frappe-mcp-server
MCP Servermascor/frappe-mcp-server
A secure Model Context Protocol server for the Frappe framework featuring granular allowlists, audit logging, and field-level permissions.
Overview
This integration bridges AI clients and Frappe ERP systems via the Model Context Protocol (MCP). It features robust security safeguards including explicit DocType allowlists, field-level restrictions, dedicated token authentication, and full request audit logging to let AI agents safely query and manipulate business data.
Capabilities
- ▸Search documents with custom filters and fields
- ▸Create new documents via MCP tools
- ▸Update and delete existing ERP records
- ▸Retrieve document metadata and schemas
- ▸Audit log tracking with latency and payload summaries
- ▸Strict allowlist validation for DocTypes and operations
Best for
Querying and searching business records like ToDos, Notes, and Events from an AI assistant, Automating creation and updates of ERP records through natural language commands, Inspecting system schemas and document metadata safely using AI agents
Works with
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Access is denied by default; administrators must explicitly enable DocTypes and actions via the MCP Doctype Allowlist. All requests are tracked in an audit log.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.