What is the DeepMark remote MCP server?
The DeepMark remote MCP server is a hosted Model Context Protocol endpoint at https://api.getdeepmark.com/mcp, so AI assistants can connect to it without installing or running anything locally.

Basic information
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
https://api.getdeepmark.com/mcpclaude mcp add deepmark --transport http https://api.getdeepmark.com/mcpCreate a complete, markable exam paper from pasted text. Provide the question paper text (required) and, if the teacher has one, the mark scheme text — DeepMark extracts it. Omit the mark scheme to have DeepMark generate schemes (lower quality, but the paper is still markable). Send RAW text: do not pre-structure it into questions or author a mark scheme yourself. Extraction runs asynchronously — this returns a job_id. Poll ingestion_get until it reaches `awaiting_confirmation`, then call paper_confirm to mint the paper. RATE LIMITED: up to 3 papers per 24 hours per account (marking existing papers is unaffected).
Mint the exam paper from a job parked at awaiting_confirmation (created via paper_create). Materialises the ExamPaper, questions, and mark schemes from the extraction draft, synchronously. Optionally override the detected identity (title/subject/board/year); omit to use what extraction detected. Idempotent — confirming an already-committed job returns its paper. Returns the exam_paper_id.
Read the current state of an ingestion job (paper creation or document ingestion). Returns the status plus a derived `awaiting` gate ('triage' | 'confirmation' | null), whether it is terminal, and the next action to take. Poll this after starting a job: a paper-creation job parks at `awaiting_confirmation` (then call paper_confirm) — it does NOT run to `complete` on its own. Stop polling on a terminal status (complete | failed | cancelled) or when an action is required.
Mark a student's typed answers against an existing exam paper. Provide the exam_paper_id and per-question answers keyed by question_number. DeepMark creates a submission and grades it through its canonical marker (per mark point / level descriptor) — results stream into the teacher's editor live. Grading is asynchronous: this returns a submission_id; poll submission_get for the per-question grades.
Read the grading state and per-question marks for a submission (created via submission_mark). Returns each question's marking_status, awarded/max marks, level, and feedback, plus an overall status ('grading' until every question is marked). Poll after submission_mark.
Retrieve the marking result for a specific answer by its ID
List all exam papers with optional filtering
Retrieve a specific exam paper by its ID with question details
Update an existing GCSE question by its ID
Update an existing mark scheme by its ID
DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
This MCP server exposes DeepMark's marking engine directly to your assistant, so exam papers can be created, marked and interrogated conversationally — without touching the web app.
DeepMark marks student answers against a real mark scheme, following the structure an examiner works to. It supports three marking types:
Every mark is returned with feedback tied to the specific criteria met and missed, so the reasoning is visible rather than a bare number.
Papers
paper_create — build a complete, markable exam paper from pasted textpaper_confirm — mint a paper from a job awaiting confirmationpaper_list / paper_get — browse and retrieve papers with question detailquestion_update / markScheme_update — amend questions and mark schemesingestion_get — check the state of a paper-creation or ingestion jobMarking
submission_mark — mark a set of typed answers against an existing papersubmission_get — read grading state and per-question marksmarkResult_get — retrieve the marking result for a single answerMarking is asynchronous. submission_mark returns a submission_id
immediately and grading continues in the background, streaming into the
teacher's editor as each question completes.
submission_mark → receive submission_idsubmission_get until status is completeawarded, max, level and feedbackAllow roughly 15–25 seconds per question. Papers created via paper_create
follow the same pattern — poll ingestion_get, then paper_confirm.
Marking inside a reasoning context means the class set is immediately available to question. Once a set is marked you can ask which mark points the cohort consistently missed, where a levels-of-response band clustered, or which misconception is driving the spread — the diagnostic layer that gets lost when marking is just a number returned.
Remote server — no local install. Add the URL and authenticate with Google OAuth. Access is scoped to your own account.
Uploaded scripts and mark schemes are not used to train models. DeepMark is built in line with the DfE's Generative AI Product Safety Standards.
Built for UK secondary teachers marking GCSE and A-Level extended writing — subject-agnostic and model-agnostic by design.
Website: https://deepmark.co.uk
The DeepMark remote MCP server is a hosted Model Context Protocol endpoint at https://api.getdeepmark.com/mcp, so AI assistants can connect to it without installing or running anything locally.
Add the endpoint https://api.getdeepmark.com/mcp to any MCP-compatible client such as Claude Code, Cursor, or VS Code. The setup snippets on this page configure each client in one step.
Yes. DeepMark uses OAuth: the first time you connect, your MCP client opens a browser window to sign in and authorize access, then reuses the credentials for future sessions.
DeepMark exposes a Streamable HTTP endpoint, the transport used by remote MCP servers and supported by all major MCP clients.
Production remote MCP server with 35 safe web-intelligence tools: 32 paid x402 URL operations plus 3 free discovery/demo tools. Base Mainnet USDC, no account or API key; SSRF protection, strict schemas and idempotent set
Ask your assistant what a competitor is advertising and get the ads themselves: text, links, images, videos, platforms and dates from the Meta Ad Library (Facebook and Instagram), Google's Ads Transparency Center and the LinkedIn Ad Library
AMap's official MCP server: geocoding, POI search, route planning, weather and AMap app hand-off (custom trip maps, navigation, ride-hailing) for AI agents.
Checks whether an EVM address has an EIP-7702 delegation (the trick behind wallet sweepers) on Ethereum, Base, BNB Chain, Arbitrum, OP, Polygon, Gnosis and Unichain
The 9apes MCP server lets an AI assistant read the GitHub Actions data 9apes already collects for your organization: runs, jobs, steps, and their durations. Ask it why a build got slower, which jobs take the longest, or
Comments