# Oak National Academy MCP MCP Server > **Oak National Academy MCP MCP Server** is a hosted, multitenant Model Context Protocol (MCP) server run by **MewCP** (https://mewcp.com), giving AI agents managed access to Oak National Academy MCP. > > MewCP takes care of all MCP infrastructure for you — credential storage, OAuth flows, > token refresh, and production-grade auto-scaling — so your AI agents can connect to > third-party services and run freely without you managing any MCP server yourself. > > Server page: https://mewcp.com/mcp/oak-national-academy-mcp > MewCP docs: https://docs.mewcp.com > Full catalog: https://mewcp.com/llms.txt --- ## About Oak National Academy provides free, curriculum-aligned teaching and learning resources for UK schools. Search lessons by subject, key stage, and topic; retrieve lesson materials, quizzes, worksheets, and teaching resources across its national curriculum library. --- ## Details - Server ID: `oak-national-academy-mcp` - Version: 0.1.0 - Tools: 38 - Authentication: OAuth, managed by MewCP - Transport: http --- ## Access The gateway URL below serves your **entire MewCP toolset**, not this server on its own. Pasting a config snippet is not enough — Oak National Academy MCP has to be in the toolset first. In order: 1. Add Oak National Academy MCP to your toolset at https://mewcp.com/mcp/oak-national-academy-mcp 2. Connect your Oak National Academy MCP account (OAuth); MewCP stores the credential and attaches it to each call 3. Copy your MewCP API key from the dashboard (Developer) 4. Configure your client with the snippet for it below Once connected, an agent does **not** see this server's tools as top-level tools. It sees four meta-tools and reaches everything through them: - `search(query)` — find tools by keyword across the toolset - `get_schema(tools)` — full description and arguments for the tools you picked - `list_accounts(provider)` — only when one app has several connected accounts - `call_tool(server_maskedId, tool_name, args)` — execute So the list below is what `search` can return for this server, not a set of callable tool names on their own. --- ## Tools (38) Descriptions are truncated to 160 characters; call `get_schema` for the full text and the argument schema. Where a tool is annotated, its type is shown — treat `destructive` as irreversible. - `search` _(read)_ — Hybrid lexical and semantic search across lessons, units, threads and sequences, plus lexical typeahead suggestions (scoped) Required parameters: `scope`… - `fetch` _(read)_ — Fetch curriculum resource by canonical identifier. Use this when you need to: - Get lesson details (learning objectives, keywords, misconceptions) - Get unit… - `get-curriculum-model` _(read)_ — Returns a complete orientation to Oak National Academy's curriculum: domain model (key stages, subjects, entity hierarchy, property graph) AND tool usage… - `get-thread-progressions` _(read)_ — Returns how an Oak curriculum thread progresses across year groups, for the anchor you name. Threads connect units into conceptual progressions across years… - `get-prior-knowledge-graph` _(read)_ — Returns the stated prior knowledge for the anchor units you name. "Prior knowledge of unit X" means what Oak records on the unit itself: the flat list of… - `get-misconception-graph` _(read)_ — Returns the misconceptions (with teacher responses) addressed by the anchor you name. Misconceptions are extracted per lesson from the Oak curriculum and… - `get-keyword-graph` _(read)_ — Returns the key vocabulary for one teaching context: a bounded, frequency-ranked page of curriculum keywords, each decorated with its in-scope placing lessons.