practera-mcp-server CLAUDE.md

Project instructions for building and using an MCP server that connects AI agents to Practera's GraphQL API and local project briefs. GraphQL is a way for software to request data from an API.

In plain words
What is it for?
Use them when developing, testing, or extending the Practera MCP server, including its authoring, learning, reviewing, and testing workflows.
Why use it?
They give contributors a shared reference for the technology, project layout, setup, authentication, and local or remote connections.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/intersective/practera-mcp-server/claude-md
Clone the repo
git clone --depth 1 https://github.com/intersective/practera-mcp-server
Per session 2,349 This file is loaded in full into every session.
When invoked 2,349 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02349 $0.02349
Opus 5 $0.01175 $0.01175
Sonnet 5 $0.00470 $0.00470
Haiku 4.5 $0.00235 $0.00235

Measured yesterday against content hash 10a86fbfd568, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

practera-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Practera MCP Server

Overview

This is the Practera MCP Server — a Model Context Protocol server that gives AI agents (Cursor, Claude Desktop, etc.) direct access to Practera's GraphQL API and local project brief data. It bridges LLMs to the Practera platform for authoring, learning, reviewing, and testing workflows.

Technology Stack

  • Protocol: MCP (Model Context Protocol) via @modelcontextprotocol/sdk
  • Language: TypeScript (ESM modules, Node.js 18+)
  • Transports: SSE over Express (for remote/shared use) + stdio (for Cursor local spawn)
  • API: Practera GraphQL (core-graphql-api) via graphql-request
  • Auth: API key header OR devLogin mutation (local/stage only)
  • Schema validation: Zod

Project Structure

practera-mcp-server/
├── src/
│   ├── server.ts              # SSE transport — Express server, used for remote/shared
│   ├── stdio.ts               # stdio transport — Cursor spawns this directly
│   ├── routes.ts              # Express routes (/sse, /messages, /health, /docs)
│   ├── auth.ts                # PracteraAuth class (currently unused by tools)
│   │
│   ├── tools/
│   │   ├── index.ts           # Registers ALL tools — add new ones here
│   │   ├── get-project.ts     # mcp_practera_get_project
│   │   ├── get-assessment.ts  # mcp_practera_get_assessment
│   │   ├── search-project-briefs.ts  # mcp_practera_search_project_briefs
│   │   ├── author/            # Admin/coordinator tools (9)
│   │   ├── student/           # Learner tools (5)
│   │   ├── reviewer/          # Reviewer tools (2)
│   │   └── testing/           # Test runner tools (1)
│   │       └── run-tests.ts   # run_tests
│   │
│   ├── resources/
│   │   └── practera-resources.ts  # 3 MCP resources (project, assessments, briefs)
│   │
│   ├── prompts/
│   │   ├── index.ts
│   │   ├── project-analysis.ts
│   │   ├── assessment-analysis.ts
│   │   └── project-brief-selection.ts
│   │
│   ├── libs/
│   │   ├── graphql-client.ts       # PRACTERA_ENDPOINTS + createGraphQLClient
│   │   ├── auth-helper.ts          # createAuthenticatedClient (apikey OR devLogin)
│   │   ├── project-brief-service.ts
│   │   └── search-utils.ts
│   │
│   └── data/
│       ├── project_briefs.json     # ~669 KB brief catalog
│       └── skill-thesaurus.json
│
├── package.json
├── tsconfig.json
└── serverless.yml              # AWS Lambda config (partially stale)

Read the full file on GitHub · 268 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 268 lines · 2,349 tokens per session scan A 10a86fbfd568

Subscribe to this mod's changes

practera-mcp-server CLAUDE.md is an instructions file published in the GitHub repository intersective/practera-mcp-server (2 stars, last pushed 2d ago), licensed MIT. It adds 2,349 tokens to every session, about $0.0117 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.