sceptre-mcp-server

Provides a Model Context Protocol (MCP) server that exposes Sceptre CloudFormation management capabilities (stack lifecycle, querying, template rendering/validation, diff & drift, change sets, and project discovery) as MCP tools for AI agents.

Evaluated Apr 04, 2026 (0d ago)
Homepage ↗ Repo ↗ Infrastructure ai-ml devops infrastructure aws cloudformation sceptre mcp tooling
⚙ Agent Friendliness
57
/ 100
Can an agent use this?
🔒 Security
45
/ 100
Is it safe for agents?
⚡ Reliability
24
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
78
Documentation
82
Error Messages
0
Auth Simplicity
65
Rate Limits
0

🔒 Security

TLS Enforcement
40
Auth Strength
60
Scope Granularity
20
Dep. Hygiene
55
Secret Handling
50

Security is largely inherited from AWS IAM and the deployment environment. The MCP server itself appears to be a local/agent-invoked process; the README does not specify transport/TLS controls, MCP authentication, audit logging, or fine-grained tool authorization. Because it can execute impactful AWS operations, the primary risk is over-permissioning IAM or lacking agent-side approval/guardrails.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
20
Error Recovery
30
AF Security Reliability

Best When

You want an agent to call well-scoped MCP tools to manage AWS CloudFormation stacks through Sceptre in an environment where AWS credentials/permissions are already controlled.

Avoid When

You cannot tightly restrict agent permissions (AWS IAM) and MCP tool usage—this tool can drive powerful AWS actions (including deletes and executing change sets).

Use Cases

  • AI-assisted CloudFormation stack management via Sceptre (create/update/delete/launch)
  • Automated investigation of stack state (status, resources, events, outputs)
  • Generating and validating CloudFormation templates from Sceptre config
  • Detecting configuration drift and showing diffs vs deployed state
  • Orchestrating change sets (create/describe/list/execute/delete)
  • Discovering stacks and dumping resolved Sceptre configuration for planning/auditing

Not For

  • Production environments that require strict approval gates for destructive operations without additional controls
  • Use cases that need a hosted HTTP API/SDK instead of a local MCP server process
  • Environments where agents should not be allowed to execute AWS operations (create/update/delete/execute change sets)

Interface

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

Authentication

Methods: AWS credential chain via environment variables (e.g., AWS_PROFILE, AWS_DEFAULT_REGION) and standard AWS auth mechanisms
OAuth: No Scopes: No

Authentication is delegated to AWS credentials resolution (standard AWS credential chain) rather than an MCP-layer auth/authorization mechanism in the provided README.

Pricing

Free tier: No
Requires CC: No

No pricing details provided; as a Python package, cost is primarily AWS API usage/CloudFormation operations plus any agent host runtime.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Destructive actions are available (delete_stack, delete_change_set, execute_change_set) and may be triggered by the agent unless you enforce approval/guardrails in the MCP client/agent workflow.
  • Many operations depend on local Sceptre project structure (config/ and templates/ dirs) and correct stack_path values relative to config/.
  • AWS operations may take time asynchronously; agent/tool workflows must account for eventual consistency and stack transitions (e.g., waiting for completion is not described).
  • AWS permissions are enforced by IAM; mis-scoped credentials will cause failures that the agent may need to interpret.

Alternatives

Full Evaluation Report

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