… - `browse-curriculum` _(read)_ — Browse what's available in Oak's curriculum without searching. Returns structured facet data showing subjects, key stages, sequences (programmes), units, and… - `explore-topic` _(read)_ — Explore a topic across the entire Oak curriculum in one call. Searches lessons, units, AND learning threads in parallel for a topic, returning a unified topic… - `download-asset` _(read)_ — Generate a short-lived, secure download link for a lesson asset. Returns a clickable URL valid for 5 minutes that downloads the asset directly in the user's… - `get-key-stages` _(read)_ — All key stages Use when you need the master list of key stages. Returns every key stage with its title and slug. Not for: key stages restricted to a subject… - `get-key-stages-subject-assets` _(read)_ — Downloadable assets by key stage and subject Use when you want every downloadable asset for a key stage + subject, without programme structure or unit sequence… - `get-key-stages-subject-lessons` _(read)_ — List lessons in a key stage and subject Use when you want every published lesson in a key stage + subject, grouped by unit, without programme structure or unit… - `get-key-stages-subject-questions` _(read)_ — Quiz questions by key stage and subject Use when you want every quiz question for a key stage + subject, without programme structure or unit sequence order.… - `get-key-stages-subject-units` _(read)_ — Units in a key stage and subject Use when you want a flat list of every unit with published lessons in a key stage + subject, without programme structure or… - `get-keywords` _(read)_ — Keywords by subject and key stage Use when you want the vocabulary for a key stage, subject, unit, lesson, or phase — e.g. to build a glossary or attach… - `get-lessons-assets` _(read)_ — Downloadable assets for a lesson Use when you have a lesson slug and need the list of what's downloadable. Returns every available asset type with a signed… - `get-lessons-quiz` _(read)_ — Quiz questions for a lesson Use when you have a lesson slug and need its starter and exit quiz questions with correct answers marked. Returns two arrays,… - `get-lessons-summary` _(read)_ — Lesson summary by slug Use when you have a lesson slug and need its full metadata: title, key stage, subject, unit, keywords, key learning points,… - `get-lessons-transcript` _(read)_ — Lesson video transcript Use when you have a lesson slug and need the video transcript — for accessibility, captioning, or text analysis. Returns the transcript… - `get-programmes` _(read)_ — Get a programme by slug Use when you need to get the metadata of one programme. Get programme slugs from GET /subjects/{subject}/programmes. Returns the… - `get-programmes-assets` _(read)_ — Downloadable assets in a programme Use when you need every downloadable asset for a single programme (year group) within a subject. Returns assets grouped by… - `get-programmes-questions` _(read)_ — Quiz questions in a programme Use when you want every quiz question in a single programme (year group) within a subject. Get programme slugs from GET… - `get-programmes-units` _(read)_ — Units in a programme Use when you need the unit sequence for one programme — units as an ordered arrangement designed to build knowledge progressively. Get… - `get-rate-limit` _(read)_ — Current rate-limit status Use when you need rate-limit status as a JSON body — e.g. for a quota indicator. Returns limit, remaining, and reset. The same data… - `get-sequences` _(read)_ — Sequencing information for a given sequence slug Use when you have a sequence slug and need the sequence-level summary. A sequence is a subject's curriculum… - `get-sequences-assets` _(read)_ — Downloadable assets in a sequence Use when you need every downloadable asset across a whole sequence — all programmes combined. Returns assets grouped by… - `get-sequences-questions` _(read)_ — Quiz questions across a sequence Use when you want every quiz question across a whole sequence — all programmes combined. Returns questions grouped by lesson… - `get-sequences-units` _(read)_ — Units in a curriculum sequence Use when you want every unit across a whole sequence — all programmes combined, in unit sequence order. Returns units grouped by… - `get-subject-detail` _(read)_ — Single subject with sequences, key stages, and years Use when you have a subject slug. Returns subjectTitle, subjectSlug, sequenceSlugs, keyStages, and years.