convez.ai
MCP ServerDados & AnalyticsIntermediário
MatthewDavisAIArchitect

OntoRamp Knowledge Cartographer

MatthewDavisAIArchitect/ontoramp-knowledge-cartographer

Grafo de conhecimento governado com saúde e cobertura mapeadas

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que transforma documentos dispersos da organização em um grafo de conhecimento governado e acessível a qualquer agente de IA. Fornece pontuações de saúde do conhecimento, mapas de cobertura por domínio e análise de lacunas. Tier gratuito com leitura ilimitada.

Instalação

$npx convez-ai MatthewDavisAIArchitect/ontoramp-knowledge-cartographer

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 3 meses
Versão
—
Issues abertas
0
Contribuidores
2

Casos de uso

  • Mapear cobertura de conhecimento organizacional por domínio
  • Detectar lacunas de conhecimento antes de treinar agentes de IA
  • Ingerir e governar documentos corporativos em estrutura de grafo
  • Avaliar prontidão de agentes para lidar com base de conhecimento existente

Veredito

Ferramenta bem-arquitetada para organizações que enfrentam fragmentação de conhecimento. O modelo de tier com leitura gratuita é sábio — reduz atrito para descoberta. Lacuna real: documentação de casos de uso além de cobertura e saúde; exemplos de integrações com agentes reais ajudariam.

README

A tradução para o português deste README ainda está na fila.

OntoRamp Knowledge Cartographer — MCP Server

Turns your organization's scattered documents and decisions into a searchable, governed knowledge graph — one MCP call at a time.

Problem: Organizational knowledge is trapped in documents. AI agents can retrieve from these stores but cannot understand the structure, authority, or governance implications of what they find.

Solution: Ingest your organization's documents into a governed knowledge graph accessible to any AI agent. Returns knowledge health scores, coverage maps, and domain-specific gap analysis.

MCP Registry License Status


Tools

ToolDescriptionTier
get_coverage_mapDomain-by-domain knowledge coverage map for your organizationFree
get_knowledge_health_scoreHealth score for your organization's current knowledge stateFree
detect_knowledge_gapsIdentify where coverage is thin or missing, by domainDeveloper+
ingest_documentIngest a document into your governed knowledge graphDeveloper+ (auth)
request_assessmentSubmit an Agentic Readiness Assessment requestAll tiers, rate-limit exempt

Tiers

TierPriceLimitsFeatures
Free— (no credit card)Unlimited readsget_coverage_map + get_knowledge_health_score (read-only, no ingest)
Developer$0.015 read / $0.05 ingestUnlimitedingest_document (auth) + detect_knowledge_gaps + all reads · Staging queue
Org$249/mo flatUnlimited reads, 500 ingest/moFull provenance chains · ARA pre-population from coverage map

Install

A hosted, remote MCP server (Streamable HTTP) — nothing to install locally. See llms-install.md for an agent-followable walkthrough.

1. Get a free API key at ontoramp.com/mcp (no credit card).

2. Add to Cline — edit ~/.cline/mcp.json (or the Cline UI → MCP Servers → Configure):

{
  "mcpServers": {
    "ontoramp-knowledge-cartographer": {
      "url": "https://ontoramp-knowledge-cartographer.fly.dev/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Other MCP clients (Claude Desktop, etc.) use the same mcpServers shape. Transport is Streamable HTTP.

3. Verify — curl https://ontoramp-knowledge-cartographer.fly.dev/health → {"status":"ok",...}.

See examples/usage.md for example calls.

Why the free read tools matter

get_coverage_map and get_knowledge_health_score show organizations their current knowledge state — almost always worse than they expect. That creates a clear, evidence-grounded path to both ingestion (improve coverage) and an ARA (interpret what the gaps mean).

ARA Trigger

When get_knowledge_health_score returns below 50, or coverage gap exceeds 40%, the server prompts:

Your knowledge coverage has gaps that a manual review won't surface. An Agentic Readiness Assessment will diagnose your current state and build a prioritized remediation plan. Schedule at ontoramp.com/assessment.

Security

  • All responses are audited for public release — no scoring-formula internals, no substrate architecture details
  • Write-path (ingest_document) requires Developer or Org tier authentication
  • Your data is scoped to your tenant namespace and never shared across organizations
  • GET /health returns live status

Support


Governed by OntoRamp Governance Physics. OntoRamp LLC · ontoramp.com

Ver o original no GitHub

Bom para

Relacionados