Sciple Platform

io.github.navaganeshrPublished by GitHub account navaganeshrv0.8.0Updated Oct 24, 2026

Sciple platform MCP: services, dashboards, runbooks, tickets, environments, AWS cloud inventory.

VerifiedSTDIODesktop onlyProductivity & WorkflowCloud & InfrastructureSecurity & Monitoring

Overview

AI-generated overview

Sciple Platform MCP lets an assistant read and manage Sciple platform content — environments, services, dashboards, runbooks, projects, tickets — plus cached…

What you can do
  • Browse cached AWS inventory: list accounts, synced resource types, EC2 instances, and query any synced resource table
  • List, create, update and delete environments and environment groups
  • Maintain the service catalog: list, create, update and delete services
  • Build observability dashboards and add or delete panels (PromQL, CloudWatch metrics/logs, ElasticSearch logs, text)
  • Author runbooks with markdown, shell or http cells, reorder them and advance lifecycle status
  • Manage projects and tickets: list, create, update, comment, link, and read project members and issue types
When to use it
Useful for engineers who already run a Sciple platform tenant and want to bootstrap tenant structure, maintain the service catalog, build dashboards, write runbooks, or triage tickets from inside an AI coding session.
Requirements
Runs locally as a PyPI package via uvx (needs uv). Requires a Sciple platform tenant and OAuth 2.0 PKCE login through the sciple-mcp login command, which stores tokens in a local credentials file; the optional SCIPLE_PLATFORM_URL variable selects a platform when several are cached. Network access to the platform is needed.
Before you install
Many tools write or delete: environments, services, dashboards and panels, runbook cells, projects and tickets can be created, changed or irreversibly deleted. Access is limited to the logged-in user's role and permissions. OAuth tokens are cached on disk and can be revoked from the dashboard. Cloud inventory tools only read the platform's last AWS sync and never call AWS directly.

Installation

In SourceWeft

  1. Open Sciple Platform in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Sciple Platform MCP Server

MCP server that lets a local Claude populate and manage Sciple platform content — environments, services, observability dashboards, runbooks, projects, and tickets — via the Sciple REST API. Engineers use it to bootstrap tenant structure, maintain the service catalog, build dashboards, author runbooks, and triage tickets without leaving their AI coding session.

Distribution channels:

ChannelUse it fromHow to install
PyPIClaude Code, custom scripts, CIuvx sciple-mcp
MCP RegistryAnywhere an MCP client speaks the registry protocolResolves automatically by io.github.navaganeshr/sciple-mcp
Desktop Extension (.dxt)Claude DesktopDouble-click sciple-mcp-<version>.dxt from the GitHub release

Install

bash
# Install uv (one-time, only if you don't have it)curl -LsSf https://astral.sh/uv/install.sh | sh

uvx sciple-mcp resolves the latest version from PyPI and caches it.

Authentication — OAuth only (v0.7.0+)

sciple-mcp authenticates against the Sciple platform via OAuth 2.0 with PKCE. The CLI is a credential helper: log in once via the browser, the access + refresh tokens land in ~/.sciple/credentials.json (mode 0600), and the MCP server reads + auto-refreshes from there.

PAT support was removed in v0.7.0. Earlier versions accepted SCIPLE_API_TOKEN=sciple_pat_… in the env (stdio mode). That path is gone — the only credential the MCP server understands is the OAuth JWT minted by sciple-mcp login. Personal Access Tokens on the platform are unchanged and still work for scripts / CI / direct REST calls against /api/v1/*.

1. Log in (one-time per platform)

bash
sciple-mcp login --platform-url https://your.sciple.cloud

Opens your browser, you click Approve on the consent page, the CLI captures the callback and writes the credential. No --tenant-id / --scope needed — the JWT inherits your full role on whichever tenant the dashboard is currently showing.

2. Wire into Claude

The Sciple platform now hosts /mcp itself, so the preferred shape is Streamable HTTP straight to the platform:

bash
# Claude Code (HTTP transport — preferred)claude mcp add-json sciple-platform "$(cat <<EOF{  "type": "http",  "url": "https://your.sciple.cloud/mcp",  "headers": { "Authorization": "Bearer $(sciple-mcp print-token)" }}EOF)"

For Claude Desktop builds that only speak stdio MCP today, use the stdio mode — same credential, no PAT:

json
{  "mcpServers": {    "sciple-platform": {      "command": "uvx",      "args": ["sciple-mcp"],      "env": {        "SCIPLE_PLATFORM_URL": "https://your.sciple.cloud"      }    }  }}

SCIPLE_PLATFORM_URL is optional — only needed if you have multiple platforms cached. Stdio mode reads ~/.sciple/credentials.json directly.

3. Manage / rotate

bash
sciple-mcp print-token            # current valid JWT (auto-refreshes near expiry)sciple-mcp logout                 # forget local cachesciple-mcp logout --revoke        # also revoke the refresh token server-side

Revoke any time from Profile → Connected apps on the dashboard.

Legacy: sciple-mcp serve (local HTTP server)

For air-gapped deployments where the client can't reach the platform's hosted /mcp endpoint, sciple-mcp serve still ships a local Streamable HTTP MCP server that re-validates OAuth JWTs against the platform's JWKS. Same credential, same flow — only the network shape differs. See --help for serve / install / uninstall.

Tools

Cloud inventory (read-only)

ToolDescription
list_aws_accountsList AWS accounts connected to the tenant (account_id, name, AWS number, regions, payer flag)
list_cloud_resource_typesList synced resource types + row counts for one AWS service in an account
query_cloud_resourcesQuery cached rows from any synced AWS resource table (paginated, region filter)
list_ec2_instancesSummarize EC2 instances for one account or across all (state/type/id/name/ip)

These read the platform's last AWS sync — they never call AWS directly and never mutate anything. They require the credential to hold cloud.view.

