About DeepMark
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.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.getdeepmark.com/mcpclaude mcp add --transport http deepmark https://api.getdeepmark.com/mcp{"mcpServers":{"deepmark":{"type":"http","url":"https://api.getdeepmark.com/mcp"}}}Open in Cursor{"servers":{"deepmark":{"type":"http","url":"https://api.getdeepmark.com/mcp"}}}Open in VS Code{"mcpServers":{"deepmark":{"type":"http","url":"https://api.getdeepmark.com/mcp"}}}{"mcpServers":{"deepmark":{"serverUrl":"https://api.getdeepmark.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
10| Parameter | Type | Required | Description |
|---|---|---|---|
| question_paper_text | string | Yes | RAW text of the question paper — questions, bracketed marks, section headers, as printed or pasted. Send the source text and let DeepMark extract the questions. Do NOT pre-structure it into questions yourself. |
| mark_scheme_text | string | No | RAW text of the mark scheme, if the teacher has one. Read jointly with the question paper so marks and numbering align. Send raw text, NOT a mark scheme you authored. Omit entirely when there is no mark scheme — DeepMark generates one per question (lower quality than a real scheme, but the paper is still markable). |
| stimulus_text | string | No | Optional source/stimulus material the questions refer to (a passage, dataset, case study). Supplied as extraction context; it is not itself turned into questions. |
| hints | object | No | Optional cover-identity hints. SOFT grounding for extraction — they steer the model, they do not override the paper text. |
| hints.subject | enum | No | GCSE subject. Grounds extraction; the paper text stays authoritative.biology | chemistry | physics | english | english_literature | mathematics | history | geography | computer_science | french | spanish | religious_studies | business | accounting | art_and_design | bengali | chinese_mandarin | citizenship_studies | dance | design_and_technology | drama | economics | engineering | environmental_science | food_preparation_and_nutrition | german | hebrew_biblical | hebrew_modern | italian | law | media_studies | music | panjabi | philosophy | physical_education | polish | politics | psychology | science | sociology | urdu |
| hints.exam_board | string | No | Awarding body, e.g. 'AQA', 'Edexcel', 'OCR'. |
| hints.tier | enum | No | foundation | higher |
| hints.year | integer | No | Exam-series year, e.g. 2024. |
| hints.year_group | string | No | Teacher's class / year group — free text, e.g. 'Year 11'. |
| hints.title | string | No | Paper title, if known. |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.