Studocu
MCP server by Studocu
Search Studocu study documents, courses and institutions, and manage study projects, quizzes and mock exams.
Connect to Studocu
No sign-in needed. Connect with Studocu’s own URL:
Paste it into any client that supports remote MCP servers. Your client talks to Studocu directly, not through mcp.tc.
Share this server
Opens this page, with the URL and setup steps.
mcp.tc/i/studocuAbout
Connects to Studocu to search study documents, lecture notes and summaries, look up institutions and courses, fetch course syllabi, and run open-web searches with citations. Signed-in users can also manage study projects, attach document sources, generate quizzes or mock exams, read course mastery, and store agent memory.
Runs as a hosted streamable HTTP endpoint. Search tools (documents, institutions, courses, web, syllabus) work anonymously with no Authorization header. The project, artifact, memory and context tools need a valid Studocu-issued token with the mcp:use scope.
What you can do
- Search Studocu documents, notes and summaries by topic
- Find institutions and courses to set education context
- Get a generated course syllabus as markdown
- Search the open web with cited answers
- Read a public web page by URL
- Create and update study projects and attach documents
- Generate quizzes or mock exams from project sources
- Read course mastery and store agent memory
Tools 19
search-documentsRead-onlyFind Studocu study documents, notes and summaries by topic, optionally scoped to a course.
search-institutionsRead-onlySearch Studocu institutions by name to set education context.
search-coursesRead-onlySearch Studocu courses, optionally scoped to an institution.
get-course-syllabusRead-onlyReturn a generated course outline as markdown for a course ID.
list-course-recordingsRead-onlyList Course Recordings
agent-os-sessionRead-onlyVerify that the server received a valid delegated Studocu session.
read-artifactRead-onlyRead a project source or creation by its studocu:// URI.
read-detached-documentRead-onlyRead a Studocu document directly without a project source.
get-contextRead-onlyReturn the user's profile, followed courses, projects and recent activity.
get-project-stateRead-onlyReturn sources and creations for one or more projects.
get-course-masteryRead-onlyReturn practised-topic Infinite Practice mastery for a course.
write-artifactWritesCreate a Studocu artifact from typed content in a project.
Show 7 more tools
add-document-sourcesWritesAttach up to 10 Studocu documents to a project.
create-projectWritesCreate a Studocu project with optional emoji and course.
update-projectCan deleteUpdate a project's title, emoji or course.
request-creationWritesGenerate a quiz or mock exam from 1-10 project sources.
read-memoryRead-onlyRead durable agent memory for the authenticated user.
write-memoryCan deleteUpsert a durable memory document for the user.
delete-memoryCan deleteDelete a durable memory document for the user.
Read from the live server on 18 Nov 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.
Example prompts
Find lecture notes on thermodynamics entropy for my physics course
Search for the course Introduction to Psychology at Utrecht University
Get the syllabus for this course and summarize the main topics
Create a study project and generate a quiz from these documents
Set up
Every client connects to agent-os-mcp.alpha.studocu.com. Pick yours; the page remembers your choice.
Claude Code
- Run this in a terminal, in your project folder:
claude mcp add --transport http studocu https://agent-os-mcp.alpha.studocu.com/mcp- Start Claude Code and type
/mcp. studocu should show as connected.
Add --scope user to make it available in every project, not just this one.
Claude Desktop
- Open Customize → Connectors, click + Add, then Add custom connector.
- Name it Studocu and paste this URL:
https://agent-os-mcp.alpha.studocu.com/mcp- Click Add. Its tools appear in the chat’s tools menu.
Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.
claude.ai
- Open the connector form on claude.ai. This button fills in the name and URL for you:
Add to claude.ai (opens in a new tab)
- Check that the URL reads
https://agent-os-mcp.alpha.studocu.com/mcpand click Add. - Turn it on in a chat from the tools menu.
Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.
ChatGPT
- On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
- Enter a name for the server.
- Under Connection, paste
https://agent-os-mcp.alpha.studocu.com/mcpas the server URL, then for authentication choose No authentication. - Check I understand and want to continue, then select Create as a plugin.
Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).
Cursor
Add to Cursor (opens in a new tab)
Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):
{
"mcpServers": {
"studocu": {
"url": "https://agent-os-mcp.alpha.studocu.com/mcp"
}
}
}VS Code
Install in VS Code (opens in a new tab)
Or from a terminal:
code --add-mcp '{"name":"studocu","type":"http","url":"https://agent-os-mcp.alpha.studocu.com/mcp"}'Or commit it to the repo in .vscode/mcp.json:
{
"servers": {
"studocu": {
"type": "http",
"url": "https://agent-os-mcp.alpha.studocu.com/mcp"
}
}
}Devin Desktop
- Add it to
~/.config/devin/mcp_config.json(macOS and Linux) or%APPDATA%\devin\mcp_config.json(Windows):
{
"mcpServers": {
"studocu": {
"serverUrl": "https://agent-os-mcp.alpha.studocu.com/mcp"
}
}
}- Refresh the MCP server list in Cascade.
Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.
Codex
codex mcp add studocu --url https://agent-os-mcp.alpha.studocu.com/mcpOr edit ~/.codex/config.toml directly:
[mcp_servers.studocu]
url = "https://agent-os-mcp.alpha.studocu.com/mcp"Gemini CLI
gemini mcp add --transport http studocu https://agent-os-mcp.alpha.studocu.com/mcpThis adds it to the current project. Add -s user to use it everywhere.
Any client
Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.
{
"mcpServers": {
"studocu": {
"type": "http",
"url": "https://agent-os-mcp.alpha.studocu.com/mcp"
}
}
}Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.
Client only starts local servers? Bridge it with npx -y mcp-remote https://agent-os-mcp.alpha.studocu.com/mcp.
Embed
Show Studocu in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work
The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.
README badge
[](https://mcp.tc/i/studocu)<a href="https://mcp.tc/i/studocu"><img src="https://mcp.tc/i/studocu/badge.svg" alt="Studocu on mcp.tc" height="20"></a>It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.
Website card
<script src="https://mcp.tc/w/studocu.js" async></script>The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.
iframe
<iframe src="https://mcp.tc/embed/studocu" title="Studocu on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.
JSON
The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).
https://mcp.tc/i/studocu.jsonAI prompt
Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Studocu card to your site.
Add the mcp.tc card for Studocu, an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.
Put this tag where the card should appear. The card renders right before it:
```html
<script src="https://mcp.tc/w/studocu.js" async></script>
```
To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.
```html
<div data-mcptc="studocu"><a href="https://mcp.tc/i/studocu">Studocu on mcp.tc</a></div>
```
Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.
If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).
For a README or other Markdown docs, use the badge instead:
```markdown
[](https://mcp.tc/i/studocu)
```
Reference: https://mcp.tc/embedChange history
We read this server’s tool list every 3 hours and record what changes. Last read 18 Nov 2026, 05:39 UTC.
-
1 tool changed.
Details, 16 Nov 2026, 11:57 UTC
Changed 1
list-course-recordingsdescription, input schema and output schemaBeforeList public class recordings (lecture audio with a transcript) that students shared for a course. Pass course_id from search-courses.
Eachrecording has an artifact_id. An empty list means no one has shared a recording for this course yet.AfterList public class recordings (lecture audio with a transcript) that students shared for a course. Pass course_id from search-courses. Most recently recorded first; each recording has a recording date and an artifact_id. An empty list means no one has shared a recording for this course yet.
-
1 tool added and 1 tool changed. Server instructions changed.
New server instructions
Details, 12 Nov 2026, 14:50 UTC
Added 1
list-course-recordingsRead-onlyList public class recordings (lecture audio with a transcript) that students shared for a course. Pass course_id from search-courses. Each recording has an artifact_id. An empty list means no one has shared a recording for this course yet.
Changed 1
read-artifactdescriptionBeforeRead a project source or creation by its studocu:// id (from get-project-state, add-document-sources, write-artifact, or request-creation). File and image sources also return the image when a viewable copy, or an original upload under 5 MB, exists.
