Skip to main content
Glama
deenesjakoruzh
Awilliv

floci-mcp

by Awilliv
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

floci-mcp

Servidor MCP que permite a un agente de IA desplegar y gestionar recursos con forma de AWS en una instancia local de Floci — «inicia una instancia EC2 con estos parámetros», «crea un bucket S3 y una tabla DynamoDB», etc.

Qué hace

Floci emula 76 servicios de AWS en http://localhost:4566. floci-mcp expone ese endpoint a cualquier cliente compatible con MCP como tres herramientas:

  • aws_call(service, action, params) — llama a cualquier operación de la API de AWS (cualquier servicio, cualquier acción) contra Floci. Esta es la herramienta principal: al ser un paso directo a la API de AWS, cubre los 76 servicios sin necesidad de una herramienta específica por operación.

  • floci_status() — comprueba si Floci es accesible.

  • floci_inventory() — resume lo que está desplegado actualmente en S3, DynamoDB, Lambda, EC2, SQS, SNS, ECS y RDS en una sola llamada.

Related MCP server: AWS MCP Server

Requisitos previos

  • Python 3.10+

  • Una instancia de Floci en ejecución — consulta el README de Floci para floci start o la configuración con Docker.

Instalación

Desde un clon (aún no publicado en PyPI):

git clone https://github.com/Awilliv/floci-mcp.git
cd floci-mcp
pip install -e .

Una vez publicado en PyPI:

pip install floci-mcp

Configuración

Variables de entorno, todas opcionales:

Variable

Default

Propósito

FLOCI_ENDPOINT_URL

http://localhost:4566

Endpoint HTTP de Floci

AWS_DEFAULT_REGION

us-east-1

Región pasada a cada cliente boto3

AWS_ACCESS_KEY_ID

test

Credencial; un valor de 12 dígitos selecciona una cuenta de Floci (aislamiento multi-cuenta)

AWS_SECRET_ACCESS_KEY

test

Credencial (cualquier valor no vacío funciona con Floci)

Ejemplos de uso

Una vez registrado con un cliente MCP, pide al agente cosas como:

«Inicia una instancia EC2 con un tipo de instancia t3.micro usando ami-00000000»

«Crea un bucket S3 llamado reports y una tabla DynamoDB llamada users con una clave de partición id»

El agente realiza estas acciones mediante aws_call — ya conoce las formas de los parámetros de la API de AWS, por lo que no necesita existir una herramienta específica por servicio para que funcione.

Registro con un cliente MCP

Claude Code

Establecer AWS_ACCESS_KEY_ID/AWS_SECRET_ACCESS_KEY explícitamente aquí (en lugar de depender del entorno del shell que lo lanza) evita firmar accidentalmente solicitudes con credenciales reales de AWS si las tienes exportadas en otro lugar.

claude mcp add floci -- floci-mcp

O añade a .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

Añade a 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 (a través de mcpo)

Open WebUI habla OpenAPI/llamada a herramientas, no MCP directamente. Intercala floci-mcp con mcpo para exponerlo como un servidor OpenAPI:

pip install mcpo
mcpo --port 8000 -- floci-mcp

Luego, en Open WebUI, ve a Configuración → Herramientas → Añadir un servidor de herramientas y añade http://localhost:8000. mcpo pasa las variables de entorno al proceso floci-mcp que lanza, así que establece FLOCI_ENDPOINT_URL etc. en el shell desde el que ejecutas mcpo antes de iniciarlo.

Desarrollo

pip install -e ".[test]"
pytest

Las pruebas de integración en tests/test_integration.py requieren una instancia de Floci en ejecución y se omiten automáticamente cuando no se puede acceder a una.

Licencia

MIT

Available Tools

3 tools
aws_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"}.

