{"id":"0pens0-tanzu-mcp-server","name":"tanzu-mcp-server","af_score":56.5,"security_score":57.2,"reliability_score":36.2,"what_it_does":"Provides a Model Context Protocol (MCP) server that exposes Cloud Foundry operations as 38/associated tools (apps, orgs/spaces, services, routes, network policies, cloning, and target/validation). Intended to be deployed on Cloud Foundry and accessed by an MCP client via the streamable HTTP transport.","best_when":"When you want an AI agent to call constrained, named Cloud Foundry operations (including operational validation) from an MCP client, and you can manage CF credentials/roles safely.","avoid_when":"When you cannot restrict who/what can access the MCP server or cannot enforce network/authZ controls for destructive actions (delete/unbind/deleteOrphanedRoutes, etc.).","last_evaluated":"2026-04-04T19:50:23.041158+00:00","has_mcp":true,"has_api":false,"auth_methods":["Cloud Foundry UAA integration (password grant described via UAA token handling/PasswordGrantTokenProvider)"],"has_free_tier":false,"known_gotchas":["Destructive tools exist (delete apps, delete spaces/service instances/routes, unbind/bind, cleanup orphaned routes). An agent should implement an allowlist/guardrails and confirmations.","No explicit rate-limit documentation is provided; agents may need their own pacing/backoff.","Idempotency and retry safety are not documented per tool; retries could cause repeated side effects for non-idempotent operations."],"error_quality":null}