AfterRead a project source or creation by its studocu:// id (from get-project-state, add-document-sources, write-artifact, or request-creation). File and image sources also return the image when a viewable copy, or an original upload under 5 MB, exists. A class recording returns its transcript only to its owner; anyone else gets the recording's summary.
Server instructions
BeforeSearch Studocu and, after the learner signs in, work with their projects. search-documents, search-institutions, search-courses, and
get-course-syllabusneed no login, and neither does previewing Studocu documents; every other tool needs a signed-in Studocu account. Leave the Authorization header off when the learner is not signed in: a bad or expired token is rejected, even for the no-login tools. Do not call search-institutions or search-courses before every search-documents.AfterSearch Studocu and, after the learner signs in, work with their projects. search-documents, search-institutions, search-courses, get-course-syllabus, and list-course-recordings need no login, and neither does previewing Studocu documents; every other tool needs a signed-in Studocu account. Leave the Authorization header off when the learner is not signed in: a bad or expired token is rejected, even for the no-login tools. Do not call search-institutions or search-courses before every search-documents.
-
1 tool changed.
Hint changed: may modify data
Details, 10 Nov 2026, 11:46 UTC
Changed 1
update-projecthintsdestructiveHintno changed to yes
-
8 tools changed. Server instructions changed.
New server instructions
Details, 9 Nov 2026, 14:50 UTC
Changed 8
add-document-sourcesoutput schemacreate-projectoutput schemaget-contextoutput schemaget-project-stateoutput schemaread-artifactoutput schemarequest-creationoutput schemaupdate-projectoutput schemawrite-artifactoutput schema
Server instructions
BeforeSearch Studocu and, after the learner signs in, work with their projects. search-documents, search-institutions, search-courses, and get-course-syllabus need no
login;every other tool needs a signed-in Studocu account. Leave the Authorization header off when the learner is not signed in: a bad or expired token is rejected, even for the no-login tools. Do not call search-institutions or search-courses before every search-documents.AfterSearch Studocu and, after the learner signs in, work with their projects. search-documents, search-institutions, search-courses, and get-course-syllabus need no login, and neither does previewing Studocu documents; every other tool needs a signed-in Studocu account. Leave the Authorization header off when the learner is not signed in: a bad or expired token is rejected, even for the no-login tools. Do not call search-institutions or search-courses before every search-documents.
-
1 tool changed.
Details, 5 Nov 2026, 11:51 UTC
Changed 1
read-artifactinput schema and output schema- Description of
artifact_idBeforeId shaped like studocu://project/{project_id}/{kind}/{uuid}. kind is source (a project source) or creation (a quiz, mock exam, note, flashcard
set, or lesson).Example:studocu://project/11111111-111…AfterId shaped like studocu://project/{project_id}/{kind}/{uuid}. kind is source (a project source) or creation (a quiz, mock exam, note, or flashcard set). Example: studocu://project/11111111-1111-4111-8…
- Description of
-
1 tool changed.
Details, 2 Nov 2026, 11:51 UTC
Changed 1
read-detached-documentinput schema- New parameters:
page
- New parameters:
-
18 tools changed. Server instructions changed.
New server instructions
Details, 30 Oct 2026, 11:46 UTC
Changed 18
add-document-sourcesdescription and input schemaBeforeAttach up to 10 Studocu documents from search-documents to a
project.Returns the sourcesthat were successfully added;compare with document_ids if somewere omitted.AfterAttach up to 10 Studocu documents from search-documents to a project as project sources. Returns the added sources with their studocu:// ids; compare with document_ids if some are missing.
- Description of
project_idBeforeUUID of the
Studocuproject thatwillreceive thedocument sources.AfterUUID of the project that should receive the Studocu documents. Example: 11111111-1111-4111-8111-111111111111. From create-project or get-context.
- Description of
document_idsBeforeOnetoten uniqueStudocu documentIDs returned by search-documents.After1 to 10 different positive integer Studocu document ids from search-documents (documents[].id). Example: [17, 42].
