: Lifecycle
  url: lifecycle/agentgateway-lifecycle.yml
- type: Deprecation
  url: https://agentgateway.dev/docs/standalone/latest/reference/release-notes/
- type: ChangeLog
  url: changelog/agentgateway-changelog.yml
- type: DataModel
  url: data-model/agentgateway-data-model.yml
- type: Sandbox
  url: sandbox/agentgateway-sandbox.yml
- type: Webhooks
  url: webhooks/agentgateway-webhooks.yml
- type: Security
  url: https://github.com/agentgateway/agentgateway/blob/main/SECURITY.md
- type: VulnerabilityDisclosure
  url: security/agentgateway-vulnerability-disclosure.yml
- type: AgentSkill
  url: skills/_index.yml
- type: LLMsTxt
  url: llms/agentgateway-llms.txt
- type: WellKnown-probe
  url: well-known/agentgateway-well-known.yml
  note: Probe record only - every /.well-known path 404s. Deliberately NOT type WellKnown, which would assert a served document.
- type: X-MCPServerCandidate
  url: mcp/agentgateway-mcp.yml
  note: Derived candidate only - agentgateway ships no MCP server of its own. Deliberately NOT type MCPServer.
- type: IssueTracker
  url: https://github.com/agentgateway/agentgateway/issues
- type: Releases
  url: https://github.com/agentgateway/agentgateway/releases
- type: SecurityPolicy
  url: https://github.com/agentgateway/agentgateway/blob/main/SECURITY.md
- type: CodeOfConduct
  url: https://github.com/agentgateway/agentgateway/blob/main/CODE_OF_CONDUCT.md
- type: License
  name: Apache-2.0
  url: https://github.com/agentgateway/agentgateway/blob/main/LICENSE
- type: AgenticAccess
  url: agentic-access/agentgateway-agentic-access.yml
- type: DomainSecurity
  url: security/agentgateway-domain-security.yml
- type: GitHubOrganization
  url: https://github.com/agentgateway
- type: JSONSchema
  url: https://raw.githubusercontent.com/api-evangelist/agentgateway/refs/heads/main/json-schema/agentgateway-llm-backend-schema.json
  title: LLM Backend Schema
- type: JSONSchema
  url: https://raw.githubusercontent.com/api-evangelist/agentgateway/refs/heads/main/json-schema/agentgateway-mcp-target-schema.json
  title: MCP Target Schema
- type: JSONSchema
  url: https://raw.githubusercontent.com/api-evangelist/agentgateway/refs/heads/main/json-schema/agentgateway-route-schema.json
  title: Route Schema
- type: JSONLD
  url: https://raw.githubusercontent.com/api-evangelist/agentgateway/refs/heads/main/json-ld/agentgateway-context.jsonld
- type: Vocabulary
  url: https://raw.githubusercontent.com/api-evangelist/agentgateway/refs/heads/main/vocabulary/agentgateway-vocabulary.yaml
- type: Portal
  url: https://agentgateway.dev/
- type: Documentation
  url: https://agentgateway.dev/docs/
- type: GettingStarted
  url: https://agentgateway.dev/docs/quickstart/
- type: Support
  url: https://discord.gg/y9efgEmppm
- type: Features
  data:
  - name: LLM Gateway
    description: Routes traffic to OpenAI, Anthropic, Google Gemini, AWS Bedrock, and Azure OpenAI through a unified API with
      model aliasing, failover, and load balancing.
  - name: MCP Gateway
    description: Connects LLMs to tools via Model Context Protocol with static and dynamic routing, tool federation, and stateful
      MCP sessions.
  - name: Agent-to-Agent (A2A) Gateway
    description: Enables secure, governed communication between AI agents using the A2A protocol for multi-agent orchestration.
  - name: Inference Routing
    description: Intelligently routes requests to self-hosted models based on GPU utilization and request priority.
  - name: Security and Authentication
    description: Provides JWT, OAuth2, API key management, CORS, CSRF protection, MCP authentication, and external authorization
      support.
  - name: Traffic Management
    description: Supports request routing and matching, header manipulation, rate limiting, retries, gRPC routing, traffic
      splitting, and direct responses.
  - name: Observability
    description: Integrates with OpenTelemetry for metrics, traces, and access logging with a built-in Admin UI and debugging
      tools.
  - name: Guardrails
    description: Applies prompt guards, content filtering, regex filters, moderation policies, and custom webhooks for AI
