floci-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@floci-mcp Spin up an EC2 instance (t3.micro) using ami-00000000"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
floci-mcp
MCP server that lets an AI agent deploy and manage AWS-shaped resources on a local Floci instance — "spin up an EC2 instance with these parameters," "create an S3 bucket and a DynamoDB table," and so on.
What it does
Floci emulates 76 AWS services on http://localhost:4566. floci-mcp
exposes that endpoint to any MCP-compatible client as three tools:
aws_call(service, action, params)— call any AWS API operation (any service, any action) against Floci. This is the core tool: since it's a thin pass-through to the AWS API, it covers all 76 services without a hand-built tool per operation.floci_status()— check whether Floci is reachable.floci_inventory()— summarize what's currently deployed across S3, DynamoDB, Lambda, EC2, SQS, SNS, ECS, and RDS in one call.
Related MCP server: AWS MCP Server
Prerequisites
Python 3.10+
A running Floci instance — see the Floci README for
floci startor Docker setup.
Install
From a clone (not yet published to PyPI):
git clone https://github.com/Awilliv/floci-mcp.git
cd floci-mcp
pip install -e .Once published to PyPI:
pip install floci-mcpConfiguration
Environment variables, all optional:
Variable | Default | Purpose |
|
| Floci's HTTP endpoint |
|
| Region passed to every boto3 client |
|
| Credential; a 12-digit value selects a Floci account (multi-account isolation) |
|
| Credential (any non-empty value works against Floci) |
Usage examples
Once registered with an MCP client, ask the agent things like:
"Spin up an EC2 instance with a t3.micro instance type using ami-00000000"
"Create an S3 bucket called
reportsand a DynamoDB table calleduserswith a partition keyid"
The agent drives these through aws_call — it already knows AWS API
parameter shapes, so no per-service tool needs to exist for it to work.
Registering with an MCP client
Claude Code
Setting AWS_ACCESS_KEY_ID/AWS_SECRET_ACCESS_KEY explicitly here (rather than relying on the launching shell's environment) avoids accidentally signing requests with real AWS credentials if you happen to have them exported elsewhere.
claude mcp add floci -- floci-mcpOr add to .mcp.json:
{
"mcpServers": {
"floci": {
"command": "floci-mcp",
"env": {
"FLOCI_ENDPOINT_URL": "http://localhost:4566",
"AWS_ACCESS_KEY_ID": "test",
"AWS_SECRET_ACCESS_KEY": "test"
}
}
}
}Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"floci": {
"command": "floci-mcp",
"env": {
"FLOCI_ENDPOINT_URL": "http://localhost:4566",
"AWS_ACCESS_KEY_ID": "test",
"AWS_SECRET_ACCESS_KEY": "test"
}
}
}
}Open WebUI (via mcpo)
Open WebUI speaks OpenAPI/tool-calling, not MCP directly. Front
floci-mcp with mcpo to expose it
as an OpenAPI server:
pip install mcpo
mcpo --port 8000 -- floci-mcpThen in Open WebUI, go to Settings → Tools → Add a Tool Server and add
http://localhost:8000. mcpo passes environment variables through to the
floci-mcp process it launches, so set FLOCI_ENDPOINT_URL etc. in the
shell you run mcpo from before starting it.
Development
pip install -e ".[test]"
pytestIntegration tests in tests/test_integration.py require a running Floci
instance and skip themselves automatically when one isn't reachable.
License
MIT
Available Tools
3 toolsaws_callA
Call any AWS API operation against the local Floci instance. service: boto3 service name (e.g. 'ec2', 's3', 'lambda', 'rds'). action: the AWS API operation name, e.g. 'RunInstances' or 'run_instances'. params: a JSON object of API parameters exactly as AWS documents them, e.g. {"Bucket": "my-bucket"}.
Inputs: action (required), service (required), params.
floci_inventoryA
Summarize resources currently deployed on Floci across common services: S3, DynamoDB, Lambda, EC2, SQS, SNS, ECS, RDS.
Inputs: no named parameters.
floci_statusA
Check whether the configured Floci instance is reachable.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools have clearly distinct purposes: aws_call for arbitrary AWS operations, floci_status for connectivity checks, and floci_inventory for resource summaries. There is no overlap or ambiguity between them.
Two tools follow a `floci_` snake_case prefix pattern, but `aws_call` uses camelCase and doesn't follow the same convention. The mixed naming style is noticeable but still readable.
With only 3 tools, the set is tightly scoped and every tool earns its place. The number is appropriate for a server that provides a generic AWS API pass-through plus convenience utilities.
The `aws_call` tool covers the full AWS API surface, so any operation can be performed. `floci_status` and `floci_inventory` fill specific monitoring and overview gaps, providing a complete workflow without dead ends.
Maintenance
Related MCP Connectors
Your AI Agent's Infrastructure Layer. Connect Claude, Copilot, Codex, or ChatGPT to 200+ managed open source services. Start databases, pipelines, and applications through natural language.
Unified API to query AWS, GCP, Azure and generate Terraform/CLI execution kits for AI agents.
Deploy and run apps in your own AWS, Google Cloud, Azure or DigitalOcean account from any AI agent.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI agents to deploy applications to AWS with DevOps capabilities by automatically inferring infrastructure needs from code and generating inspectable Infrastructure as Code specifications.1515Apache 2.0
- AlicenseBqualityDmaintenanceEnables management and provisioning of AWS resources like EC2, S3, and RDS using natural language prompts through the Model Context Protocol. It allows users to automate complex infrastructure tasks, such as setting up VPCs and security groups, via a chat interface.5427MIT
- FlicenseNot gradedqualityDmaintenanceEnables interaction with AWS services (EC2, S3, Lambda, DynamoDB, etc.) through the Model Context Protocol, allowing natural language management of cloud resources.2-
- AlicenseNot gradedqualityDmaintenanceProvides conversational access to LocalStack AWS services (S3, DynamoDB, Lambda, SQS) through natural language, enabling local cloud infrastructure management without real AWS costs.MIT