Pressroom MCP Server
Enables headless execution of the full Pressroom pipeline via MCP, including scouting, generating, auditing, publishing content, and managing SEO, analytics, and team workflows through natural language prompts.
README
Pressroom MCP Server
Run the full Pressroom pipeline headless — no browser, no UI.
Any Claude Code session or MCP-compatible client can scout, generate, audit, publish, and more from a prompt.
Setup
cd /home/captain/data/projects/pressroom-mcp
./install.sh
Or manually:
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env
# Edit .env if your Pressroom backend is not on localhost:8000
Usage
Run standalone (stdio transport)
source venv/bin/activate
python server.py
Add to Claude Code
Add to your ~/.claude/settings.json or project .claude/settings.json:
{
"mcpServers": {
"pressroom": {
"command": "/home/captain/data/projects/pressroom-mcp/venv/bin/python",
"args": ["/home/captain/data/projects/pressroom-mcp/server.py"],
"env": {
"PRESSROOM_URL": "http://localhost:8000"
}
}
}
}
Available Tools (101)
Org Management
pressroom_list_orgs()— List all organizationspressroom_get_org(org_id)— Get org details
Pipeline
pressroom_scout(org_id, since_hours=24)— Pull signals from sourcespressroom_generate(org_id, channels=None)— Generate content from signalspressroom_approve(org_id, content_ids)— Approve content itemspressroom_publish(org_id)— Publish approved contentpressroom_full_pipeline(org_id, channels=None)— Scout + Generate in one shot
Content
pressroom_list_content(org_id, status="queued", limit=50)— List content itemspressroom_get_content(content_id)— Get full content itempressroom_spike_content(org_id, content_ids)— Spike (reject) content itemspressroom_edit_content(org_id, content_id, body="", headline="")— Edit content body or headlinepressroom_humanize_content(org_id, content_id)— Run humanizer on contentpressroom_schedule_content(org_id, content_id, publish_at)— Schedule content for future publish
Content Performance
pressroom_content_performance(org_id)— Get performance metrics for published contentpressroom_fetch_performance(org_id, content_id)— Fetch latest performance for a content item
Signals
pressroom_list_signals(org_id, limit=50)— List wire signals
Story Workbench
pressroom_list_stories(org_id, limit=20)— List editorial storiespressroom_create_story(org_id, title, angle="", editorial_notes="", signal_ids=None)— Create a storypressroom_get_story(org_id, story_id)— Get story with signals and notespressroom_add_signal_to_story(org_id, story_id, signal_id, editor_notes="")— Attach signal to storypressroom_generate_from_story(org_id, story_id, channels=None, team_member_id=None)— Generate content from storypressroom_discover_signals(org_id, story_id, mode="web")— Discover signals for a story
Wire (Company-Owned Sources)
pressroom_list_wire_sources(org_id)— List Wire sourcespressroom_create_wire_source(org_id, type, name, config=None)— Create a Wire sourcepressroom_fetch_wire(org_id, wire_source_id=None)— Fetch signals from Wire sourcespressroom_list_wire_signals(org_id, limit=40, type="")— List Wire signals
SIGINT Sources (Global Library)
pressroom_list_sources(type="", active_only=True)— List global source librarypressroom_create_source(type, name, config=None, category_tags=None, fetch_interval_hours=6)— Create a global sourcepressroom_sweep_sources(org_id, source_ids=None)— Sweep sources for signalspressroom_get_feed(org_id, limit=40, min_score=None)— Get relevance-scored SIGINT feed
Audit
pressroom_audit(org_id, domain="", deep=True)— Run SEO auditpressroom_scoreboard()— All orgs ranked by SEO scorepressroom_audit_history(org_id, audit_type="", limit=20)— Past audit results
Company Audit
pressroom_company_audit(org_id)— Run full company audit
SEO PR Pipeline
pressroom_seo_pr_run(org_id, repo_url, domain="", base_branch="main")— Start SEO PR pipelinepressroom_seo_pr_list(org_id)— List SEO PR runspressroom_seo_pr_status(org_id, run_id)— Get SEO PR run status
Competitive Intelligence
pressroom_competitive_scan(org_id, competitor_urls)— Run competitive scanpressroom_competitive_results(org_id)— Get stored competitive results
AI Visibility
pressroom_ai_visibility_scan(org_id)— Scan AI models for citationspressroom_ai_visibility_results(org_id)— Get AI visibility resultspressroom_ai_visibility_questions(org_id, questions)— Set visibility tracking questions