Example — explore your AWS estate

Ask Claude in plain language; it chains the tools for you:

You: What EC2 instances are running across all our AWS accounts?

Claude calls list_ec2_instances (no account_id → sweeps every connected account) and summarizes:

45 EC2 instances across 4 accounts.
### Production (account_id=LlDZzq) — 13 instances (12 running, 1 shutting-down)  [running] m5.2xlarge i-047323d5f680e822f portal-apps-ondemand (10.40.2.11)  [running] t2.micro   i-00fcaed2de8131fd1 prod-nat-instance-1a (10.40.0.9)  ...

To drill into a single account, or a different resource type, Claude discovers what's synced first, then queries it:

You: Show the RDS databases in the Production account.

1. list_aws_accounts                  → Production has account_id "LlDZzq"2. list_cloud_resource_types(         → aws_rds_db_instance: 4     account_id="LlDZzq", service="rds")3. query_cloud_resources(             → 4 rows (engine, class, status, endpoint…)     account_id="LlDZzq", service="rds",     resource_type="aws_rds_db_instance")

query_cloud_resources is the generic accessor for any of the 19 supported services (ec2, rds, s3, vpc, iam, lambda, eks, ecs, ebs, elasticache, route53, cloudfront, dynamodb, ecr, efs, and the code* suite) — pass an unknown service and the tool returns the valid set. Use region to filter ("global" for S3) and page / page_size (≤500) to walk large tables.

Environments

ToolDescription
list_environmentsList all environments in the tenant (id, name, slug, group, default flag)
create_environmentCreate an environment with optional group assignment and default flag
update_environmentUpdate an environment's name, description, group, or sort order
delete_environmentDelete an environment by id (irreversible)
list_environment_groupsList environment groups (id, name, slug, AWS account binding)
create_environment_groupCreate an environment group with optional AWS account binding

Services

ToolDescription
list_servicesList all services in the tenant catalog (id, name, slug)
create_serviceCreate a service in the catalog with kind, language, SCM provider, and repository
update_serviceUpdate a service's metadata, lifecycle, owner, tags, links, or environment associations
delete_serviceDelete a service from the catalog by id (irreversible)

Observability

ToolDescription
list_dashboardsList all observability dashboards in the tenant (id, name, panel count)
get_dashboardGet a dashboard's name, description, and panel list
create_dashboardCreate a new dashboard with optional description
update_dashboardReplace a dashboard's name and description (full PUT; name required)
delete_dashboardDelete a dashboard and all its panels (irreversible)
add_panelAdd 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_log_group + optional cw_filter_pattern), or Text (text_content + optional text_background). Log panels also accept display options (log_columns, log_limit, log_wrap_message, log_expandable_rows, log_highlight_by_severity, log_live_tail). Always pass datasource_id for metric + log panels.
delete_panelDelete a panel from a dashboard (irreversible)

Runbooks

ToolDescription
list_runbooksList all runbooks in the tenant with lifecycle status and cell count
get_runbookGet a runbook with its cells (name, status, content preview per cell)
create_runbookCreate a new runbook in draft status
add_cellAdd a markdown / shell / http cell to a runbook with optional k8s/ecs/ec2 target
update_cellUpdate a cell's content or execution target
delete_cellRemove a cell from a runbook
reorder_cellsSet the execution order of all cells in a runbook
promote_runbookAdvance the runbook lifecycle: draft → reviewed → standard
deprecate_runbookMark a runbook as deprecated

Runbook lifecycle: draft → reviewed → standard. Deprecation is one-way from any state.

Projects

ToolDescription
list_projectsList all projects in the tenant (id, key, name, classification)
get_projectGet a single project's details (owner, description, classification)
create_projectCreate a new project (name + uppercase key like "PLAT", optional classification + owner)
list_project_membersList the user_ids and roles of a project's members (use to find an assignee)
list_project_issue_typesList a project's issue types (required before create_project_ticket)

Tickets

ToolDescription
list_ticketsList tickets across the tenant with optional filters (service, assignee, status, priority, type, tag, full-text q)
get_ticketGet a single ticket's full details + activity counts (by internal id)
create_ticketCreate a service-level ticket (not bound to a project) — tickets.manage
update_ticketPATCH a ticket — change status, priority, assignee, dates, tags, parent
comment_on_ticketAdd a comment to a ticket — tickets.comment
link_ticketsRelate two tickets (blocks / relates_to / duplicates)
list_project_ticketsList tickets in a project
get_project_ticketGet a project ticket by sequence number (the NNN in KEY-NNN)
create_project_ticketCreate 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.

Ticket statuses: open → in_progress → done (or cancelled from any state). Priorities: low / medium / high / urgent. Severities (optional): minor / major / critical. Types: epic / story / task / subtask / bug.

Security

The server can only do what the PAT's scope allows. Attempts to write without the relevant manage permission return a 403 from the API and are surfaced as an error in Claude's response. The PAT is revocable at any time from Profile → Access tokens in the Sciple dashboard — revoking it immediately cuts off the server's access without any config change.

Development

To work on the server itself:

bash
git clone https://github.com/navaganeshr/sciple-mcpcd sciple-mcpuv sync --all-groupsuv run python -m pytest -q

Releases are tag-driven via a GitHub Actions workflow using PyPI Trusted Publishing (OIDC). To cut a release:

  1. Bump version in pyproject.toml.
  2. Commit, then git tag vX.Y.Z && git push origin vX.Y.Z.
  3. Approve the pypi environment deployment in the Actions UI.

Source: README.md at commit 70690b2

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.8.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.