Fibery MCP

為什麼要用

核心特性

Auto-discovers your custom Fibery types via the schema API
Read/write entities with rich-text descriptions
Cross-database links (Feature → Customer Insight, etc.)
Fibery formula execution for derived fields
Workspace-scoped token

即時演示

實際使用效果

fibery-mcp.replay ▶ 就緒

0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

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

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit

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

點擊 Cline 側欄中的 MCP Servers 圖示，然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

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

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "fibery-mcp",
      "command": "uvx",
      "args": [
        "fibery-mcp-server"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "fibery-mcp": {
      "command": {
        "path": "uvx",
        "args": [
          "fibery-mcp-server"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add fibery-mcp -- uvx fibery-mcp-server

一行命令搞定。用 claude mcp list 驗證，claude mcp remove 移除。

使用場景

實戰用法： Fibery MCP

Convert customer insights into prioritized feature requests

👤 Product managers using Fibery ⏱ ~15 min intermediate

何時使用： You have a stack of Insight entities and need to roll them up into Features.

前置條件

Server/skill installed and authenticated — See repo README

步驟

Pull recent insights

Find Insight entities created this month grouped by theme.✓ 已複製

→ Themed clusters of insights
Create features

For the top 3 themes, create a Feature entity linked to all contributing Insights with a 'why now' summary.✓ 已複製

→ Three new Features with backlinks

結果： Backlog grounded in real user feedback with traceability.

注意事項

Fibery types are workspace-specific — Fibery types are workspace-specific — always start with describe_schema before assuming a field name.

搭配使用： filesystem

組合

與其他 MCP 搭配，撬動十倍槓桿

fibery-mcp + filesystem

Pair with filesystem for complementary capabilities

Use this server together with filesystem to complete a multi-step task.✓ 已複製

工具

此 MCP 暴露的能力

工具	輸入參數	何時呼叫	成本
describe_schema	(none)	First — to discover types and fields	1 API call
query_entities	type, filter, limit	Find entities matching criteria	1 API call
update_entity	id, fields	Change a field value	1 API call

成本與限制

運行它的成本

API 配額: See provider docs for rate limits
每次呼叫 Token 數: Varies by tool
費用: See repo README for pricing details
提示: Cache tool results and avoid repeated identical calls.

安全

權限、密鑰、影響範圍

憑證儲存： Use environment variables; never commit secrets

資料出站： Tool calls go to the provider's API as documented

故障排查

常見錯誤與修復

401 Unauthorized

Generate an API token at Fibery workspace settings → API keys. Set FIBERY_HOST and FIBERY_TOKEN.

驗證： describe_schema returns types

field not found

Field names in Fibery's API use the type-qualified form (e.g. Workflow/State). Use describe_schema to find the exact name.

驗證： Inspect the type's fields

替代方案

Fibery MCP 對比其他方案

替代方案	何時用它替代	權衡
Linear MCP	Eng-only	Fixed schema; less flexible