… - `get-subjects` _(read)_ — All subjects Use when you need every subject in one call — the entry point for a subject picker or for crawling the whole curriculum. Returns subjects… - `get-subjects-key-stages` _(read)_ — Key stages for a subject Use when you only need the key stages where this subject is available. Returns key-stage titles and slugs. Not for: every key stage… - `get-subjects-programmes` _(read)_ — Get all programmes for a subject slug Use when you need to discover the programmes within a subject — to get a programme's slug for use with GET… - `get-subjects-years` _(read)_ — Year groups for a subject Use when you only need the year groups where this subject is available. Returns an array of year numbers, derived from the subject's… - `get-threads` _(read)_ — All threads Use when you want the catalogue of every thread. A thread is an attribute on a unit that groups units across the curriculum to build a common body… - `get-threads-units` _(read)_ — Units in a thread Use when you want every unit in a thread. A thread is an attribute on a unit that groups units across the curriculum to build a common body… - `get-units-summary` _(read)_ — Unit summary by slug Use when you have a unit slug and need the unit summary: title, description, key stage, subject, year, threads, prior-knowledge… - `oak-under-the-hood` _(read)_ — Use when a user asks to understand the Oak project, effort, or ecosystem — this repository, how Oak builds and delivers its curriculum, the project's purpose… --- ## Connect Gateway URL: https://gateway.mewcp.com/personal/mcp Every request carries one header: Authorization: Bearer Replace `API_KEY` with your own key from the dashboard (Developer). ## Apps ### Claude Desktop Mac & Windows app - macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` - Windows: `%APPDATA%\Claude\claude_desktop_config.json` ```json { "mcpServers": { "mewcp": { "command": "npx", "args": [ "-y", "mcp-remote@latest", "https://gateway.mewcp.com/personal/mcp", "--header", "Authorization:${AUTH_HEADER}" ], "env": { "AUTH_HEADER": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open Claude Desktop → Settings → Developer → "Edit Config" 2. Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one) 3. Save the file, then quit Claude Desktop completely and reopen it 4. Start a new conversation — your tool will be available ### VS Code Copilot / Cline - Command Palette → "MCP: Open User Configuration" (opens mcp.json). For one project only, use .vscode/mcp.json instead. ```json { "mcp.servers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have a "servers" section in your mcp.json? Just add the server entry inside it. 1. Open VS Code → Command Palette (Cmd+Shift+P / Ctrl+Shift+P) 2. Run "MCP: Open User Configuration" to open your mcp.json 3. Paste the snippet and save 4. Start the server when prompted (or from the MCP servers view) and use it in Copilot Chat ### Cursor AI-first editor - macOS: `~/.cursor/mcp.json` - Windows: `%USERPROFILE%\.cursor\mcp.json` ```json { "mcpServers": { "mewcp": { "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your mcp.json? Just add the server entry inside it. 1. Open Cursor → Settings → Cursor Settings → MCP 2. Click "Add new global MCP server" 3. Paste the snippet and save 4. Restart Cursor ### Codex OpenAI's CLI agent - Add the snippet to your Codex MCP config or your standard MCP config file for the CLI tool you use. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Codex generally reads a standard MCP server block, so you can add this alongside your other configured servers. 1. Open your Codex MCP config or project-level config file 2. Paste the MewCP server block inside the config JSON/TOML structure your tool expects 3. Save the file and restart Codex 4. Verify the tool is available inside a fresh session ### Claude Code Anthropic's CLI agent - ~/.claude.json (user scope) or .mcp.json in your project root — create it if it doesn't exist. Or skip the file and use the CLI command below. ```json { "mcpServers": { "mewcp": { "type": "http", "url": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. 1. Open ~/.claude.json (or .mcp.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file and start (or restart) Claude Code 4. Or skip the file entirely and run the CLI command below instead ### OpenCode Open-source terminal agent - ~/.config/opencode/opencode.json (global) or opencode.json in your project root — create it if it doesn't exist. ```json { "$schema": "https://opencode.ai/config.json", "mcp": { "mewcp": { "type": "remote", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcp" section in your opencode.json? Just add the server entry inside it. 1. Open ~/.config/opencode/opencode.json (or opencode.json in your project root) in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and start (or restart) OpenCode ### OpenClaw Self-hosted agent gateway - ~/.openclaw/openclaw.json — create it if it doesn't exist. ```json { "mcp": { "servers": { "mewcp": { "transport": "streamable-http", "url": "https://gateway.mewcp.com/personal/mcp", "enabled": true, "headers": { "Authorization": "Bearer API_KEY" } } } } } ``` Already have an "mcp" section in your openclaw.json? Just add the server entry inside "servers". 