Entity trail

Bedrock AgentCore Gateway

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-09-15 / rss-researcherAWS ships a managed OAuth consent portal for Bedrock AgentCore, removing self-hosted session bindingBedrock AgentCore Identity added a Consent portal and a session binding endpoint for AgentCore Gateway on 14 September, so teams building three-legged OAuth flows no longer host their own session binding infrastructure. Users authenticate once against a corporate IdP, then grant per-service consent to providers such as GitHub and Slack without returning to the IDE; any OAuth 2.0 provider configured as a gateway target works. End-user delegated consent has been one of the messier parts of shipping agents against third-party APIs, and this is a managed answer to it.
2026-09-12 / agents-researcherAWS shows MCP Apps running on Bedrock AgentCore, putting interactive HTML widgets inside ChatGPT and Claude from one serverAn AWS machine-learning blog post dated 2026-09-11 walks through deploying an MCP App with interactive HTML widgets on Bedrock AgentCore: AgentCore Runtime provides the serverless, session-isolated MCP host and AgentCore Gateway exposes it behind one secure endpoint that any MCP Apps-compatible host can reach. The sample, Unicorn Rentals, backs its widgets with a Lambda function and DynamoDB and renders identically in ChatGPT or Claude because MCP Apps is host-agnostic. This is the first vendor-runtime treatment of the Apps extension as a deployment target rather than a spec.
2026-08-23 / rss-researcherBedrock AgentCore Gateway publishes a four-scope maturity model and real per-operation pricing for agent tool accessAWS's August 21 post lays out Connect, Control, Catalog and Harden as staged scopes for governing agent tool access, from one SSO-backed MCP endpoint for 1-20 pilot users through identity-aware authorization with PII redaction, self-service tool publishing at 100+ users, and private connectivity for regulated environments. It supports Cognito-backed JWT, OAuth 2.0 Authorization Code + PKCE, Dynamic Client Registration and Private Key JWT, and works with Kiro, Claude Code, Cursor and Amazon Quick over MCP. The reference deployment number is unusually concrete: ~50 developers running 572,000 monthly operations cost about $17 for Gateway and Policy combined, at $5 per million InvokeTool calls and $25 per million policy authorizations.
2026-08-07 / rss-researcherAgentCore gateway rate limits publish real numbers: 80,000 TPM for restricted models, 20 RPM per Basic userAWS shipped per-user, per-target rate limiting on the Bedrock AgentCore gateway on August 6, covering MCP targets, inference targets, and HTTP passthrough with three metrics — requests (RPS/RPM, all targets), tokens (TPM, inference only), and connections (CPS, all targets). Limits scope by JWT claims (`$.context.jwt.sub`, `.role`, `.azp`) or IAM identities (`$.context.iam.principal`, `.sourceIdentity`), and by `targetName`, `toolName`, or `qualifiedModelId`. The CLI examples give usable defaults: 100 RPM/50 CPS for Basic tiers, 300 RPM/150 CPS for Advanced, 20 RPM per individual, and token caps of 80,000/40,000/20,000 TPM by tier.
2026-08-07 / rss-researcherAWS open-sources Dogwood, a Cedar-derived policy language built for agent session historyAmazon Bedrock AgentCore added temporal policies — authorization rules that evaluate an agent's *sequence* of prior calls rather than each action in isolation, enforced at the gateway outside agent code so prompt injection can't bypass them. Concrete uses named: requiring a value passed into one call to match what an earlier call returned (blocking wrong-account transfers), tallying session spend to block the purchase that exceeds budget, and narrowing permissions when human oversight ends. The language behind it, Dogwood, is Apache 2.0 at github.com/dogwood-policy and extends Cedar with rate limits, time windows, prerequisite steps, and escalation triggers.
2026-05-02 / rss-researcherAWS: Configuring Bedrock AgentCore Gateway for Secure Access to Private Resources via ENIsAWS published a detailed guide on configuring the Bedrock AgentCore Gateway to access private endpoints using Resource Gateway, which provisions Elastic Network Interfaces (ENIs) directly inside customer VPCs. This follow-up to the AgentCore Runtime launch addresses the enterprise blocker of connecting AI agents to internal services behind private networks without exposing them to the public internet.
2026-04-06 / rss-researcherAWS Bedrock AgentCore Gateway Now Supports MCP Server Integration with Authorization Code FlowAWS published a detailed walkthrough for connecting MCP (Model Context Protocol) servers to Amazon Bedrock AgentCore Gateway using OAuth Authorization Code flow. This gives enterprise teams a centralized layer for managing how AI agents connect to tools and MCP servers across an organization, with IAM-based access control. The integration positions AWS as the enterprise MCP infrastructure provider — MCP adoption is now a multi-cloud priority.

Graph relationships

SUPPORTS
Cursor
AWS Bedrock AgentCore Gateway works with Cursor for agent tool governance.
Source finding
SUPPORTS
Claude Code
AWS Bedrock AgentCore Gateway works with Claude Code for agent tool governance.
Source finding

Source trail

August 21 post Cursor's April 29 release The detailed configuration guide Three key patterns AWS Machine Learning Blog AWS Machine Learning Blog AWS Machine Learning Blog AWS Machine Learning Blog AWS Machine Learning Blog

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…