SecurityCopilotSAFE
MCP Server that integrates with Security Copilot, Sentinel and other tools (in the future). It enhance the process of developing , testing and uploading Security Copilot artifacts.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Python-based MCP server using FastMCP library that provides integration with Microsoft Security Copilot and Microsoft Sentinel using Azure Identity Authentication.
Overview
This project implements an MCP server that enables:
- Running KQL queries against Microsoft Sentinel
- Uploading/Updating Microsoft Security Copilot skillsets/plugins
- Running prompts and skills in Microsoft Security Copilot
The server acts as a bridge between development environments and Microsoft Security Copilot, allowing for testing, deployment, and execution of skills and plugins. It uses SSE as transport layer for the MCP server. There are many use cases for the current integration. One of the most interesting ones is to support the development, test and deployment of Security Copilot KQL Skills.
Features
- Sentinel Integration: Execute KQL queries against your Sentinel workspace
- Security Copilot Management:
- List existing skillsets/plugins
- Upload new or update existing skillsets/plugins
- Run prompts or skills within Security Copilot
- Authentication Support: Multiple authentication methods including interactive browser, client secret, and managed identity
Roadmap
The next features will include:
- Promptbook test and Update
- Run Advance Hunting queries in Defender XDR
Prerequisites
- Python 3.8+
- Microsoft Sentinel workspace
- Microsoft Security Copilot access
- Appropriate Azure permissions for Sentinel and Security Copilot
Installation
- Clone the repository:
git clone https://github.com/jguimera/SecurityCopilotMCPServer.git cd SecurityCopilotMCPServer
- Install dependencies:
pip install -r requirements.txt
- Create a
.envfile with the following configuration:
#Add App Reg to use ClientID and Secret authentication #AZURE_TENANT_ID=your_tenant_i
134d1d96d522OBSERVED · 2026-10-09Exposed tools (4)
1 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_skillsets | read | Get skillsets from Security Copilot. |
run_prompt | write | |
run_sentinel_query | write | Run a query against Sentinel. |
upload_plugin | write |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
azure-identity, azure-monitor-query, pyyaml, msgraph-sdk, python-dotenv, pandas, fastmcp
Gates applied: no_behavioural_pass.
134d1d96d522full audit observations/trust-audit/mcp-server/jguimera__securitycopilot.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 134d1d96d522 | SAFE | B | 89 | first audit |
Questions
What is the SecurityCopilot MCP server?
MCP Server that integrates with Security Copilot, Sentinel and other tools (in the future). It enhance the process of developing , testing and uploading Security Copilot artifacts.
What tools does SecurityCopilot expose?
4 in total: 1 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is SecurityCopilot safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does SecurityCopilot need?
It reads AUTHENTICATION_TYPE and AZURE_CLIENT_SECRET from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does SecurityCopilot run?
It speaks sse, so it runs as a service you connect to over the network.
How current is this page?
The grade is for one exact copy of the source (134d1d96d522), read on 2026-10-09. The repository is watched and re-audited when it changes.