winrm-mcp-server

An MCP server for working with Windows Remote Management (WinRM). It exposes WinRM-related capabilities to AI agents via the Model Context Protocol (MCP), allowing them to connect to Windows hosts and perform remote operations (e.g., run commands) through the MCP tool interface.

Evaluated Apr 04, 2026 (17d ago)
Homepage ↗ Repo ↗ Infrastructure mcp winrm windows automation remote-execution devtools
⚙ Agent Friendliness
37
/ 100
Can an agent use this?
🔒 Security
43
/ 100
Is it safe for agents?
⚡ Reliability
32
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
55
Documentation
40
Error Messages
0
Auth Simplicity
35
Rate Limits
0

🔒 Security

TLS Enforcement
60
Auth Strength
50
Scope Granularity
20
Dep. Hygiene
45
Secret Handling
40

Security characteristics depend on MCP tool design and WinRM configuration (TLS, auth method, credential storage). Because no concrete implementation details were provided in the prompt, scores assume typical risks: remote execution capability, potential coarse authorization, and the need for strict host/command allowlisting, least-privilege WinRM accounts, and strong credential protection.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
45
AF Security Reliability

Best When

You have controlled access to Windows hosts over WinRM and want agents to perform scripted administrative actions through an MCP tool layer.

Avoid When

You cannot restrict agent actions/targets, lack auditing, or cannot secure WinRM credentials and network paths.

Use Cases

  • Agent-driven remote command execution on Windows machines via WinRM
  • Automating administrative tasks (e.g., service checks, script execution) across managed Windows fleets
  • Integrating WinRM operations into multi-tool agent workflows

Not For

  • Interactive human approval workflows without guardrails
  • Untrusted-agent execution in high-sensitivity environments without strict authorization and auditing
  • Public-facing internet use without network controls

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: WinRM authentication (e.g., username/password or Kerberos/NTLM depending on configuration; exact method not provided in prompt data)
OAuth: No Scopes: No

Authentication mechanism details are not present in the provided prompt content, so exact auth method and whether fine-grained scopes are supported cannot be confirmed.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; likely an open-source/community package or self-hosted tool.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Remote execution tools are high-risk: agents may accidentally run destructive commands unless actions are tightly constrained
  • WinRM reliability can be sensitive to network/firewall/WinRM configuration and auth type; retries may amplify load if commands are not idempotent
  • Credential handling and host allowlisting are critical to prevent lateral movement

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for winrm-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered