Which integrations are available for this server?

Provides deployment support for hosting the MCP server on AWS Lambda, with serverless deployment capabilities. Integrates with Practera's GraphQL API to allow querying learning data including projects, assessments, milestones, activities, and tasks. Supports deployment using the Serverless Framework for deploying the MCP server to AWS Lambda.

How do I use Practera MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Practera MCP Server get details for project 456 to analyze its structure" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

en es ja ko zh

Practera MCP Server

by intersective

Overview Schema Related Servers Score Discussions

TypeScript

Remote

Practera MCP Server

An MCP (Model Context Protocol) server that gives AI agents direct access to Practera's GraphQL API and local project brief data. Connect Cursor, Claude Desktop, or any MCP client to author learning programs, manage assessments, submit work as a learner, conduct reviews, and run test suites across the Practera monorepo.

Why Practera MCP?

With this MCP server, an agent can:

Analyse and restructure existing projects for different audiences or grade levels
Generate assessment blueprints and create questions automatically
Import/export programs between institutions or LMS data formats
Submit assessments and manage review workflows
Search a library of 5400+ experiential learning project briefs by skill
Run test suites across all Practera repos directly from Cursor

Related MCP server: GraphQL MCP Toolkit

Quick Start (Cursor — local dev)

Clone this repo alongside the other Practera repos.
Install dependencies: npm install
Add .cursor/mcp.json to any Practera repo (see Cursor Configuration).
Reload the Cursor MCP panel — the practera server will appear.

No separate server process needed. Cursor spawns the MCP server via stdio automatically.

Transports

stdio (Cursor local — recommended)

Cursor spawns the server as a subprocess. No separate npm run dev needed.

# For manual testing / debugging
npm run dev:stdio

SSE (remote / shared)

An HTTP server with Server-Sent Events — use when multiple clients share one instance.

npm run dev        # → http://localhost:3000/sse

Connect an MCP client to http://localhost:3000/sse.

Cursor Configuration

Create .cursor/mcp.json in your repo (or add to ~/.cursor/mcp.json for all workspaces):

{
  "mcpServers": {
    "practera": {
      "command": "node",
      "args": [
        "/absolute/path/to/practera-mcp-server/dist/stdio.js"
      ],
      "env": {
        "PRACTERA_REGION": "local",
        "AUTH_EMAIL": "your@email.com",
        "GRAPHQL_URL": "http://localhost:8000",
        "WORKSPACE_ROOT": "/absolute/path/to/practera-workspace"
      }
    }
  }
}

Run npm run build in practera-mcp-server after any source changes to rebuild dist/stdio.js.

For production regions, omit AUTH_EMAIL/GRAPHQL_URL and pass apikey in each tool call instead.

Authentication

API Key (production)

Pass apikey in each tool call. The key is forwarded as the apikey HTTP header to the GraphQL API.

Omit apikey and set AUTH_EMAIL (or pass email per tool call). The server calls the devLogin GraphQL mutation to obtain a JWT automatically. Only works with region=local or region=stage.

Available Tools

Generic / Read-only

Tool	Description
`mcp_practera_get_project`	Full project tree: milestones, activities, tasks
`mcp_practera_get_assessment`	Assessment detail with questions and answer choices
`mcp_practera_search_project_briefs`	Search the local brief catalog by skill keyword

Author (admin/coordinator role required)

Tool	GraphQL Operation	Description
`create_experience`	`createExperience`	Create a new program inside an institution
`create_milestone`	`createMilestone`	Add a milestone to an experience
`create_activity`	`createActivity`	Add an activity to a milestone
`create_assessment`	`createAssessment`	Create an assessment on an activity
`add_question`	`createAssessmentQuestion`	Add a question to an assessment
`add_task_to_activity`	`addTaskToActivity`	Add a task (resource/link) to an activity
`enroll_user`	`enrollUser`	Enroll a user in an experience
`import_experience`	`importExperienceData`	Bulk-import experience content from a JSON export
`export_experience`	`exportExperience`	Export an experience structure as JSON

Student (learner)

Tool	GraphQL Operation	Description
`list_experiences`	`experiences`	List all experiences for the current user
`get_milestones`	`project.milestones`	Get milestones and activities for a project
`get_tasks`	`tasks(activityId:)`	Get tasks for an activity
`submit_assessment`	`submitAssessment`	Submit an assessment
`get_feedback`	`submission(id:)`	Get submission details including review feedback

Reviewer

Tool	GraphQL Operation	Description
`list_pending_reviews`	`reviews(status: "pending")`	List assessments awaiting review
`submit_review`	`submitReview`	Submit a completed review

Testing

Tool	Description
`run_tests`	Run a test suite across any Practera repo — shells out to npm/cargo/docker

`run_tests` parameters

Parameter	Required	Description
`repo`	Yes	Which repo: `core-graphql-api`, `login-api`, `app-v2`, `practera`, `practera-mcp-server`, `practera-devops-center`
`suite`	Yes	Which suite (see table below)
`pattern`	No	Test file/name filter (passed as `--testPathPattern` for Jest targets)
`workspaceRoot`	No	Absolute path to workspace root. Falls back to `WORKSPACE_ROOT` env var.

