Server data from the Official MCP Registry
Safe Facebook Pages publishing with brand-voice, image-required & anti-duplication checks.
Safe Facebook Pages publishing with brand-voice, image-required & anti-duplication checks.
Valid MCP server (1 strong, 4 medium validity signals). No known CVEs in dependencies. Package registry verified. Imported from the Official MCP Registry.
9 files analyzed · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: META_USER_TOKEN
Environment variable: MCP_FB_PUBLISHER_CONFIG
Environment variable: MCP_FB_PUBLISHER_CONFIG_JSON
Environment variable: OPENAI_API_KEY
Environment variable: FAL_KEY
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-anthonyjbolo-mcp-fb-publisher": {
"env": {
"FAL_KEY": "your-fal-key-here",
"OPENAI_API_KEY": "your-openai-api-key-here",
"META_USER_TOKEN": "your-meta-user-token-here",
"MCP_FB_PUBLISHER_CONFIG": "your-mcp-fb-publisher-config-here",
"MCP_FB_PUBLISHER_CONFIG_JSON": "your-mcp-fb-publisher-config-json-here"
},
"args": [
"mcp-fb-publisher"
],
"command": "uvx"
}
}
}From the project's GitHub README.
An MCP server that lets Claude (or any MCP-compatible LLM) safely publish posts to multiple Facebook Pages through the Meta Graph API, with built-in guardrails: brand-voice config, banned-topic blocklists, image-required enforcement, and anti-duplication checks across recent feed posts.
Letting an LLM agent post directly to your Facebook Pages is a footgun unless you put guardrails in front. Common failure modes I have hit running 5+ pages:
mcp-fb-publisher ships an MCP server that wraps the Meta Graph API behind 4 deterministic tools, all driven by a single config.yaml. Every publish call goes through validation by default. Validation is pure-Python (no LLM), reproducible in CI, and runs offline.
4 MCP tools:
| Tool | What it does |
|---|---|
fb_publish_post | Publishes (or schedules) a post on a configured page. Runs full validation by default; pass skip_validation=True to bypass. |
fb_validate_pre_publish | Dry-run all guardrails. Returns `verdict: go |
fb_anti_duplicate_check | Compares a candidate message against the page's recent posts using Jaccard similarity over word 4-grams. |
fb_generate_post_with_image | Generates an image via OpenAI (gpt-image-1) or fal.ai (flux-pro) and returns a URL ready for fb_publish_post. |
# 1. Install
pip install mcp-fb-publisher
# 2. Copy and edit the example config
cp config.example.yaml config.yaml
# -> set page_id values, brand voices, banned_topics
# 3. Set required env
export META_USER_TOKEN="<your long-lived Meta page/user token>"
export MCP_FB_PUBLISHER_CONFIG="$PWD/config.yaml"
# 4. (Optional) for image generation
export OPENAI_API_KEY="sk-..." # or
export FAL_KEY="..."
# 5. Run the MCP server (stdio transport)
mcp-fb-publisher
Add to your claude_desktop_config.json:
{
"mcpServers": {
"fb-publisher": {
"command": "mcp-fb-publisher",
"env": {
"META_USER_TOKEN": "your_token_here",
"MCP_FB_PUBLISHER_CONFIG": "/absolute/path/to/config.yaml",
"OPENAI_API_KEY": "sk-..."
}
}
}
}
Then ask Claude things like:
"Post on the marketing page: 'New collection drops Friday'. Generate an image first, validate, then publish."
Claude will call fb_generate_post_with_image → fb_validate_pre_publish → fb_publish_post.
flowchart LR
A[Claude / MCP client] -->|tool call| B[FastMCP server]
B --> C{tool}
C -->|generate| D[OpenAI / fal.ai]
C -->|validate| E[Validator<br/>pure Python]
C -->|anti-dup| F[Meta Graph API<br/>fetch_recent_posts]
C -->|publish| G[Meta Graph API<br/>POST /feed or /photos]
E -.reads.-> H[(config.yaml<br/>per-page rules)]
G -.reads.-> H
F -.reads.-> H
The split between generation, validation and publish is intentional: it lets the LLM iterate on the visual without burning Meta API quota, and it makes the guardrails inspectable in CI without a Meta account.
We compare the candidate message against every post within anti_duplicate_lookback_days (per-page, default 14) using Jaccard similarity over word 4-grams:
similarity = |A ∩ B| / |A ∪ B|similarity >= similarity_threshold (default 0.5), block.Why this and not embeddings: deterministic, free, no extra API key, fast enough for 50 candidates per call. If you want LLM-grade semantic comparison, add another layer on top — the fb_validate_pre_publish tool returns the score so your agent can decide.
defaults:
language: en
brand_voice: |
Direct, professional, no fluff.
banned_topics: []
image_required: true
anti_duplicate_lookback_days: 14
pages:
marketing_main:
page_id: "0000000000000000"
name: "My Brand — Main"
brand_voice: |
Confident, concise, customer-first.
banned_topics:
- competitor_brand_a
- leaked_codename
image_required: true
community:
page_id: "0000000000000002"
name: "Community"
image_required: false
Note: the brand_voice field is informational — it's surfaced to the calling LLM via the tool description but the server itself does not LLM-validate against it. This is by design (tests must run offline). Layer your own LLM check on top if you want enforcement.
You manage 5 Facebook pages for clients. Each has its own brand voice, banned topics (competitor names), and image policy. Configure them all in one config.yaml, give Claude the tool, and let the agent draft + validate + publish across all of them with safety rails.
You run a single product page and want Claude to schedule the next 30 days of posts. Set image_required: true, give the agent your product brief, and use fb_anti_duplicate_check to make sure no two posts land on the same angle within a fortnight.
You rotate flash promos. Set anti_duplicate_lookback_days: 7 for the promo page and 14 for the evergreen content page. Combine with scheduled_at to queue a week's worth of posts in one shot.
git clone https://github.com/anthonyjbolo/mcp-fb-publisher.git
cd mcp-fb-publisher
python3.12 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev,openai,fal]"
# Run the test suite (offline, no Meta credentials needed)
pytest
# Lint
ruff check .
All tests use httpx.MockTransport and pytest-mock. No real Meta API calls in tests.
META_USER_TOKEN only. Never hard-code it.***REDACTED***) before they leave the process.config.yaml is in .gitignore. Only config.example.yaml is committed.fb_check_token_expiry).Construit en Nouvelle-Calédonie pour gérer 5 pages FB en parallèle (auto-école, marketplace de bingo, atelier d'apps, marque de tee-shirts, page média). Tous les écueils ci-dessus sont des bugs que j'ai vraiment vécus. Le serveur MCP est la couche que j'aurais aimé avoir le premier jour — maintenant elle est libre.
MIT — see LICENSE.
Issues + PRs welcome. Please run pytest and ruff check . before opening a PR. For substantial features, open an issue first to discuss.
#BuiltOnClaudeCode
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.