# Sciple Platform [Health: Active]

**Category:** ☁️ Cloud Platforms  
**Repository:** https://github.com/navaganeshr/sciple-mcp  
**GitHub Stars:** 0  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/sciple-platform

## Description
MCP server for the Sciple platform — environments, services, dashboards, runbooks, tickets.

## Tools
Capabilities this server exposes over MCP:

- **list_aws_accounts** — List AWS accounts connected to the tenant (account_id, name, AWS number, regions, payer flag)
- **list_cloud_resource_types** — List synced resource types + row counts for one AWS service in an account
- **query_cloud_resources** — Query cached rows from any synced AWS resource table (paginated, region filter)
- **list_ec2_instances** — Summarize EC2 instances for one account or across all (state/type/id/name/ip)
- **list_environments** — List all environments in the tenant (id, name, slug, group, default flag)
- **create_environment** — Create an environment with optional group assignment and default flag
- **update_environment** — Update an environment's name, description, group, or sort order
- **delete_environment** — Delete an environment by id (irreversible)
- **list_environment_groups** — List environment groups (id, name, slug, AWS account binding)
- **create_environment_group** — Create an environment group with optional AWS account binding
- **list_services** — List all services in the tenant catalog (id, name, slug)
- **create_service** — Create a service in the catalog with kind, language, SCM provider, and repository
- **update_service** — Update a service's metadata, lifecycle, owner, tags, links, or environment associations
- **delete_service** — Delete a service from the catalog by id (irreversible)
- **list_dashboards** — List all observability dashboards in the tenant (id, name, panel count)
- **get_dashboard** — Get a dashboard's name, description, and panel list
- **create_dashboard** — Create a new dashboard with optional description
- **update_dashboard** — Replace a dashboard's name and description (full PUT; name required)
- **delete_dashboard** — Delete a dashboard and all its panels (irreversible)
- **add_panel** — Add a panel to a dashboard. Supports **5 shapes** end-to-end (pick one): **PromQL** (`promql`), **CloudWatch Metrics** (`cw_namespace`+`cw_metric_name`+`cw_stat` + optional `cw_dimensions`/`cw_period`), **ElasticSearch/OpenSearch logs** (`es_index` + optional `kql_filter`), **CloudWatch Logs** (`cw…
- **delete_panel** — Delete a panel from a dashboard (irreversible)
- **list_runbooks** — List all runbooks in the tenant with lifecycle status and cell count
- **get_runbook** — Get a runbook with its cells (name, status, content preview per cell)
- **create_runbook** — Create a new runbook in draft status
- **add_cell** — Add a markdown / shell / http cell to a runbook with optional k8s/ecs/ec2 target
- **update_cell** — Update a cell's content or execution target
- **delete_cell** — Remove a cell from a runbook
- **reorder_cells** — Set the execution order of all cells in a runbook
- **promote_runbook** — Advance the runbook lifecycle: draft → reviewed → standard
- **deprecate_runbook** — Mark a runbook as deprecated
- **list_projects** — List all projects in the tenant (id, key, name, classification)
- **get_project** — Get a single project's details (owner, description, classification)
- **create_project** — Create a new project (name + uppercase key like "PLAT", optional classification + owner)
- **list_project_members** — List the user_ids and roles of a project's members (use to find an assignee)
- **list_project_issue_types** — List a project's issue types (required before `create_project_ticket`)
- **list_tickets** — List tickets across the tenant with optional filters (service, assignee, status, priority, type, tag, full-text `q`)
- **get_ticket** — Get a single ticket's full details + activity counts (by internal id)
- **create_ticket** — Create a **service-level** ticket (not bound to a project) — `tickets.manage
- **update_ticket** — PATCH a ticket — change status, priority, assignee, dates, tags, parent
- **comment_on_ticket** — Add a comment to a ticket — `tickets.comment
- **link_tickets** — Relate two tickets (`blocks` / `relates_to` / `duplicates`)
- **list_project_tickets** — List tickets in a project
- **get_project_ticket** — Get a project ticket by sequence number (the NNN in KEY-NNN)
- **create_project_ticket** — Create a ticket inside a project** — returns a "KEY-NNN" display id. Recommended for most ticket creation. Supports `custom_fields` (JSON string of `{field_id: value}`). Requires `tickets.create`.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):

```json
"mcpServers": {
  "sciple-platform": {
    "command": "uvx",
    "args": ["sciple-mcp"],
    "env": {
      "SCIPLE_PLATFORM_URL": ""
    }
  }
}
```