Analytics
pressroom_analytics(org_id)— Get analytics dashboard
Scoreboard
pressroom_team_activity(org_id)— Get team activity metrics from scoreboard
YouTube Studio
pressroom_youtube_script(org_id, content_id=None, brief="")— Generate YouTube scriptpressroom_youtube_list(org_id)— List scriptspressroom_youtube_export(script_id)— Export Remotion JSON packagepressroom_youtube_update(org_id, script_id, title="", hook="")— Update script title or hookpressroom_youtube_delete(org_id, script_id)— Delete a YouTube scriptpressroom_youtube_render(org_id, script_id)— Render script to video via Remotionpressroom_youtube_publish_video(org_id, script_id)— Publish rendered video
Blog Management
pressroom_blog_scrape(org_id, url)— Scrape and import a blog postpressroom_blog_list(org_id)— List blog postspressroom_blog_delete(org_id, post_id)— Delete a blog post
Google Search Console
pressroom_gsc_status(org_id)— Check GSC connection statuspressroom_gsc_properties(org_id)— List available GSC propertiespressroom_gsc_set_property(org_id, property_url)— Set active GSC propertypressroom_gsc_analytics(org_id, days=28)— Get GSC analytics datapressroom_gsc_summary(org_id)— Get GSC performance summarypressroom_gsc_blog_performance(org_id)— Get GSC blog post performancepressroom_gsc_inspect_url(org_id, url)— Inspect URL indexing status
Site Properties
pressroom_list_properties(org_id)— List site propertiespressroom_create_property(org_id, name, value, prop_type="domain")— Create a propertypressroom_update_property(org_id, property_id, value)— Update a propertypressroom_delete_property(org_id, property_id)— Delete a property
Brand
pressroom_brand_scrape(org_id, domain)— Scrape brand info from domainpressroom_brand_get(org_id)— Get brand profile
Assets
pressroom_list_assets(org_id, asset_type="")— List assetspressroom_create_asset(org_id, name, url, asset_type)— Create an assetpressroom_delete_asset(org_id, asset_id)— Delete an asset
Skills
pressroom_list_skills()— List available skillspressroom_get_skill(skill_name)— Get skill contentpressroom_invoke_skill(skill_name, input_text)— Run text through a skill
Team
pressroom_list_team(org_id)— List team memberspressroom_add_team_member(org_id, name, title="", bio="", email="", linkedin_url="", expertise_tags=None)— Add team memberpressroom_discover_team(org_id)— Auto-discover team memberspressroom_update_team_member(org_id, member_id, name="", title="", bio="")— Update team member detailspressroom_analyze_voice(org_id, member_id)— Analyze member's writing voicepressroom_team_gist_check(org_id)— Check gist status for all memberspressroom_generate_gist(org_id, member_id)— Generate author bio pagepressroom_publish_gist(org_id, member_id)— Publish author bio page
Settings
pressroom_get_settings(org_id)— Get all org settingspressroom_update_settings(org_id, settings)— Update org settingspressroom_connection_status(org_id)— Check service connection status
Onboarding
pressroom_onboard(org_id, domain, extra_context="")— Onboard a companypressroom_onboard_apply(org_id, profile)— Apply onboarding profilepressroom_onboard_status(org_id)— Check onboarding status
pressroom_compose_email(org_id, content_id)— Compose email draft from contentpressroom_list_email_drafts(org_id, status="", limit=20)— List email drafts
Medium
pressroom_medium_publish(org_id, content_id)— Publish content to Medium
Slack
pressroom_slack_test(org_id)— Send test Slack messagepressroom_slack_notify(org_id, content_id)— Send Slack notification for contentpressroom_slack_notify_queue(org_id)— Notify Slack about queued content
Token Usage
pressroom_usage(org_id)— Get current token usagepressroom_usage_history(org_id)— Get token usage history
Imports
pressroom_import_paste(org_id, text, channel="linkedin")— Import content from pasted text
Activity Log
pressroom_log(org_id, limit=20)— Get activity log
Data Sources
pressroom_list_datasources(org_id)— List data sourcespressroom_create_datasource(org_id, name, type, config)— Create a data sourcepressroom_test_datasource(org_id, ds_id)— Test data source connectionpressroom_delete_datasource(org_id, ds_id)— Delete a data source
Requirements
- Pressroom backend running at
PRESSROOM_URL(default:http://localhost:8000) - Python 3.10+
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.