OSINT MCP Server
MCP server for the OSINT Intelligence Platform, enabling AI assistants to interact with Telegram intelligence archives via 65 tools for search, entity analysis, event tracking, social graph, and platform monitoring.
README
OSINT MCP Server
MCP (Model Context Protocol) server for the OSINT Intelligence Platform, enabling Claude and other AI assistants to interact with your Telegram intelligence archive.
Features
This MCP server provides 65 tools organized into 14 categories for comprehensive OSINT analysis:
Message Tools (5 tools)
| Tool | Description |
|---|---|
search_messages |
Full-text search with 15+ filters (topic, importance, language, views, etc.) |
get_message |
Get detailed message with media, AI tags, entities, locations |
get_message_album |
Get grouped media album for lightbox display |
get_message_network |
Entity relationship graph (Flowsint-compatible) |
get_message_timeline |
Temporal context - before/after, semantic, event-based |
Semantic Search Tools (4 tools)
| Tool | Description |
|---|---|
semantic_search |
AI-powered 384-dim vector search - find by meaning |
find_similar_messages |
Find content similar to a specific message |
get_tags |
Get popular AI-generated tags (keywords, topics, emotions) |
search_by_tags |
Search messages by tags with AND/OR logic |
Unified Search (1 tool)
| Tool | Description |
|---|---|
unified_search |
Search across ALL sources: messages, events, RSS, entities |
Channel Tools (4 tools)
| Tool | Description |
|---|---|
list_channels |
List monitored Telegram channels with filters |
get_channel |
Channel details, affiliation, metadata |
get_channel_stats |
Message counts, spam rate, topic distribution |
get_channel_network |
Semantic relationship graph with topic clusters |
Social Graph Tools (7 tools)
| Tool | Description |
|---|---|
get_message_social_graph |
Complete social context: forwards, replies, comments, reactions |
get_channel_influence |
Channel-to-channel forward relationships |
get_influence_network |
Platform-wide influence network |
get_engagement_timeline |
Virality tracking over time |
get_message_comments |
Discussion thread from linked chat |
get_top_forwarded |
Viral content leaderboard |
get_top_influencers |
Top influencer profiles |
Entity Tools (4 tools)
| Tool | Description |
|---|---|
search_entities |
Search people, orgs, equipment (curated + OpenSanctions) |
get_entity |
Entity profile with aliases, metadata, linked counts |
get_entity_relationships |
Wikidata SPARQL relationships (employers, positions) |
get_entity_mentions |
Messages mentioning a specific entity |
Event Tools (5 tools)
| Tool | Description |
|---|---|
list_events |
Detected event clusters by tier (rumor→confirmed→verified) |
get_event_stats |
Event statistics by tier and type |
get_event |
Event details with channels, messages, RSS sources |
get_event_timeline |
Chronological timeline combining Telegram + RSS |
get_events_for_message |
Events linked to a specific message |
Analytics Tools (7 tools)
| Tool | Description |
|---|---|
get_timeline_stats |
Message volume over time (hour/day/week/month) |
get_topic_distribution |
Distribution across 13 topics |
get_language_distribution |
Language breakdown (uk, ru, en, etc.) |
get_channel_analytics |
Per-channel performance metrics |
get_activity_heatmap |
Daily activity for calendar visualization |
get_entity_analytics |
Most mentioned entities over time |
get_media_analytics |
Media archival stats with deduplication metrics |
Map/Geo Tools (6 tools)
| Tool | Description |
|---|---|
get_map_messages |
GeoJSON messages with server-side clustering |
get_map_clusters |
Event clusters by geographic location |
get_map_events |
Confirmed events for map display |
get_map_heatmap |
Density aggregation for heatmap |
suggest_locations |
Autocomplete from 30,000+ UA/RU locations |
reverse_geocode |
Find nearest location to coordinates |
Stream Tools (1 tool)
| Tool | Description |
|---|---|
get_unified_stream |
Combined Telegram + RSS intelligence feed |
Validation Tools (2 tools)
| Tool | Description |
|---|---|
validate_message |
Cross-reference Telegram with RSS (confirms/contradicts) |
get_message_correlations |
Find correlated RSS articles |
Media Tools (1 tool)
| Tool | Description |
|---|---|
get_media_gallery |
Browse archived media by channel, type, date |
Admin Stats Tools (15 tools)
| Tool | Description |
|---|---|
get_platform_dashboard |
Platform overview: messages, channels, entities, storage |
get_platform_stats_overview |
Comprehensive stats with service health |
get_data_quality_stats |
Enrichment coverage (translation, embeddings, geo) |
get_processing_stats |
Hourly processing metrics and latency |
get_storage_stats |
Storage breakdown by table and media type |
get_worker_stats |
Redis queue health and pending messages |
get_enrichment_tasks |
