Skip to main content
Glama
deenesjakoruzh
lethain

Systems MCP

by lethain
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

sistemas-mcp

systems-mcp es un servidor MCP para interactuar con la biblioteca lethain:systems para el modelado de sistemas.

Proporciona dos herramientas:

  • run_systems_model ejecuta la especificación systems de un modelo de sistemas. Toma dos parámetros: la especificación y, opcionalmente, el número de rondas para ejecutar el modelo (el valor predeterminado es 100).

  • load_systems_documentation carga la documentación y los ejemplos en la ventana de contexto. Esto es útil para preparar los modelos y que sean más útiles al escribir modelos de sistemas.

Está diseñado para ejecutarse localmente junto con Claude Desktop o una herramienta similar.

Uso

A continuación se muestra un ejemplo del uso de systems-mcp para ejecutar y renderizar un modelo.

Ejemplo de solicitud para usar sistemas-mcp

Aquí está el artefacto generado a partir de ese mensaje, incluido el resultado de la ejecución del modelo de sistemas.

Ejemplo de artefacto para utilizar la salida de sistemas-mcp

Finalmente, aquí se presenta un ejemplo del uso de la herramienta load_systems_documentation para preparar la ventana de contexto y usarla para generar una especificación de sistemas. Esto equivale aproximadamente a incluir lethain:systems/README.md en la ventana de contexto, pero también incluye varios ejemplos adicionales (consulte los archivos incluidos en ./docs/ ).

Ejemplo de solicitud de carga de documentación en la ventana de contexto

Luego puedes renderizar el modelo como antes.

Ejemplo de solicitud de representación del modelo generado

Lo más interesante aquí es que nunca he utilizado personalmente systems para modelar una red social, pero el LLM pudo hacer un trabajo notablemente decente al generar una especificación a pesar de eso.

Related MCP server: MCP Server Demo

Instalación

Estas instrucciones describen la instalación de Claude Desktop en OS X. Debería funcionar de manera similar en otras plataformas.

  1. Instalar Claude Desktop .

  2. Clone sistemas-mcp en una ubicación conveniente. Supongo que /Users/will/systems-mcp

  3. Asegúrate de tener instalado uv , puedes seguir estas instrucciones

  4. Vaya a Cladue Desktop, Configuración, Desarrollador y cree su archivo de configuración MCP. Luego, actualice su archivo claude_desktop_config.json . (Tenga en cuenta que debe reemplazar will con su usuario, por ejemplo, la salida de whoami ).

     cd /Users/will/Library/Application Support/Claude
 vi claude_desktop_config.json

    Luego agrega esta sección:

     {
   "mcpServers": {
     "systems": {
       "command": "uv",
       "args": [
         "--directory",
         "/Users/will/systems-mcp",
         "run",
         "main.py"
       ]
     }
   }
 }

  5. Cierra Claude y vuelve a abrirlo.

  6. Debería funcionar...

Available Tools

2 tools
load_systems_documentationB

Load systems documentation, examples, and specification details to improve the models ability to generate specifications.

Returns: Documentation and several examples of systems models

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

B3.2/5.0
Behavior3/5

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

No annotations are provided, so the description carries full burden. It discloses that the tool returns 'documentation and several examples of systems models' which describes output behavior. However, it doesn't mention important behavioral traits like whether this is a read-only operation, if it requires authentication, rate limits, or what happens if documentation isn't available. The description adds some behavioral context but leaves significant gaps.

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 appropriately concise with two sentences that each serve a purpose: the first states what the tool does and its purpose, the second describes the return value. It's front-loaded with the main action. There's minimal waste, though the second sentence could be integrated more smoothly.

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 0 parameters, 100% schema coverage, and an output schema exists, the description is reasonably complete. It explains what the tool does and what it returns. The existence of an output schema means the description doesn't need to detail return values extensively. For a simple parameterless documentation loading tool, this provides adequate context.

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 0 parameters with 100% schema description coverage, so the baseline is 4. The description appropriately doesn't waste space discussing non-existent parameters. No additional parameter information is needed or provided, which is correct for a parameterless tool.

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

Purpose3/5

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

The description states the tool 'loads systems documentation, examples, and specification details' which is a clear purpose, but it's somewhat vague about what exactly is being loaded. It distinguishes from the sibling tool 'run_systems_model' by focusing on loading documentation rather than executing models, but the distinction could be more explicit. The description doesn't specify verb+resource with precision.

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?

The description mentions the tool helps 'improve the models ability to generate specifications' which implies usage context, but provides no explicit guidance on when to use this tool versus alternatives. There's no mention of prerequisites, timing, or comparison with the sibling tool 'run_systems_model'. The usage context is implied rather than clearly stated.

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

run_systems_modelC

Run a systems model and return output of list of dictionaries in JSON.

Args: spec: The systems model specification rounds: Number of rounds to run (default: 100)

ParametersJSON Schema
NameRequiredDescriptionDefault
specYes
roundsNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool runs a model and returns JSON output, but doesn't describe what 'running a systems model' entails (e.g., computational requirements, execution time, side effects, error conditions, or authentication needs). For a tool that presumably performs computation, this is a significant gap in behavioral context.

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 appropriately concise with two sentences that directly address purpose and parameters. The structure is front-loaded with the core functionality first, followed by parameter details. No wasted words, though it could be slightly more polished in formatting.

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 that there's an output schema (which handles return value documentation) but no annotations and incomplete parameter semantics, the description is minimally adequate. It covers the basic purpose and parameters but lacks important behavioral context for a computational tool. The presence of an output schema reduces the need to describe return values, but other gaps remain.

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

Parameters3/5

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

The description adds some semantic context beyond the schema: it explains that 'spec' is 'The systems model specification' and 'rounds' is 'Number of rounds to run (default: 100)'. However, with 0% schema description coverage, the description doesn't fully compensate - it doesn't explain what format the 'spec' should be in (e.g., JSON, YAML, specific syntax) or what 'rounds' means in the context of systems modeling.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'Run a systems model and return output of list of dictionaries in JSON.' This specifies the verb ('Run'), resource ('a systems model'), and output format. However, it doesn't explicitly differentiate from the sibling tool 'load_systems_documentation', which appears to be a documentation loading function rather than a model execution tool.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling tool 'load_systems_documentation' or any other context for selection. The only usage hint is the default value for 'rounds', but this doesn't help with tool selection decisions.

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. 2 tool updatesv1.0.0
    • Changedload_systems_documentation1 field changed
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "title": "Result",
+      "type": "string"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "title": "load_systems_documentationOutput",
+  "type": "object"
+}
    • Changedrun_systems_model1 field changed
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "properties": {
+    "result": {
+      "title": "Result",
+      "type": "string"
+    }
+  },
+  "required": [
+    "result"
+  ],
+  "title": "run_systems_modelOutput",
+  "type": "object"
+}
  2. 2 tool updates
    • First observedload_systems_documentation
    • First observedrun_systems_model
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

B3.1/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have completely distinct purposes: one loads documentation/examples for reference, while the other executes a model with given specifications. There is no overlap in functionality, and an agent would easily differentiate between them based on their clear descriptions.

Naming Consistency5/5

Both tools follow a consistent verb_noun pattern with snake_case naming: load_systems_documentation and run_systems_model. The naming is predictable and readable, with no deviations in style or convention across the set.

Tool Count2/5

With only 2 tools, the server feels thin for the domain of 'systems modeling,' which typically involves more operations like creating, updating, or analyzing models. This limited set may hinder agents from performing comprehensive tasks, as it lacks tools for specification generation, validation, or result analysis beyond basic execution.

Completeness2/5

The tool set is severely incomplete for systems modeling. It provides documentation loading and model execution but misses essential operations such as creating or editing specifications, validating models, analyzing outputs in-depth, or managing model versions. This creates significant gaps that will likely cause agent failures in real-world scenarios.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • MCP LLMS-TXT Documentation

    langchain-ai
    A
    license
    Not graded
    quality
    F
    maintenance
    An MCP server that provides tools to load and fetch documentation from any llms.txt source, giving users full control over context retrieval for LLMs in IDE agents and applications.
    1,033
    MIT

  • MCP Server Demo

    Drakoxw
    F
    license
    B
    quality
    D
    maintenance
    A Model Context Protocol server implementation that can be run directly or through Docker, enabling AI assistants to interact with external systems through the MCP standard.
    2
    -

  • mcp-toy

    xiangshiyin
    A
    license
    B
    quality
    D
    maintenance
    A toy MCP server for exploring Model Context Protocol capabilities, including resources, tools, and prompts.
    1
    Apache 2.0