Skip to content
Back to search

facebook-mcp-server

Facebook MCP server for automating posts, comment moderation, insights, and sentiment filtering.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/hagaihen--facebook-mcp-server/badge.svg)](/listings/hagaihen--facebook-mcp-server)

HTML

<a href="/listings/hagaihen--facebook-mcp-server"><img src="/api/listings/hagaihen--facebook-mcp-server/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

1. Clone the Repository

git clone https://github.com/your-org/facebook-mcp-server.git
cd facebook-mcp-server

2. πŸ› οΈ Installation

Install dependencies using uv, a fast Python package manager: If uv is not already installed, run:

curl -Ls https://astral.sh/uv/install.sh | bash

Once uv is installed, install the project dependencies:

uv pip install -r requirements.txt

3. Set Up Environment

Create a .env file in the root directory and add your Facebook Page credentials. You can obtain these from https://developers.facebook.com/tools/explorer

FACEBOOK_ACCESS_TOKEN=your_facebook_page_access_token
FACEBOOK_PAGE_ID=your_page_id

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md Β· README Β· 136 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Facebook MCP Server
  2. This project is a **MCP server** for automating and managing interactions on a Facebook Page using the Facebook Graph API. It exposes tools to create posts, moderate comments, fetch post insights, and filter negative feedback β€” ready to plug into Claude, or other LLM-based agents.
  3. [![Trust Score](https://archestra.ai/mcp-catalog/api/badge/quality/HagaiHen/facebook-mcp-server)](https://archestra.ai/mcp-catalog/hagaihen__facebook-mcp-server)
  4. <a href="https://glama.ai/mcp/servers/@HagaiHen/facebook-mcp-server">
  5. <img width="380" height="200" src="https://glama.ai/mcp/servers/@HagaiHen/facebook-mcp-server/badge" />
  6. </a>
  7. ---
  8. ## πŸ€– What Is This?
  9. This MCP provides a suite of AI-callable tools that connect directly to a Facebook Page, abstracting common API operations as LLM-friendly functions.
  10. ### βœ… Benefits
  11. - Empowers **social media managers** to automate moderation and analytics.
  12. - Seamlessly integrates with **Claude Desktop or any Agent client**.
  13. - Enables fine-grained control over Facebook content from natural language.
  14. ---
  15. ## πŸ“¦ Features
  16. | Tool | Description |
  17. |----------------------------------|---------------------------------------------------------------------|
  18. | `post_to_facebook` | Create a new Facebook post with a message. |
  19. | `reply_to_comment` | Reply to a specific comment on a post. |
  20. | `get_page_posts` | Retrieve recent posts from the Page. |
  21. | `get_post_comments` | Fetch comments on a given post. |
  22. | `delete_post` | Delete a specific post by ID. |
  23. | `delete_comment` | Delete a specific comment by ID. |
  24. | `hide_comment` | Hide a comment from public view. |
  25. | `unhide_comment` | Unhide a previously hidden comment. |
  26. | `delete_comment_from_post` | Alias for deleting a comment from a specific post. |
  27. | `filter_negative_comments` | Filter out comments with negative sentiment keywords. |
  28. | `get_number_of_comments` | Count the number of comments on a post. |
  29. | `get_number_of_likes` | Count the number of likes on a post. |
  30. | `get_post_impressions` | Get total impressions on a post. |
  31. | `get_post_impressions_unique` | Get number of unique users who saw the post. |
  32. | `get_post_impressions_paid` | Get number of paid impressions on the post. |
  33. | `get_post_impressions_organic` | Get number of organic impressions on the post. |
  34. | `get_post_engaged_users` | Get number of users who engaged with the post. |
  35. | `get_post_clicks` | Get number of clicks on the post. |
  36. | `get_post_reactions_like_total` | Get total number of 'Like' reactions. |
  37. | `get_post_top_commenters` | Get the top commenters on a post. |
  38. | `post_image_to_facebook` | Post an image with a caption to the Facebook page. |
  39. | `send_dm_to_user` | Send a direct message to a user. |
  40. | `update_post` | Updates an existing post's message. |
  41. | `schedule_post` | Schedule a post for future publication. |
  42. | `get_page_fan_count` | Retrieve the total number of Page fans. |
  43. | `get_post_share_count` | Get the number of shares on a post. |
  44. | `get_post_reactions_breakdown` | Get all reaction counts for a post in one call. |
  45. | `bulk_delete_comments` | Delete multiple comments by ID. |
  46. | `bulk_hide_comments` | Hide multiple comments by ID. |
  47. | `bulk_unhide_comments` | Unhide multiple comments by ID. |
  48. | `get_comment_replies` | Get all replies to a specific comment. |
  49. | `get_post_permalink` | Get the permalink URL of a post. |
  50. | `get_scheduled_posts` | List all scheduled (unpublished) posts on the Page. |
  51. | `get_page_info` | Get extended Page details (name, about, category, website). |
  52. ---
  53. ## πŸš€ Setup & Installation
  54. ### 1. Clone the Repository
  55. ```bash
  56. git clone https://github.com/your-org/facebook-mcp-server.git
  57. cd facebook-mcp-server
  58. ```
  59. ### 2. πŸ› οΈ Installation
  60. Install dependencies using uv, a fast Python package manager:
  61. If uv is not already installed, run:
  62. ```bash
  63. curl -Ls https://astral.sh/uv/install.sh | bash
  64. ```
  65. Once uv is installed, install the project dependencies:
  66. ```bash
  67. uv pip install -r requirements.txt
  68. ```
  69. ### 3. Set Up Environment
  70. Create a .env file in the root directory and add your Facebook Page credentials.
  71. You can obtain these from https://developers.facebook.com/tools/explorer
  72. ```bash
  73. FACEBOOK_ACCESS_TOKEN=your_facebook_page_access_token
  74. FACEBOOK_PAGE_ID=your_page_id
  75. ```
  76. ## 🧩 Using with Claude Desktop
  77. To set up the FacebookMCP in Clade:
  78. 1. Open Clade.
  79. 2. Go to Settings β†’ Developer β†’ Edit Config.
  80. 3. In the config file that opens, add the following entry:
  81. ```bash
  82. "FacebookMCP": {
  83. "command": "uv",
  84. "args": [
  85. "run",
  86. "--with",
  87. "mcp[cli]",
  88. "--with",
  89. "requests",
  90. "mcp",
  91. "run",
  92. "/path/to/facebook-mcp-server/server.py"
  93. ]
  94. }
  95. ```
  96. ---
  97. ## βœ… You’re Ready to Go!
  98. That’s it β€” your Facebook MCP server is now fully configured and ready to power Claude Desktop. You can now post, moderate, and measure engagement all through natural language prompts!
  99. ---
  100. ## 🀝 Contributing
  101. Contributions, issues, and feature requests are welcome!
  102. Feel free to fork the repo and submit a pull request.
  103. - Create a branch: `git checkout -b feature/YourFeature`
  104. - Commit your changes: `git commit -m 'feat: add new feature'`
  105. - Push to the branch: `git push origin feature/YourFeature`
  106. - Open a pull request πŸŽ‰

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.