      safety.
  - name: Cost Controls
    description: Tracks budget and spend limits per user, team, or application with RBAC-based controls on LLM consumption.
  - name: Prompt Enrichment
    description: Supports prompt templates and enrichment for standardizing and augmenting requests before routing to LLM
      providers.
- type: UseCases
  data:
  - name: Unified LLM Routing
    description: Route requests across multiple LLM providers with a single API, enabling failover, load balancing, and cost
      optimization without changing client code.
  - name: MCP Tool Federation
    description: Aggregate tools from multiple MCP servers behind a single gateway endpoint, enabling agents to discover and
      invoke tools from any connected MCP server.
  - name: Enterprise AI Governance
    description: Apply organization-wide security policies, rate limits, budget controls, and content filters to all AI agent
      traffic through a centralized gateway.
  - name: REST API to MCP Conversion
    description: Convert existing REST APIs into MCP-native tool endpoints that AI agents can discover and invoke through
      the Model Context Protocol.
  - name: Multi-Agent Orchestration
    description: Enable secure agent-to-agent communication using the A2A protocol, allowing specialized agents to delegate
      tasks to each other through the gateway.
  - name: Observability and Debugging
    description: Collect unified telemetry across all AI agent and LLM interactions to monitor cost, latency, and behavior
      at scale.
- type: Integrations
  data:
  - name: OpenAI
    description: Route to OpenAI GPT models through the AgentGateway LLM backend with model aliasing and budget controls.
  - name: Anthropic
    description: Connect to Anthropic Claude models via the unified LLM gateway with failover and load balancing.
  - name: Google Gemini
    description: Route traffic to Google Gemini models through the AgentGateway multi-provider backend.
  - name: AWS Bedrock
    description: Integrate with AWS Bedrock for managed LLM access via the AgentGateway routing layer.
  - name: Azure OpenAI
    description: Route requests to Azure-hosted OpenAI models through the unified gateway API.
  - name: Ollama
    description: Connect to locally hosted Ollama models for self-hosted inference routing.
  - name: vLLM
    description: Route to vLLM inference servers with GPU utilization-aware routing for optimal performance.
  - name: OpenTelemetry
    description: Export metrics, traces, and logs to any OpenTelemetry-compatible observability backend.
  - name: Kubernetes Gateway API
    description: Deploy and configure AgentGateway on Kubernetes using the standard Gateway API for dynamic configuration.
- type: LlmsText
  url: https://agentgateway.dev/llms.txt
- url: https://agentgateway.dev/blog/index.xml
  type: Blog
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
x-enrichment:
  date: '2026-08-30'
  status: enriched
  artifacts_added: 25
  pass: local-v1

AgentGateway API — frequently asked questions

Does AgentGateway have an API?

Yes. APIs.io lists 7 APIs from AgentGateway, including AgentGateway, AgentGateway Config API and AgentGateway Debug API, and 4 more.

Is there an OpenAPI specification for the AgentGateway API?

Yes. APIs.io indexes 6 OpenAPI specifications for AgentGateway, each linked for download from this page.

How do I authenticate with the AgentGateway API?

AgentGateway uses bearer-token authentication (0 schemes). The details are profiled on APIs.io as Agentgateway Authentication.

Is the AgentGateway API ready for AI agents?

AgentGateway has a Kin Score of 52.9 out of 100 (developing) and an Agent Readiness score of 28.1 (agent-aware), scored by API Evangelist on 2026-11-06.

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/agentgateway"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/agentgateway/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/agentgateway/evidence"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

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.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.