**Requires environment variables:** `SCIPLE_PLATFORM_URL` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What Sciple Platform MCP server does

The Sciple Platform MCP server exposes Sciple tenant operations as MCP tools for AI-assisted infrastructure and operations work. It can create, inspect, update, and delete environments, environment groups, services, dashboards, dashboard panels, and runbooks. Runbook tools also support cells, ordering, lifecycle promotion, and deprecation.

Cloud inventory tools provide read-only access to AWS data already synchronized into Sciple. They list connected accounts, show available resource types and row counts, query cached resource tables, and summarize EC2 instances across one or more accounts. The generic resource query supports the synced service families documented by the project, including EC2, RDS, S3, VPC, IAM, Lambda, EKS, ECS, EBS, ElastiCache, Route 53, CloudFront, DynamoDB, ECR, EFS, and Code services.

## How it works

The Sciple Platform MCP server can connect through Sciple’s hosted `/mcp` endpoint using Streamable HTTP, or run locally over stdio. A legacy local Streamable HTTP mode is also available for deployments where the MCP client cannot reach the hosted endpoint. The server communicates with the Sciple REST API rather than calling AWS directly.

Authentication uses OAuth 2.0 with PKCE. Running `sciple-mcp login --platform-url https://your.sciple.cloud` opens a browser consent flow and saves access and refresh tokens in `~/.sciple/credentials.json`. The server reads that credential and refreshes it when needed. The project states that personal access token support was removed from version 0.7.0 onward.

## Setup and configuration

Install the command through PyPI with `uvx sciple-mcp`, or use the MCP Registry identifier `io.github.navaganeshr/sciple-mcp`. Claude Desktop can also install the released desktop extension. After logging in, Claude Code can be configured with the hosted HTTP endpoint and a bearer token from `sciple-mcp print-token`.

For stdio configuration, set `SCIPLE_PLATFORM_URL` to the platform URL when multiple platforms are cached. The value is optional when the saved credentials identify the intended platform. The same OAuth credential is used for hosted HTTP, stdio, and the legacy local HTTP mode.

## Tools and capabilities

- Inspect connected AWS accounts and cached cloud resources, with pagination and region filtering.
- Create and maintain environments and environment groups, including AWS account bindings.
- Maintain service catalog records with ownership, lifecycle, tags, links, and environment associations.
- Create dashboards and panels using PromQL, CloudWatch metrics, OpenSearch or Elasticsearch logs, CloudWatch Logs, or text.
- Build runbooks from markdown, shell, and HTTP cells, optionally targeting Kubernetes, ECS, or EC2 resources.
- Promote runbooks from draft to reviewed to standard, or mark them deprecated.

## Limitations and notes

Cloud inventory is limited to the last AWS synchronization in Sciple; these tools do not query AWS live and do not mutate cloud resources. Cloud inventory access requires a credential containing the `cloud.view` permission.

Several operations are destructive, including deleting environments, services, dashboards, panels, and runbook cells. Dashboard updates replace the dashboard name and description as a full PUT operation, and the name is required. Dashboard metric and log panels require a `datasource_id`.

The Sciple Platform MCP server uses OAuth credentials rather than the older `SCIPLE_API_TOKEN` path. Local credentials are stored in a file with restrictive permissions, and the CLI provides commands to print the current token, log out, or revoke the refresh token.

_Full upstream README: https://allmcps.com/mcp/sciple-platform/readme_