Status of 13 enrichment tasks |
get_cache_stats |
Redis cache hit rates and memory usage |
get_audit_stats |
LLM decision audit and verification rates |
get_spam_stats |
Spam classification metrics |
get_channels_admin_stats |
Channel inventory by affiliation/folder/rule |
get_entities_admin_stats |
Entity catalog stats and top mentioned |
get_rss_feeds_stats |
RSS feed health and article counts |
get_llm_prompts_stats |
LLM prompt performance metrics |
get_viral_posts |
Tracked viral posts for comment fetching |
System Health Tools (9 tools)
| Tool | Description |
|---|---|
get_system_health |
Basic API health check |
get_hardware_config |
Hardware tier detection (laptop/server/GPU) |
get_system_status |
Detailed system status |
get_metrics_overview |
Platform KPIs |
get_metrics_llm |
Ollama/LLM performance |
get_metrics_pipeline |
Real-time pipeline status |
get_metrics_services |
Per-service health |
list_llm_models |
Available LLM models (6 runtime-switchable) |
get_llm_model_health |
LLM availability check |
Installation
From npm (recommended)
npm install -g @osintukraine/mcp-server
From source
git clone https://github.com/osintukraine/osint-mcp-server.git
cd osint-mcp-server
npm install
npm run build
Configuration
Environment Variables
| Variable | Description | Default |
|---|---|---|
OSINT_API_URL |
OSINT Platform API base URL | http://localhost:8000 |
| JWT Authentication | ||
OSINT_JWT_TOKEN |
JWT token for authentication | (none) |
| API Key Authentication | ||
OSINT_API_KEY |
API key for authentication | (none) |
| Ory Kratos Authentication | ||
OSINT_ORY_USER_ID |
Ory Kratos user UUID | (none) |
OSINT_ORY_USER_EMAIL |
User email (optional) | (none) |
OSINT_ORY_USER_ROLE |
User role: authenticated, admin | authenticated |
Authentication Priority
The MCP server uses the first available authentication method:
- JWT Token -
OSINT_JWT_TOKEN- Standalone JWT authentication - API Key -
OSINT_API_KEY- Programmatic API access - Ory Kratos -
OSINT_ORY_USER_ID- Ory identity headers
Claude Code Configuration
Add a .mcp.json file to your project root:
Using npm package:
{
"mcpServers": {
"osint": {
"command": "npx",
"args": ["@osintukraine/mcp-server"],
"env": {
"OSINT_API_URL": "http://localhost:8000"
}
}
}
}
Using local installation:
{
"mcpServers": {
"osint": {
"command": "node",
"args": ["/path/to/osint-mcp-server/dist/index.js"],
"env": {
"OSINT_API_URL": "http://localhost:8000"
}
}
}
}
With API Key authentication:
{
"mcpServers": {
"osint": {
"command": "npx",
"args": ["@osintukraine/mcp-server"],
"env": {
"OSINT_API_URL": "https://api.osint.example.com",
"OSINT_API_KEY": "your-api-key-here"
}
}
}
}
With Ory Kratos authentication:
{
"mcpServers": {
"osint": {
"command": "npx",
"args": ["@osintukraine/mcp-server"],
"env": {
"OSINT_API_URL": "https://api.osint.example.com",
"OSINT_ORY_USER_ID": "your-kratos-user-uuid",
"OSINT_ORY_USER_EMAIL": "your-email@example.com",
"OSINT_ORY_USER_ROLE": "admin"
}
}
}
}
Usage Examples
Once configured, Claude can use these tools naturally:
Message Search & Analysis
"Search for high-importance messages about Bakhmut from the last 7 days"
"Find messages similar to message #12345 and show their social graph"
"Get the entity network for message #67890"
Entity Investigation
"Search for Putin in OpenSanctions and show relationships"
"Find all messages mentioning the Wagner Group"
Event Analysis
"List confirmed events from the last 24 hours"
"Show the timeline for event #123 with both Telegram and RSS sources"
"Validate message #456 against news sources"
Social Graph & Influence
"Who are the top influencers in the last week?"
"Show the influence network between channels"
"Get the engagement timeline for this viral message"
Platform Monitoring
"What's the current platform health?"
"Show data quality stats - translation and embedding coverage"
"Check the worker queue status"
Geographic Analysis
"Get geolocated messages in the Kharkiv region"
"Show the event heatmap for the last 48 hours"
Development
# Watch mode (auto-rebuild on changes)
npm run dev
# Type checking
npm run typecheck
# Test with MCP Inspector
npm run inspector
Architecture
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ Claude Code │────▶│ MCP Server │────▶│ OSINT API │
│ (AI Assistant) │ │ (65 tools) │ │ (FastAPI) │
└─────────────────┘ └──────────────────┘ └─────────────────┘
│ │ │
│ stdio transport │ HTTP/JSON │
│ │ │
┌────┴────┐ ┌─────┴─────┐ ┌──────┴──────┐
│ Request │ │ API Client│ │ PostgreSQL │
│ Handler │ │ (fetch) │ │ + pgvector │
└─────────┘ └───────────┘ └─────────────┘
License
MIT - see LICENSE
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
Related Projects
- OSINT Intelligence Platform - Main platform
- Model Context Protocol - MCP specification
- MCP SDK - Official MCP SDK
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。