ParametersJSON Schema
NameRequiredDescriptionDefault
actionYes
paramsNo
serviceYes

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description reveals that parameters are passed exactly as AWS documents them, indicating a passthrough to the AWS API. However, with no annotations provided, it fails to disclose potential side effects (e.g., mutating resources), authentication requirements, or what happens on errors or returns, leaving the agent without a full picture of the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loading the core purpose and then explaining each parameter in a clear, linear structure. While it could be slightly more compact, it is efficient and well-organized, with no unnecessary filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's generic nature (any AWS API call) and the absence of an output schema, the description does not explain what the tool returns after execution, how to interpret errors, or any prerequisites like authentication. These gaps leave the agent under-informed for a potentially complex operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Each parameter is explained in detail: service includes boto3 service name examples (ec2, s3, lambda, rds); action provides both PascalCase and snake_case examples (RunInstances vs run_instances); params is defined as a JSON object exactly as AWS documents, with a bucket example. This substantially adds meaning beyond the schema's bare types and required flags, fully compensating for the 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool calls any AWS API operation against a local Floci instance, specifying the verb 'Call' and the resource 'any AWS API operation' on the target. It distinguishes itself from sibling tools by being generic, though it doesn't explicitly compare, the purpose is unambiguous and specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus the sibling tools (floci_status, floci_inventory). The description does not mention alternatives, exclusions, or prior conditions, leaving the agent to infer that it's for arbitrary AWS calls without knowing when the siblings would be more appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

floci_inventoryA

Summarize resources currently deployed on Floci across common services: S3, DynamoDB, Lambda, EC2, SQS, SNS, ECS, RDS.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden. 'Summarize' inherently signals a safe, non-destructive read operation, which is adequate basic transparency. However, it does not disclose details an agent might need — whether results are scoped to a specific account/region, whether there are pagination or rate limits, or what a 'summary' contains (counts vs. names vs. configurations).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, tightly-wound sentence that leads with the verb, names the resource scope, and enumerates the services. Every clause earns its place and there is zero filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter inventory tool with no output schema and no annotations, the description covers the essential ground: what it does, its scope, and the eight services covered. A minor gap is that it does not describe the return shape of the summary, but since the agent is not required to construct any arguments, nothing is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With zero parameters, there is no schema meaning for the description to supplement, so the baseline of 4 applies. The description adds genuine value by specifying exactly which services are included in the inventory and by clarifying that the output is a summary of currently deployed resources rather than a full configuration dump.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Summarize'), a precise resource ('resources currently deployed on Floci'), and enumerates the covered services (S3, DynamoDB, Lambda, EC2, SQS, SNS, ECS, RDS). This clearly distinguishes it from the sibling aws_call (an execution tool) and floci_status (a status check) — an agent can tell it apart without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The verb 'Summarize' and the term 'inventory' imply this is a read-only overview used when a user wants an at-a-glance resource listing rather than executing operations (aws_call) or checking status (floci_status). However, the description never explicitly states when to prefer this tool over the alternatives, nor does it state exclusions or prerequisites. Usage context is implied, not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

floci_statusA

Check whether the configured Floci instance is reachable.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It states the tool checks reachability but does not disclose what 'reachable' entails (e.g., HTTP status, latency, auth requirements) or the exact return format. For a health-check tool, this is acceptable but minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that is efficient and front-loaded, with no wasted words. It states the action and target clearly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and no output schema, the description is mostly complete. However, it does not specify the nature of the result (e.g., boolean, status message) or any error handling. A slight gap, but acceptable for a simple health check.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has no parameters, and schema coverage is 100% (trivially). Per guidelines, zero parameters warrant a baseline of 4. The description adds no param-specific details because none exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Check') and resource ('configured Floci instance'), clearly distinguishing this status-check tool from siblings like aws_call and floci_inventory. The purpose is unambiguous and actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly indicates its use case (verifying reachability) which naturally separates it from inventory or calls. It does not explicitly name alternatives or exclusions, but the context is clear enough for an agent to select it when connectivity is in question.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv0.1.0
    • First observedaws_call
    • First observedfloci_inventory
    • First observedfloci_status
Deploy Server
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

TDQS

A4.1/5.0

Scored across 3 tools

Disambiguation5/5

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.

Naming Consistency3/5

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.

Tool Count5/5

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.

Completeness5/5

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

ActivitySlowing
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers