Skip to main content
Glama
Sign In
deeszh
byaml-mcp

byaml-mcp

by breakingthecloud
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

byaml-mcp v2 (ByaML-004)

MCP server de BYaML Architecture Graph para agentes (Kiro, Cursor, Claude, Copilot).

El agente NO escribe YAML — usa el grafo. Input: evaluación/scan/terraform plan. Output: Architecture Graph v0.4 + insights (blast radius, costo) + remediación.

Tools (8)

Tool

Descripción

graph_from_evaluation

eval_id/findings → Graph v0.4

graph_from_terraform

tfplan.json → Graph v0.4

graph_from_account

profile AWS → Graph v0.4 (scan)

validate_graph

valida grafo (byaml.validate)

blast_radius

downstream impact de un nodo (nan-graph)

cost_summary

costo por layer/servicio/owner (nan-graph)

remediation_plan

findings → pasos IaC (snippet terraform)

schema_latest

fetch version/catalog del registry schema.byaml.org (ByaML-003)

Related MCP server: Synlake MCP Server

Run

uv run server.py          # stdio
uvx byaml-mcp             # publicado (PyPI)

Config MCP (Kiro / Claude / Cursor)

{ "mcpServers": { "byaml": { "command": "uvx", "args": ["byaml-mcp"] } } }

Depende de

  • byaml (PyPI 0.4.0a1) — modelo v0.4 + convert (from_evaluation/from_terraform) + validate

  • nan-graph (PyPI) — blast_radius, cost_chain, team_cost, SPOF

  • mcp (FastMCP) — transporte stdio

Available Tools

8 tools
blast_radiusA

Downstream impact de un nodo: qué se cae si falla (nan-graph blast_radius).

Args: node_id: id del nodo origen (ej. 'api'). graph: graph JSON v0.4 (output de graph_from_*). max_depth: profundidad máxima (None = infinito). rel_types: filtrar a estos relType (ej. ['invokes']).

Inputs: graph (required), node_id (required), max_depth, rel_types.

cost_summaryC

Resumen de costo del grafo.

Args: graph: graph JSON v0.4. by: agrupar por 'layer' | 'type' | 'owner'.

Inputs: graph (required), by.

graph_from_accountA

Convierte un perfil AWS (scan) en un Architecture Graph v0.4.

NOTA: por ahora con sample: true devuelve un grafo de ejemplo (pour no requerir credenciales AWS en el agente). Con sample: false espera un scan previo (SOFE).

Inputs: profile (required), sample.

graph_from_evaluationA

Construye un Architecture Graph v0.4 desde una evaluación SOFE (findings).

Args: findings: lista de findings (con resource_id/resource_type/severity/policy). cost_map: opcional, {resource_id: monthly_cost}. eval_id: id de la evaluación. account: cuenta/entorno (ej. 'aws-acc-123').

Inputs: findings (required), account, eval_id, cost_map.

graph_from_terraformB

Convierte un terraform show -json plan en un Architecture Graph v0.4.

Args: plan_path: ruta al tfplan JSON (terraform show -json plan.tfplan > plan.json). account: opcional, cuenta/entorno.

Inputs: plan_path (required), account.

remediation_planB

Genera un plan de remediación (pasos IaC con snippet terraform) para findings.

Args: findings: lista JSON de findings (ej. [{"resource":"i-0abc","type":"no-idle-ec2"}]). graph: opcional, graph v0.4 para contexto.

Inputs: findings (required), graph.

schema_latestB

Versión vigente del schema + resumen del catálogo (fetch schema.byaml.org).

Devuelve latest + count de tipos del catalog v0.4.

Inputs: no named parameters.

validate_graphC

Valida un Architecture Graph v0.4 y devuelve errors/warnings (byaml.validate).

Inputs: graph (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.6/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool targets a distinct concern: schema retrieval, graph construction from three different input sources, graph validation, downstream impact analysis, cost aggregation, and remediation planning. No two tools overlap in purpose, making selection unambiguous.

    Naming Consistency4/5

    Names follow snake_case and mostly verb_noun (validate_graph, cost_summary, remediation_plan), with graph_from_* indicating source. Minor deviations like schema_latest and blast_radius are still clear and consistent in style, so no confusion arises.

    Tool Count5/5

    With 8 tools, the surface is well-scoped for an architecture analysis server. Each tool contributes to a clear workflow (create graph, validate, analyze, remediate), and the count is within the ideal range for coherence.

    Completeness4/5

    The set covers graph generation from multiple sources, validation, blast radius, cost, and remediation. Minor gaps exist (e.g., no graph diff or editing), but the core lifecycle for analysis is complete and no dead ends are apparent.

    Resources

    Related MCP Connectors

    Related MCP Servers

    • Synlake MCP Server

      Synlake MCP Serverofficial

      Synlake-ai
      A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to discover, evaluate, and provision cloud infrastructure across AWS, GCP, and Azure with cross-cloud normalization, cost comparisons, and deployable execution kits.
      5
      12 npm
      MIT

    • archiet-xray

      Anioko
      A
      license
      A
      quality
      C
      maintenance
      Extracts deterministic architecture maps from codebases for AI agents, enabling queries about blast radius, routes, security findings, and production readiness without sending code anywhere.
      6
      MIT