DocSentinel MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
pip install docsentinel
2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add doc-sentinel -- python "<FULL_PATH_TO_DOCSENTINEL>/dist/index.js"

Replace <FULL_PATH_TO_DOCSENTINEL>/dist/index.js with the actual folder you prepared in step 1.

README.md

Automated security assessment for documents and questionnaires

English | 简体中文 | 日本語 | 한국어 | Français | Deutsch

DocSentinel Automated security assessment for documents and questionnaires


What is DocSentinel?

DocSentinel is an AI-powered assistant for security teams. It automates the review of security-related documents, forms, and reports (e.g. Security Questionnaires, design docs, compliance evidence), compares them against your policy and knowledge base, and produces structured assessment reports with risks, compliance gaps, and remediation suggestions.

🚀 Agent Ready: Supports Model Context Protocol (MCP) to be used as a "skill" by OpenClaw, Claude Desktop, and other autonomous agents.

  • Multi-format input: PDF, Word, Excel, PPT, text — parsed into a unified format for the LLM.
  • Knowledge base (RAG): Upload policy and compliance documents; the agent uses them as reference when assessing.
  • Multiple LLMs: Use OpenAI, Claude, Qwen, or Ollama (local) via a single interface.
  • Structured output: JSON/Markdown reports with risk items, compliance gaps, and actionable remediations.

Ideal for enterprises that need to scale security assessments across many projects without proportionally scaling headcount.


Why DocSentinel?

Pain Point DocSentinel Solution
Fragmented criteriaPolicies, standards, and precedents are scattered. Single knowledge base ensures consistent findings and traceability.
Heavy questionnaire workflowBusiness fills form → Security reviews → Business adds evidence → Security reviews again. Automated first-pass and gap analysis reduces manual back-and-forth rounds.
Pre-release review pressureSecurity needs to review and sign off on technical docs before launch. Structured reports help reviewers focus on decision-making, not line-by-line reading.
Scale vs. consistencyMany projects and standards lead to inconsistent or delayed manual reviews. Unified pipeline with configurable scenarios keeps assessments consistent and auditable.

See the full problem statement and product goals in SPEC.md.


Architecture

DocSentinel is built around an orchestrator that coordinates parsing, the knowledge base (RAG), skills, and the LLM. You can use cloud or local LLMs and optional integrations (e.g. AAD, ServiceNow) as your environment requires.

flowchart TB
    subgraph User["👤 User / Security Staff"]
    end
    subgraph Access["Access Layer"]
        API["REST API / MCP"]
    end
    subgraph Core["DocSentinel Core"]
        Orch["Orchestrator"]
        Mem["Memory"]
        Skill["Skills"]
        KB["Knowledge Base (RAG)"]
        Parser["Parser"]
    end
    subgraph LLM["LLM Layer"]
        Abst["LLM Abstraction"]
    end
    subgraph Backends["LLM Backends"]
        Cloud["OpenAI / Claude / Qwen"]
        Local["Ollama / vLLM"]
    end

    User --> API
    API --> Orch
    Orch <--> Mem
    Orch --> Skill
    Orch --> KB
    Orch -->

Tools (2)

assess_documentAnalyzes a security document or questionnaire against the knowledge base to identify risks and compliance gaps.
query_knowledge_baseSearches the RAG knowledge base for policy or compliance information.

Environment Variables

OPENAI_API_KEYAPI key for OpenAI LLM integration
ANTHROPIC_API_KEYAPI key for Claude LLM integration

Configuration

claude_desktop_config.json
{"mcpServers": {"docsentinel": {"command": "python", "args": ["path/to/docsentinel/main.py"], "env": {"OPENAI_API_KEY": "your-key-here"}}}}

Try it

Assess the attached security questionnaire against our internal compliance policy.
Find any compliance gaps in the provided design document regarding data encryption.
Search the knowledge base for our current policy on third-party vendor risk management.
Generate a remediation report for the identified security risks in the uploaded report.

Frequently Asked Questions

What are the key features of DocSentinel?

Multi-format input parsing for PDF, Word, Excel, PPT, and text files. RAG-based knowledge base for consistent policy and compliance assessment. Automated generation of structured reports with risk items and remediation suggestions. Support for multiple LLM backends including OpenAI, Claude, and local Ollama models.

What can I use DocSentinel for?

Automating the first-pass review of incoming security questionnaires from vendors. Scaling security sign-offs on technical design documents before product launch. Ensuring consistent compliance gap analysis across multiple enterprise projects. Reducing manual back-and-forth between security teams and business units.

How do I install DocSentinel?

Install DocSentinel by running: pip install docsentinel

What MCP clients work with DocSentinel?

DocSentinel works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep DocSentinel docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare