ping-iga-mcp-server
MCP server exposing Ping IGA self-service governance operations (access requests, approvals, certifications, and manual tasks) to MCP clients, acting on behalf of the authenticated user.
README
ping-iga-mcp-server
MCP server exposing Ping IGA self-service governance operations — access requests, approvals, certifications, and manual tasks — to MCP clients, acting on behalf of the authenticated user.
Stack: JavaScript (ES modules) on Node 20 + Express. No TypeScript, no build step. Zod for runtime validation. MCP 2026-07-28 stateless transport.
Status: Phase 1 complete. Auth (introspection, throttle, rate-limit, RFC 9728 metadata) is wired. The
/mcpendpoint and governance tools are built out phase by phase per the implementation plan.
Requirements
- Node 20 LTS (
.nvmrcpins20)
Getting started
nvm use # Node 20
npm install
cp .env.example .env # adjust as needed
npm run dev # starts with --watch on http://localhost:3000
curl http://localhost:3000/healthz # -> {"status":"ok"}
Scripts
| Script | Purpose |
|---|---|
npm run dev |
Start with node --watch |
npm start |
Start once |
npm test |
Run vitest |
npm run lint |
ESLint |
npm run format |
Prettier write |
npm run inspector |
Launch MCP Inspector against the server |
401 → metadata → token walkthrough
With the server running (npm run dev) and .env populated, the full bootstrap flow can be traced manually:
Step 1 — hit a protected route without a token; receive a metadata pointer
curl -si http://localhost:3000/_authcheck
# HTTP/1.1 401
# WWW-Authenticate: Bearer resource_metadata="https://<PUBLIC_URL>/.well-known/oauth-protected-resource"
Step 2 — fetch the resource-server metadata document (no token needed)
curl -s http://localhost:3000/.well-known/oauth-protected-resource | jq .
# {
# "resource": "https://<PUBLIC_URL>",
# "authorization_servers": ["https://<AIC_BASE_URL>/am/oauth2"],
# "scopes_supported": ["iga:read", "iga:write", "iga:mutate"],
# "bearer_methods_supported": ["header"]
# }
Step 3 — obtain a token from the authorization server listed above
Use the authorization_servers[0] URL with your preferred OAuth 2.0 flow
(client credentials, authorization code, device flow — whichever your AIC
tenant and client registration support). The resulting access token must have
at least the iga:read scope.
Step 4 — call the probe route with the token
TOKEN=<access token from step 3>
curl -si http://localhost:3000/_authcheck \
-H "Authorization: Bearer $TOKEN"
# HTTP/1.1 200
# {"sub":"<user>","scopes":["iga:read",...]}
/_authcheck is a throwaway probe route (D1=a) that will be removed when
/mcp lands in Phase 2.
Deployment prerequisites
Beyond the skeleton, running the server against a tenant requires AIC configuration (a confidential client for token introspection, MCP tool-gating scopes, client registration, and verification of the tenant's token model). These are enumerated in the implementation plan and expanded in this README as each phase lands.
WebStorm
Shared run configurations for dev, test, and inspector are committed under
.run/. Open the project folder in WebStorm; set the project Node interpreter to
your Node 20 install. The .idea/ folder is intentionally not committed — WebStorm
generates it on first open.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.