Dubstrata MCP server

Read from the package source without running it. The installed server may list more.

• check_source_trust

  Checks the historical trust and fallacy rate of a specific domain. Returns a structured JSON featuring 'structured_result' with registry metadata, fallacy rates, absolute claims count, is_trusted status, and security alerts.

• compile_intelligence_report

  Compiles a deeply analytical, formal 10-section intelligence report (featuring BLUF, Key Findings, Source Evaluation, Outlook) on a specific financial or narrative topic, utilizing advanced causal RAG reasoning and Gemini.

• find_conflicts

  Identifies potential contradictions by grouping all claims about an entity by their source URL. Returns a structured JSON featuring 'structured_result' with conflict groupings and source URL lists.

• get_all_facts

  Bypasses vector math to pull ALL active claims and facts known about an entity. Returns a structured JSON featuring 'structured_result' with lists of atomic facts, evidence, and source attributions.

• get_entities_by_category

  Finds entities matching a specific category (e.g., 'PERSON', 'ORGANIZATION'). Returns a structured JSON featuring 'structured_result' with entity lists, matching counts, and filter options.

• get_historical_timeline

  Acts as a Time Machine to retrieve superseded or historical claims about an entity. Returns a structured JSON featuring 'structured_result' with ordered list of timeline items and timestamps.

• get_interaction_hooks

  Fetches actionable next-steps (Interaction Hooks) associated with a specific Document URL. Returns a structured JSON featuring 'structured_result' with lists of next-steps hooks.

• ingest_knowledge

  Ingests knowledge into the Graph RAG (via URL scrape or direct text). Returns a structured JSON featuring 'structured_result' with code, source metadata, entities/claims counts, and token compression ratios.

• query_graph

  Retrieves dense Graph RAG context via vector similarity search and graph traversal. Returns a structured JSON featuring 'structured_result' containing standard outcome status codes, aggregate causal/sentiment indices, and lists of claims, relations, and source document metadata.

• submit_feedbackwrite action

  Submits authenticated tenant feedback (score 1 to 5) for a specific transaction log_id, dynamically adjusting RAG graph weights and consensus parameters.

• Code scan2 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancerepository not readable: repo not found3/15
• Maintainer identityno repository or website to verify2/10

Dubstrata: common questions

Is Dubstrata MCP server safe?

With care: it is graded C, so read the findings first (55/100). Read the Dubstrata safety report

How do I install Dubstrata?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Dubstrata need an API key?

Yes. The registry entry asks for DUBSTRATA_API_KEY.

Is Dubstrata maintained?

The latest release is v1.3.1.

What can I use instead of Dubstrata?

Servers from other publishers that do the same job: DataSinking MCP server, Google Surf MCP server and rag-rat MCP server. Compare all Dubstrata alternatives.