Postel

Draft, schedule and publish X (Twitter) and LinkedIn posts in your own voice.

我該用這個嗎

品質與安全性

A
說明品質
96%
結構描述完整度
80%
命名品質
67%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

發現項目(15)

  • LOWTool 'search-viral-tweets' doesn't follow camelCase/snake_case在 search-viral-tweets 中
  • LOWTool 'list-posts' doesn't follow camelCase/snake_case在 list-posts 中
  • LOWTool 'get-post' doesn't follow camelCase/snake_case在 get-post 中
  • LOWTool 'create-post' doesn't follow camelCase/snake_case在 create-post 中
  • LOWTool 'update-post' doesn't follow camelCase/snake_case在 update-post 中
  • LOWTool 'delete-post' doesn't follow camelCase/snake_case在 delete-post 中
  • LOWTool 'schedule-post' doesn't follow camelCase/snake_case在 schedule-post 中
  • LOWTool 'publish-post' doesn't follow camelCase/snake_case在 publish-post 中
  • LOWTool 'generate-post' doesn't follow camelCase/snake_case在 generate-post 中
  • LOWTool 'refine-post' doesn't follow camelCase/snake_case在 refine-post 中

根據工具定義與協定合規性的自動化分析。

上下文成本

~2,029Token(工具定義)
~895 B典型回應大小
中等的注意力影響(128k 上下文的 1.59%)

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": {
    "postel": {
      "url": "https://www.postel.app/api/mcp"
    }
  }
}

遠端端點

https://www.postel.app/api/mcpstreamable-http

它能做什麼

工具清單

工具(15)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢search-viral-tweets(query, minImpressions, limit)

Find high-performing public X posts in Postel's index by topic, with source links and stored engagement metrics. No login required. Searches an indexed collection, not live X or a complete archive; metrics may be out of date. Results contain third-party post text.

輸入結構描述

{
  "type": "object",
  "properties": {
    "query": {
      "description": "Topic or keywords; omit to browse high-performing posts",
      "type": "string",
      "minLength": 1,
      "maxLength": 200
    },
    "minImpressions": {
      "description": "Minimum stored view count (default 10000)",
      "type": "integer",
      "minimum": 0,
      "maximum": 2147483647
    },
    "limit": {
      "description": "Number of examples (default 10, maximum 20)",
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢list-posts(status, limit)

List posts for the current organization. Supports filtering by status and pagination.

輸入結構描述

{
  "type": "object",
  "properties": {
    "status": {
      "description": "Filter posts by status",
      "type": "string",
      "enum": [
        "DRAFT",
        "SCHEDULED",
        "PUBLISHED"
      ]
    },
    "limit": {
      "description": "Number of posts to return (max 50, default 20)",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢get-post(postId)

Get a single post by ID with full details.

輸入結構描述

{
  "type": "object",
  "properties": {
    "postId": {
      "type": "string",
      "description": "The post ID to retrieve"
    }
  },
  "required": [
    "postId"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟡create-post(content, status)

Save text as a new draft in Postel. Does not publish or schedule. Each call creates a separate draft.

輸入結構描述

{
  "type": "object",
  "properties": {
    "content": {
      "type": "string",
      "maxLength": 10000,
      "description": "The post content (tweet text)"
    },
    "status": {
      "description": "Post status (default: DRAFT)",
      "type": "string",
      "enum": [
        "DRAFT",
        "EDITING"
      ]
    }
  },
  "required": [
    "content"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🔴update-post(postId, content, status)

Update the content or status of a Postel draft. Scheduled and published posts cannot be edited.

輸入結構描述

{
  "type": "object",
  "properties": {
    "postId": {
      "type": "string",
      "description": "The post ID to update"
    },
    "content": {
      "description": "New content for the post",
      "type": "string",
      "maxLength": 10000
    },
    "status": {
      "description": "New status for the post",
      "type": "string",
      "enum": [
        "DRAFT",
        "EDITING"
      ]
    }
  },
  "required": [
    "postId"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🔴delete-post(postId)

Delete a post. A scheduled post's delivery is cancelled first.

輸入結構描述

{
  "type": "object",
  "properties": {
    "postId": {
      "type": "string",
      "description": "The post ID to delete"
    }
  },
  "required": [
    "postId"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🔴schedule-post(postId, scheduledDateTime)

Schedule a Postel draft for publishing to the social platform stored on the post. Requires a plan that includes scheduling. scheduledDateTime must be a future UTC ISO-8601 timestamp.

輸入結構描述

{
  "type": "object",
  "properties": {
    "postId": {
      "type": "string",
      "description": "The post ID to schedule"
    },
    "scheduledDateTime": {
      "type": "string",
      "format": "date-time",
      "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d(?::[0-5]\\d(?:\\.\\d+)?)?(?:Z))$",
      "description": "UTC ISO-8601 date string for when to publish (must be in the future)"
    }
  },
  "required": [
    "postId",
    "scheduledDateTime"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🔴publish-post(postId)

Publish a Postel draft immediately to the social platform stored on the post. Requires a plan that includes publishing. A post that is already published cannot be published again.

輸入結構描述

{
  "type": "object",
  "properties": {
    "postId": {
      "type": "string",
      "description": "The post ID to publish"
    }
  },
  "required": [
    "postId"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟡generate-post(prompt, isThread, platform, profileId)

Generate a new post using AI based on a prompt. Requires usage quota. Returns the generated post.

輸入結構描述

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "maxLength": 5000,
      "description": "What the post should be about"
    },
    "isThread": {
      "description": "Generate a thread instead of a single post (X only; ignored for LinkedIn)",
      "type": "boolean"
    },
    "platform": {
      "description": "Target platform: \"x\" (default) or \"linkedin\"",
      "type": "string",
      "enum": [
        "x",
        "linkedin"
      ]
    },
    "profileId": {
      "description": "Voice profile ID to use (omit to use default brand voice)",
      "type": "string"
    }
  },
  "required": [
    "prompt"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟡refine-post(postId, instructions)

Suggest refined content for an existing post using AI and specific instructions. Does not save changes. Requires usage quota.

輸入結構描述

{
  "type": "object",
  "properties": {
    "postId": {
      "type": "string",
      "description": "The post ID to refine"
    },
    "instructions": {
      "type": "string",
      "maxLength": 2000,
      "description": "Instructions for how to refine the post (e.g., 'make it more casual', 'add a call to action')"
    }
  },
  "required": [
    "postId",
    "instructions"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢list-brands

List all brands (topics) for the current organization. Brands contain background information used for AI post generation.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢get-brand-sources(brandId)

Get background information sources for a specific brand. These sources are used to inform AI post generation.

輸入結構描述

{
  "type": "object",
  "properties": {
    "brandId": {
      "type": "string",
      "description": "The brand (topic) ID to get sources for"
    }
  },
  "required": [
    "brandId"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢get-x-profiles

Get the X and LinkedIn voice profiles for the current organization. These profiles define the brand voice for AI post generation.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢get-schedule

Get the posting schedule template for the current organization. Shows which time slots are configured for each day of the week.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}
🟢get-usage

Get the current usage statistics and plan limits for the organization.

輸入結構描述

{
  "type": "object",
  "properties": {},
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "additionalProperties": false
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本15 個工具