- Description of
agent-os-sessiondescription and titleBeforeUse
this proof tooltoverifythatthe Agent OS MCP server received a valid delegated Studocu session.AfterShow who the current Studocu sign-in belongs to: authenticated, subject, clientId, and scopes. Use only to check that login worked.
title
BeforeAgent OS SessionAfterCheck Studocu Sign-in
create-projectdescription, input schema and output schemaBeforeCreate a
Studocu projectandoptionally configure its emoji and course. A numeric course_id is validated before project creation.AfterCreate a new project. Every field is optional. Returns project_id for add-document-sources, write-artifact, and request-creation.
- Description of
titleBeforenone
AfterName, 1-255 characters, with at least one non-space character. Example: "Biology midterm". Omit to create the project without a name; the returned title is then "Untitled project".
- Description of
emojiBeforenone
AfterIcon text, usually an emoji. Example: "📚". Omit to leave the icon unset.
- Description of
course_idBeforenone
AfterPositive integer course id from search-courses. Example: 1581710. The course is checked before the project is created; an unknown id creates nothing. Omit to leave the project unlinked.
- Description of
delete-memorydescription and input schemaBeforeDelete one
durablememorydocument identifiedby(scope, kind) for the authenticated user. Provideproject_idfor project-local memory, or null/omit for global. Identity comes from Core via the session bearer, not from input.AfterDelete one saved memory for this learner, chosen by project_id and kind.
- Description of
project_idBeforeProjectUUIDfor project-local memory;nullor omitted deletes global (user-level)memory.AfterUUID of the project memory to delete, or null. Example: 11111111-1111-4111-8111-111111111111. Omit or null to delete a learner-wide memory.
- Description of
kindBeforeMemory kindtodelete, e.g. study_preferenceorproject_learning_context.AfterKind of the memory to delete. Example: "study_preference" or "project_learning_context".
- Description of
get-contextdescription, title and input schemaBeforeReturntheunified Agent OS context manifest for the authenticated user:profile, followed courses,project metadata,andrecent activity. Every project includes has_course_mastery and started_course_mastery (course supports Infinite Practice / learner has started it). Course masteryisvisible only on projects, not followed_courses. Practised-topic detail (topic_masteries) isincluded only whenacourse is inscope (project_id, a sole remaining project, or remaining projects that share one course_id); the field is omitted when detail was not loaded. Empty topic_masteries means that course was loaded and the learner has no practised topics. Use get-course-mastery(course_id) for the practised-topic list when context omitted detail. Agent OS is read-only: chatting or calling this tool does not change mastery. Source of truth is Infinite Practice attempts (identity + course + topic); web IP writes, ACE/mobile/Agent OS only read.AfterLoad the learner's profile, followed courses, and projects. Use get-project-state for what is inside a project. Per-topic practice scores are included only when one course is in scope; otherwise use get-course-mastery.
title
BeforeStudocu Agent OSContextAfterGet Learner Context
- Description of
project_idBeforeNarrow contexttoa single project by id.AfterReturn only this project. Example: "11111111-1111-4111-8111-111111111111". From an earlier get-context or create-project result. Omit to include the learner's projects.
- Description of
course_idBeforeNarrow context to a single followedcourse and its projects.AfterReturn only this course and its projects. Numeric id or the same id as text. Example: 1581710 or "1581710". Omit to include every followed course.
- Description of
recent_onlyBeforeLimitthemanifest to recently active context.AfterOptional true or false. It is echoed on the response and does not change which courses or projects are returned. Omit it.
- Description of
active_onlyBeforeLimitthemanifest to active context.AfterOptional true or false. It is echoed on the response and does not change which courses or projects are returned. Omit it.
