Amazon Bedrock MCP setup and connection checker
Provides setup and connection checking for Amazon Bedrock, including authenticated hosted tool discovery, inspection of available Bedrock-related tools, and controlled execution through the PipMCP gateway.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Plan a model-access checklist in the correct AWS account and region
Amazon Bedrock + your AI assistant · powered by PipMCP
You want a model-access checklist in the correct AWS account and region, but first need to establish what Amazon Bedrock can support and what is ready in your account.
Made for: Teams planning an AI feature
This is a setup helper. You will need PipMCP and access to Amazon Bedrock to complete a connection.
Ask your AI to set this up
Paste this into a coding assistant that can open project files and run commands, such as Codex, Claude Code or Grok Build. You do not need to understand the code first.
Help me use this project: https://github.com/jannikco/amazon-aws-bedrock-mcp
I'm not a programmer. My goal is: Plan a model-access checklist in the correct AWS account
and region.
Read the project instructions and set it up in a new folder without overwriting my work.
Guide me through PipMCP and its private key setup; never ask me to paste secrets into this
chat. Start with the documented setup plan and explain what is still needed to connect my
app. Explain the result in plain English. Ask before changing records, sending messages or
publishing anything.Related MCP server: Agent Response MCP
Three useful things to ask for
Help me plan a model-access checklist in the correct AWS account and region with Amazon
Bedrock. Explain the setup steps in plain English.Compare that goal with the linked Amazon Bedrock documentation. Tell me whether an import,
account details or manual setup is still needed.Check which suitable actions are actually available in my PipMCP account. If none are
ready, stop with a missing-step checklist instead of pretending the business task has run.Your path to a real result
flowchart LR
A["Define your goal"] --> B["Check connection needs"] --> C["Complete PipMCP setup"] --> D["Try an available<br/>action"]Open the connection guide and check whether the app is available or needs an API import.
Let your AI explain the required PipMCP account and provider permissions.
Run the documented setup check. A successful check is not proof that provider actions ran.
What to expect: You get a setup plan and connection checks. This project does not bundle a ready-made Amazon Bedrock action set. Importing an API or completing manual PipMCP settings may still be needed before any business task can run.
Add your PipMCP key privately in your project settings. Keep keys out of chat and public repositories.
Keep going
Amazon Bedrock MCP setup and connection checker
Prepare Amazon Bedrock for AI workflows with a PipMCP setup doctor, agent instructions and authenticated connector discovery.
Activate with PipMCP · Integration directory
Build something useful
Prepare Amazon Bedrock and inspect your hosted setup
This repository is a setup utility. Availability depends on your actual hosted integration and connection.
Quick start
Requires Node.js 22+. Clone this repository, then:
npm ci --ignore-scripts
npm test
npm start
# After configuring your provider in PipMCP and setting PIPMCP_API_KEY:
npm start -- --live
# Launch the stdio MCP bridge:
npm run serverCreate a PipMCP API key with explicit connectors:read and connectors:call scopes. Set PIPMCP_API_KEY in the calling process environment. Provider credentials are configured in PipMCP. Multiple accounts require explicit PIPMCP_INTEGRATION_ID and PIPMCP_CONNECTION_ID from discovery. Existing keys do not gain scopes automatically.
Built for coding agents
Install this repository's skill into your project:
node lib/cli.mjs agents install --client codex --scope project --project /path/to/project
# Use claude or grok for those clients.Connect AI agents to Amazon Bedrock using one PipMCP API key and actual hosted tool discovery. Native AGENTS.md, CLAUDE.md and project skills support the current coding session. No additional AI model key is required. capabilities.json describes the package; llms.txt indexes its instructions.
Inspect actual tools before calling
import {PipMCPGatewayClient} from './lib/index.mjs';
const client = new PipMCPGatewayClient(); // PIPMCP_API_KEY
const inventory = await client.getTools("amazon-aws-bedrock");
console.log(inventory.data.tools);
// Select a real tool and validate your arguments against its returned schema.
// client.callTool(provider, actualToolName, reviewedArguments, {idempotencyKey});PipMCP enforces workspace, role, connection, policy/approval and usage controls. Preserve the original idempotency key when retrieving/resuming a receipt. Pending and confirmation_required are not completed provider results; uncertain writes are held for reconciliation. The bridge never auto-approves a hosted action.
Version 1 migration
This release uses the authenticated PipMCP gateway for real discovery/execution. Upgrade your MCP launch command and configure PIPMCP_API_KEY before reconnecting. Historical local runtimes remain available under their original MIT license in Git history.
Evidence and support
Transport, package and agent fixtures are tested. Authentication/provider access must be checked in your own configured workspace; synthetic fixtures do not establish live provider execution. Do not include credentials or customer records in public issues. MIT covers this public client.
Use a manually imported API
If the provider is not already available in your workspace, import your reviewed API definition, publish the selected tools and configure its connection in PipMCP. Set PIPMCP_CONNECTOR_ID=custom-api together with PIPMCP_INTEGRATION_ID and, when needed, PIPMCP_CONNECTION_ID. Then run npm run doctor or npm run server. These select your published private API; they do not change the fixed PipMCP origin or bypass hosted authorization. Leaving PIPMCP_CONNECTOR_ID unset uses amazon-aws-bedrock. Importing requires integrations:read and integrations:write on the same PipMCP key; discovery and calls use connectors:read and connectors:call.
Provider setup reference
Official provider documentation. Credentials are entered in PipMCP; this package does not accept or store provider secrets.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.
Zero-setup MCP gateway securely connecting AI to your tools with authentication and workflows
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
One gateway, every app: Gmail, GitHub, Notion and more. Connect once, call any tool. Managed auth.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to install coding-agent instructions, run setup diagnostics, and discover and call hosted tools through an authenticated PipMCP gateway with policy and approval controls.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to discover and call hosted tools through an authenticated PipMCP gateway, with setup diagnostics and provider-connection checks.MIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to validate a hosted setup, discover available tools, and invoke them through an authenticated gateway with policy and approval controls.44 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to validate a hosted recruitment-platform connection, discover authenticated tools through a gateway, and invoke them under policy and approval controls.MIT