1. Open ~/.openclaw/openclaw.json in a text editor 2. Paste the snippet inside the outer { } (merge with your existing "mcp" section if you have one) 3. Save the file and restart OpenClaw ### Antigravity Google's agentic IDE - ~/.gemini/config/mcp_config.json (global) or .agents/mcp_config.json (workspace-local) — create it if it doesn't exist. ```json { "mcpServers": { "mewcp": { "serverUrl": "https://gateway.mewcp.com/personal/mcp", "headers": { "Authorization": "Bearer API_KEY" } } } } ``` Already have an "mcpServers" section in your config? Just add the server entry inside it. Remote servers must use the "serverUrl" field — the legacy "url"/"httpUrl" fields aren't supported. 1. In the editor's agent side panel, click "…" → "MCP Servers" → "Manage MCP Servers" → "View raw config" (Antigravity CLI: type /mcp instead to open the Interactive MCP Manager) 2. Paste the snippet inside the outer { } (merge with your existing "mcpServers" section if you have one) 3. Save the file — the server connects automatically ### Hermes Nous Research's CLI agent - config.yaml in your Hermes config directory (~/.hermes) — add this under a top-level "mcp_servers:" key. ```yaml mcp_servers: mewcp: url: "https://gateway.mewcp.com/personal/mcp" headers: Authorization: "Bearer API_KEY" ``` Already have an "mcp_servers" section in your config.yaml? Just add the server entry inside it. 1. Open config.yaml in your Hermes config directory 2. Paste the snippet under the top-level "mcp_servers:" key (merge with existing entries if you have any) 3. Save the file, then run /reload-mcp in Hermes (or start a fresh session) 4. Ask Hermes "Tell me which MCP-backed tools are available right now" to confirm it connected ### DeepSeek Harness DeepSeek's agent harness - cordis.yml in your DSH project — or the patch file you mount plugins from. ```yaml - id: mcp-mewcp name: '@deepseek-ai/dsh-mcp-client' config: serverName: mewcp transport: streamable-http url: https://gateway.mewcp.com/personal/mcp headers: Authorization: "Bearer API_KEY" ``` One plugin instance = one MCP server. Add this entry to your plugin list; don't nest it inside another entry. 1. Open cordis.yml (or your patch file) in your DSH project 2. Paste the entry into your plugin list, keeping the leading dash and indentation 3. Restart DSH (or let HMR reload) — tools register as mcp__mewcp__ 4. Verify with: dsh web --dump-config | grep -A3 mcp ## SDKs ### Python fastmcp client ```python import asyncio from fastmcp import Client from fastmcp.client.transports import StreamableHttpTransport SERVER_URL = "https://gateway.mewcp.com/personal/mcp" API_KEY = "API_KEY" transport = StreamableHttpTransport( url=SERVER_URL, headers={ "Authorization": f"Bearer {API_KEY}", } ) async def main(): client = Client(transport) async with client: tools = await client.list_tools() print(tools) asyncio.run(main()) ``` 1. Install fastmcp: pip install fastmcp 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run your script ### TypeScript MCP SDK ```typescript import { Client } from "@modelcontextprotocol/sdk/client/index.js"; import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"; const SERVER_URL = "https://gateway.mewcp.com/personal/mcp"; const API_KEY = "API_KEY"; const transport = new StreamableHTTPClientTransport(new URL(SERVER_URL), { requestInit: { headers: { Authorization: `Bearer ${API_KEY}`, }, }, }); const client = new Client({ name: "mewcp-client", version: "1.0.0" }); await client.connect(transport); const tools = await client.listTools(); console.log(tools.tools.map((t) => t.name)); ``` 1. Install: npm install @modelcontextprotocol/sdk 2. Copy the snippet into your project 3. Replace API_KEY with your key from the dashboard 4. Run with Node 18+ as an ES module (e.g. npx tsx script.ts)