localcore-gateway
A local reimplementation of the AWS Bedrock AgentCore Gateway with a pluggable Lambda backend for developing and testing agent-integrations offline.
README
localcore-gateway
A local, faithful-enough reimplementation of AWS Bedrock AgentCore Gateway, with a pluggable local Lambda backend. Develop and test agent ↔ gateway ↔ Lambda integrations entirely on your machine, then point the same MCP client at the real AWS gateway with no code changes.
There is no official local emulator for AgentCore Gateway (AWS's agentcore dev
is for the Runtime, not the Gateway). This fills that gap.
0.x — unstable. The CLI flags and config schema may change between minor releases until 1.0. Pin a version if you depend on it.
What it reproduces
- MCP Streamable-HTTP at
/mcp— the same wire surface as the real gateway (built on the FastMCP 3.x server; no hand-rolled JSON-RPC). - Target aggregation — every
(target, tool)is exposed as one MCP tool namedtarget___tool(AgentCore's triple-underscore convention). - AgentCore Lambda contract — the tool arguments are passed as the Lambda
event; the tool identity is delivered via
context.client_context.custom['bedrockAgentCoreToolName']; the Lambda's return value becomes the tool result. - OpenAPI targets — a REST API's spec becomes MCP tools; the tool name is
the operation's
operationIdverbatim (as the real gateway does, not a slugified form), spec-level security is ignored (auth configured out of band).
Local Lambda backends
| backend | Docker | fidelity | use it for |
|---|---|---|---|
native |
no | one subprocess per target (real process isolation — monorepo-safe), faithful event/context, error envelope, CloudWatch-style logs, hot reload, hard timeout |
the fast dev loop |
sam |
yes | the real AWS Lambda Linux runtime via sam local start-lambda |
full Linux-runtime fidelity check before AWS |
Documentation
- Architecture — request flow, AgentCore contract mapping, component map
- Configuration reference — every config field
- Writing Lambda handlers — the handler contract, multi-tool, errors, logs, native vs sam
- CLI reference —
serve/dev/tools/invoke - Connecting agents — point an MCP client at it; promote to real AWS
Install
uv tool install localcore-gateway # or: pipx install localcore-gateway
uvx --from localcore-gateway lcgw --help # one-off, no install
Quick start
A handler and a config (nothing else needed):
# handlers.py
def handler(event, context):
return {"sum": event["a"] + event["b"]}
# gateway.yaml
targets:
- type: lambda
name: demo
lambda: { backend: native, handler: handlers.handler }
tools:
- name: add
inputSchema:
type: object
properties: { a: { type: number }, b: { type: number } }
required: [a, b]
lcgw tools -c gateway.yaml
lcgw invoke -c gateway.yaml demo___add --data '{"a":2,"b":40}'
lcgw serve -c gateway.yaml # MCP at http://127.0.0.1:8080/mcp
lcgw dev -c gateway.yaml # same, with hot reload
Point any MCP client at http://127.0.0.1:8080/mcp. Richer examples (multi
target, math_handlers.py, Strands agent) are in examples/.
From source (development)
git clone https://github.com/tawAsh1/localcore-gateway && cd localcore-gateway
uv sync
uv run pytest
uv run lcgw serve -c examples/config.yaml
Using the sam backend
Run sam local start-lambda in your SAM project, then set in the target:
lambda:
backend: sam
sam_endpoint: http://127.0.0.1:3001
sam_function: DemoFunction
Configuration
See examples/config.yaml. A target declares a Lambda
(backend, handler/sam_function, memory_mb, timeout_sec, env) and the
tools it backs (each with an explicit JSON Schema). One Lambda can back many
tools; the handler branches on bedrockAgentCoreToolName.
Known limitations
nativeruns your handler in a subprocess but is not a security sandbox (no filesystem/network jail) — only point it at trusted code.nativeserializes invokes per target (one warm execution environment); it does not model Lambda's concurrent-environment scaling.samper-invoke logs appear in thesam localconsole (out-of-band for the Invoke API).- AgentCore's builtin semantic tool search (
x_amz_bedrock_agentcore_search) is not implemented (intentionally omitted). - Target types: Lambda and OpenAPI are implemented; MCP-passthrough and Smithy are not yet. OpenAPI outbound auth covers static API key (header/query) and bearer; OAuth 2LO is out of scope.
License
Apache License 2.0. See NOTICE for attribution and the
trademark disclaimer below.
Trademarks & disclaimer
This is an unofficial, community project. It is not affiliated with, endorsed by, or sponsored by Amazon Web Services, Inc. or its affiliates.
"AWS", "Amazon Web Services", "Amazon Bedrock", "Amazon Bedrock AgentCore", and "AWS Lambda" are trademarks of Amazon.com, Inc. or its affiliates. They are used here only nominatively, to accurately describe the AWS service this project interoperates with / reimplements locally. No AWS trademark, logo, or trade dress is used as the name or branding of this project.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。