bridgecore

Say what should happen; get the right app tool per step, an n8n workflow, or the call itself.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
100%
命名品質
80%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目(1)

  • LOWTool 'do' name length outside 3-30 range在 do 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~1,492Token(工具定義)
~2.7 KB典型回應大小
中等的注意力影響(128k 上下文的 1.17%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "bridgecore": {
      "url": "https://bridgecore-mcp.chinlee2200.workers.dev/"
    }
  }
}

遠端端點

https://bridgecore-mcp.chinlee2200.workers.dev/streamable-http

它能做什麼

工具清單

工具(4)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢do(need, inputs, dry_run)

One tool for 3,597 app capabilities (n8n catalog + OpenAPI + MCP): say what should happen; get the exact call or the result. Plain words in ('send an sms to +1 213 555 0100 saying hello', 'add a row to google sheets'); the matching capability is found, its required inputs are checked (values you said out loud — emails, #channels, +phones — are filled for you), and then: dry_run=true (default, safe, free) returns the exact HTTP/MCP request that would be sent, with `missing` naming any input still needed; dry_run=false makes the call and returns the service's reply (`charged` counts successful calls at fee_usd each; failures and missing inputs cost nothing). A 'when …' need or several steps returns the plan: HTTP/MCP steps are called one by one (no data flows between them), n8n-only steps come back as an importable n8n workflow — they run inside n8n, not here. No credentials pass through this server: a capability that needs an API key is called from an Apify Actor run (per-run `auth`), here it only shows the request. Use plan_automation to see alternatives, find_recipe for ready-made flows.

輸入結構描述

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string",
      "description": "What should happen, in plain words. One action to run it ('text +1… saying hi'); 'when …' for a flow."
    },
    "inputs": {
      "type": "object",
      "description": "Values for the capability's inputs by name (see `missing` in a dry run). Optional.",
      "additionalProperties": true
    },
    "dry_run": {
      "type": "boolean",
      "default": true,
      "description": "true (default): show the exact request, send nothing. false: make the call."
    }
  },
  "required": [
    "need"
  ]
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string"
    },
    "dry_run": {
      "type": "boolean",
      "description": "true = nothing was sent"
    },
    "fee_usd": {
      "type": "number",
      "description": "price per successful real call"
    },
    "steps": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true,
        "description": "One step: text, kind (trigger/action), the chosen tool or a gap."
      },
      "description": "per step: capability, request (headers masked), missing inputs, status/data/error"
    },
    "ran": {
      "type": "integer",
      "description": "real calls made"
    },
    "charged": {
      "type": "integer",
      "description": "successful calls billed"
    },
    "workflow": {
      "type": "object",
      "description": "n8n workflow when a step can only run inside n8n"
    },
    "note": {
      "type": "string"
    }
  },
  "required": [
    "need"
  ],
  "additionalProperties": true
}
🟢find_recipe(need, limit)

Find a ready-made automation recipe for a plain-words need, e.g. 'when a typeform is submitted add a row to google sheets and send a slack message'. Returns the best matching recipes (apps chained with →, what it does, the n8n workflow JSON, the blanks to fill and accounts to connect) plus matching public n8n templates (title + official link). Use when a person wants to connect apps, automate a workflow, sync tools, or get notified when something happens.

輸入結構描述

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string",
      "description": "What should happen, in plain words. Start with 'when …' for the trigger."
    },
    "limit": {
      "type": "integer",
      "default": 3,
      "minimum": 1,
      "maximum": 10,
      "description": "How many recipes to return (1-10)."
    }
  },
  "required": [
    "need"
  ]
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string"
    },
    "recipes": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      },
      "description": "matching tested recipes, each with its n8n workflow, blanks and accounts"
    },
    "public_templates": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      },
      "description": "public n8n templates: title + official link"
    },
    "planned_steps": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true,
        "description": "One step: text, kind (trigger/action), the chosen tool or a gap."
      }
    }
  },
  "required": [
    "need"
  ],
  "additionalProperties": true
}
🟢plan_automation(need, alternatives)

Turn a plain-words need into steps (one trigger + actions) and pick the concrete tool for each step from 3,000+ app capabilities (n8n nodes, OpenAPI, MCP). Reports a gap when the named app cannot do a step instead of substituting another app. Use before building any integration or workflow.

輸入結構描述

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string",
      "description": "What should happen, in plain words: 'when <trigger> <action>, then <action>'."
    },
    "alternatives": {
      "type": "integer",
      "default": 3,
      "minimum": 1,
      "maximum": 5,
      "description": "Runner-up tools to list per step (1-5)."
    }
  },
  "required": [
    "need"
  ]
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string"
    },
    "steps": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true,
        "description": "One step: text, kind (trigger/action), the chosen tool or a gap."
      },
      "description": "trigger + actions, each with the best tool, alternatives, or a gap"
    }
  },
  "required": [
    "need"
  ],
  "additionalProperties": true
}
🟢make_n8n_workflow(need, name)

Generate an importable n8n workflow JSON from a plain-words need, with every node wired in order, values said out loud already filled (emails, #channels, trigger events), plus the list of blanks only the person can fill and the credentials to connect. Shape-checked; the person tests it in n8n before turning it on.

輸入結構描述

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string",
      "description": "What should happen, in plain words. Start with 'when …' for the trigger."
    },
    "name": {
      "type": "string",
      "description": "Workflow name shown in n8n (optional; made from the need when left out)."
    }
  },
  "required": [
    "need"
  ]
}

輸出結構描述

{
  "type": "object",
  "properties": {
    "need": {
      "type": "string"
    },
    "workflow": {
      "type": "object",
      "description": "importable n8n workflow JSON"
    },
    "to_fill": {
      "type": "array",
      "items": {
        "type": "object",
        "additionalProperties": true
      },
      "description": "blanks only the person can fill"
    },
    "accounts": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "credentials to connect"
    },
    "problems": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "shape-check findings (empty = clean)"
    },
    "how_to_import": {
      "type": "string"
    },
    "links": {
      "type": "object",
      "additionalProperties": true
    }
  },
  "required": [
    "need"
  ],
  "additionalProperties": true
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本4 個工具