Available test suites

Repo	Suite	Command
`core-graphql-api`	`unit`	`npm test` (Jest, with coverage)
`core-graphql-api`	`integration`	`npm run test:integration`
`core-graphql-api`	`parity`	`npm run test:parity`
`login-api`	`unit`	`npx vitest run tests/unit`
`login-api`	`integration`	`npx vitest run tests/integration`
`login-api`	`full`	`npm run test:coverage`
`app-v2`	`unit`	`npm test -- --watch=false`
`practera`	`phpunit`	`docker exec practera-core ./vendor/bin/phpunit`
`practera-mcp-server`	`typecheck`	`npm run typecheck`
`practera-devops-center`	`cargo`	`cargo test`

MCP Resources

Resource URI	Description
`practera://project/current`	Current project data (GraphQL)
`practera://assessments/{assessmentId}`	Assessment by ID
`practera://briefs/{briefId}`	Project brief from local catalog

MCP Prompts

Prompt	Purpose
`project-analysis`	Analyse project structure and learning design quality
`assessment-analysis`	Evaluate assessment structure and question quality
`skill-brief-selection`	Find briefs matching a skill from the catalog
`complex-brief-finder`	Match briefs by skill, complexity, and timeframe

Environment Variables

Variable	Description
`PORT`	HTTP port (default 3000 dev / 80 production)
`NODE_ENV`	Environment (`development`, `production`)
`GRAPHQL_URL`	Override local GraphQL endpoint
`PRACTERA_REGION`	Default region: `local`, `stage`, `usa`, `aus`, `euk`
`AUTH_EMAIL`	Default email for devLogin (local/stage)
`WORKSPACE_ROOT`	Absolute path to workspace root — used by `run_tests`

GraphQL Regions

Region	Endpoint
`local`	`http://localhost:8000` (or `GRAPHQL_URL`)
`stage`	`https://core-graphql-api.p2-stage.practera.com/`
`usa`	`https://core-graphql-api.usa.practera.com/`
`aus`	`https://core-graphql-api.aus.practera.com/`
`euk`	`https://core-graphql-api.euk.practera.com/`

Build and Deploy

# Build
npm run build       # compiles TS + copies src/data → dist/

# Run SSE server (compiled)
npm start

# Run stdio (compiled — use in production Cursor config)
npm run start:stdio

AWS App Runner

The apprunner.yaml configures an App Runner service running the SSE server on port 80.

AWS Lambda (stale)

serverless.yml exists but the Lambda handler export is not currently wired up. Use App Runner for production deployment.

Roadmap

GraphQL read access (project, assessment)
Author CRUD tools (create experience, milestone, activity, assessment, questions, tasks, enroll)
Import/export experience JSON
Student tools (list, submit, feedback)
Reviewer tools (list pending, submit review)
Project brief search (5400+ briefs, skill-based)
stdio transport for Cursor integration
run_tests tool for cross-repo test execution
Metrics API (generate LLM-readable reports from calculateMetrics)
OAuth 2.1 (currently scaffolded, not active)
Thread auth context through MCP Resources
assign_reviewer, handle_review tools for reviewer workflow management
Media asset generation

License

MIT

This server cannot be installed

license - permissive license

quality - not tested

maintenance

How are these scores calculated?

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Appeared in Searches

A server for finding medical data

Latest Blog Posts

Lightport: Open-Sourcing Glama's AI Gateway
By punkpeye on April 27, 2026.
open source
OpenAI
Tool Definition Quality Score (TDQS)
By punkpeye on April 3, 2026.
mcp
The Hackers Who Tracked My Sleep Cycle
By punkpeye on March 26, 2026.
security

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/intersective/practera-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

Practera MCP Server

Why Practera MCP?

Quick Start (Cursor — local dev)

Transports

stdio (Cursor local — recommended)

SSE (remote / shared)

Cursor Configuration

Authentication

API Key (production)

devLogin (local/stage only)

Available Tools

Generic / Read-only

Author (admin/coordinator role required)

Student (learner)

Reviewer

Testing

run_tests parameters

Available test suites

MCP Resources

MCP Prompts

Environment Variables

GraphQL Regions

Build and Deploy

AWS App Runner

AWS Lambda (stale)

Roadmap

License

Resources

Looking for Admin?

Appeared in Searches

Latest Blog Posts

MCP directory API

`run_tests` parameters