{"id":"bigcoder84-mcp-excel-server","name":"mcp-excel-server","af_score":43.8,"security_score":13.0,"reliability_score":18.8,"what_it_does":"Provides an MCP server (via Spring AI MCP framework) that allows an LLM to read from and write to local Excel files (.xlsx/.xls). It runs as a stdio-based MCP server (Java command) and exchanges Excel content using the MCP protocol, returning JSON for read operations and writing JSON-provided data back into Excel.","best_when":"You run an MCP-capable client (e.g., Claude/Cursor-like tooling) in an environment where the MCP server can access local files you intend to expose to the model, and you can manage process isolation and file permissions externally.","avoid_when":"You cannot control what files the agent can access, you cannot enforce least-privilege filesystem permissions, or you require strong operational guarantees (SLA, documented error codes, retry/idempotency semantics) before production use.","last_evaluated":"2026-04-04T19:37:15.407240+00:00","has_mcp":true,"has_api":false,"auth_methods":[],"has_free_tier":false,"known_gotchas":["Local file access: ensure the process has least-privilege permissions; an agent may attempt to read/write unintended paths if not constrained by client configuration.","Excel write operations may be non-idempotent depending on how the tool applies updates; without explicit semantics, repeated runs could overwrite data.","No documented rate-limits, timeouts, or output schemas beyond a high-level description—agent behavior may be sensitive to tool response formats."],"error_quality":0.0}