Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ihatesea69/kiro-kit --skill agentcore-gateway-mcpgit clone --depth 1 https://github.com/ihatesea69/kiro-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ihatesea69/kiro-kit/agentcore-gateway-mcp)<a href="https://agentmods.dev/skills/ihatesea69/kiro-kit/agentcore-gateway-mcp"><img src="https://agentmods.dev/badge/skills/ihatesea69/kiro-kit/agentcore-gateway-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ihatesea69/kiro-kit/agentcore-gateway-mcp"><img src="https://agentmods.dev/badge/skills/ihatesea69/kiro-kit/agentcore-gateway-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.01247 |
| Opus 5.5 | $0.00023 | $0.00499 |
| Sonnet 5.5 | $0.00012 | $0.00249 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
agentcore-gateway-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentCore Gateway (MCP)
Activate this skill when an agent needs tools and you do not want to hand-roll an MCP server per integration.
When to Use
- Exposing existing Lambda functions or REST APIs to an agent as MCP tools
- Fronting an MCP server you already run
- Choosing inbound (agent → Gateway) or outbound (Gateway → target) auth
- Scaling past a few dozen tools without blowing up the context window
What It Does
Gateway converts APIs, Lambda functions, and existing services into MCP-compatible tools, and connects to pre-existing MCP servers, exposing all of them to agents through Gateway endpoints. The result is one tool surface unifying MCP servers, knowledge bases, internal APIs, and Lambda functions.
Pricing: $0.005 per 1,000 API invocations, plus $0.02 per 100 tools indexed per month.
Target Types
| Target | Source of truth | Good for |
|---|---|---|
| Lambda | Function ARN + a tool schema you supply | Bespoke logic, private data access |
| OpenAPI | An OpenAPI 3 document | Existing REST services |
| Smithy | A Smithy model | AWS-service-shaped APIs |
| MCP server | A remote MCP endpoint | Servers you or a vendor already run |
Lambda target sketch:
import boto3
agentcore = boto3.client("bedrock-agentcore-control")
agentcore.create_gateway_target(
gatewayIdentifier=gateway_id,
name="order-lookup",
targetConfiguration={"mcp": {"lambda": {
"lambdaArn": "arn:aws:lambda:us-east-1:123456789012:function:order-lookup",
"toolSchema": {"inlinePayload": [{
"name": "lookup_order",
"description": (
"Return status, items, and delivery estimate for a customer order. "
"Do not use for refunds or cancellations — see process_refund."
),
"inputSchema": {"type": "object",
"properties": {"order_id": {"type": "string"}},
"required": ["order_id"]},
}]},
}}},
credentialProviderConfigurations=[{"credentialProviderType": "GATEWAY_IAM_ROLE"}],
)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 136 lines · 58 tokens per session scan A 62f16f7d3156
agentcore-gateway-mcp is a skill published in the GitHub repository ihatesea69/kiro-kit (19 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 1,247 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
agentcore-gateway-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentcore-gateway-mcpihatesea69/kiro-kit | Skill | 19 | 2mo ago | MIT | A | 58 | Claude Code, Codex |
| voidenVoidenHQ/voiden | Skill | 1.8k | 2d ago | Apache-2.0 | A | 28 | Claude Code, Codex |
| csharp-dotnetericrisco/rsc-harness | Skill | 598 | yesterday | MIT | A | 89 | Claude Code, Codex |
| scaffold-projectMarve10s/Better-Fullstack | Skill | 823 | yesterday | MIT | A | 80 | Claude Code |
| migrate-oracle-formsmendixlabs/mxcli | Skill | 139 | yesterday | Apache-2.0 | A | 47 | Claude Code |
| business-eventsmendixlabs/mxcli | Skill | 139 | yesterday | Apache-2.0 | A | 50 | Claude Code |
| oly-appsslaveOftime/open-relay | Skill | 110 | yesterday | MIT | A | 32 | Claude Code, Codex |