- Description of
get-course-masterydescription, title, input schema and output schemaBeforeReturn
practised-topic Infinite Practice masteryfora course (topic_id, topic_name when available, display 0–100, questions_answered). Use after get-context flags (has_course_mastery / started_course_mastery) or whenever context omitted topic_masteries. Agent OS is read-only: chatting, creating artifacts, or calling this tool does not change mastery. Source of truth is Infinite Practice attempts (user_topic_mastery: identity + course + topic); display matchestheweb IP UI. Progress is learner- and course-scoped, not chat- or client-scoped — web IP writes it; ACE/mobile/Agent OS only read the same rows. Empty topic_masteriesmeans noIP attempts yet, not a separate client score. Requires course_id.AfterReturn the learner's practice scores (0-100) for the topics they have practised in one course. An empty list means no practice yet.
title
BeforeGet
InfinitePracticeCourse MasteryAfterGet Course Practice Scores
- Description of
course_idBeforeCourseidto load practised-topic Infinite Practice mastery for.AfterNumeric course id from search-courses or get-context. Example: 1581710. A numeric string such as "1581710" is accepted.
- Description of
get-course-syllabusdescription and input schemaBeforeReturn a
generatedcourseoutlineasmarkdown when this tool has one. This isthebest grounding for high-quality study guidance. If it is missing, a syllabus may be generating, sotry again in a few minutes.Requires course_id.AfterReturn Studocu's generated outline for a course as markdown. If none exists yet, the call returns an error; try again in a few minutes.
- Description of
course_idBeforeStudocucourse idwhose published syllabus should be loaded.AfterNumeric course id from search-courses. Example: 1581710. A numeric string such as "1581710" is accepted.
- Description of
get-project-statedescription and input schemaBeforeReturnsources and creations(project state) forone or moreprojects by id. Creation rowsmay include external_id(quizIdormockExamId) soa request-creationcreating response can be matched once Alpha identity appears. Use after get-context (which lists projects without their sources/creations) to load those projects' artifacts. Only projects you can access are returned.AfterList the project sources and creations inside one or more projects. A creation may include external_id (a quiz id or mock-exam id) to match a request-creation result that is still being saved.
- Description of
idsBeforeTheproject idsto load sources and creations (project state) for. Only projectsyoucanaccess arereturned.After1 to 20 project ids from get-context or create-project. Example: ["11111111-1111-4111-8111-111111111111"]. Projects you cannot access are left out.
- Description of
read-artifactdescription, input schema and output schemaBeforeRead a
Studocuproject source or creation by itsstudocu://project/{project_id}/{kind}/{uuid} URI. Returns normalized metadata with explicitly mapped inline content. file/imagesources alsoincludethephoto as animagecontent blockwhen a viewableimage,or an original upload under 5 MB,is available.AfterRead a project source or creation by its studocu:// id (from get-project-state, add-document-sources, write-artifact, or request-creation). File and image sources also return the image when a viewable copy, or an original upload under 5 MB, exists.
- Description of
artifact_idBeforeArtifact URI in the formstudocu://project/{project_id}/{kind}/{uuid}.AfterId shaped like studocu://project/{project_id}/{kind}/{uuid}. kind is source (a project source) or creation (a quiz, mock exam, note, flashcard set, or lesson). Example: studocu://project/11111111-111…
- Description of
cursorBeforeOpaque continuation cursor returned bya previous read.AfterToken from a previous read when the result said there is more, for long content. Omit on the first read. Pass it back unchanged with the same artifact_id.
- Description of
read-detached-documentdescription, title and input schemaBeforeRead a Studocu document
directly,withoutrequiring or creating a project source. Use read-artifact for documents attachedto a project.AfterRead the text of a Studocu document by its search-documents id, without adding it to a project.
title
BeforeRead
DetachedStudocu DocumentAfterRead Studocu Document
- Description of
document_idBeforeStudocu document ID to read without creating a project source.AfterPositive integer id from search-documents (documents[].id). Example: 17.
- Description of
read-memoryrequest-creationsearch-coursessearch-documentssearch-institutionsupdate-projectwrite-artifactwrite-memoryServer instructions
BeforeUsetheAgent OS MCP server for Studocu document search and authenticated Agent OS capability discovery.search-documents, search-institutions, search-courses, and get-course-syllabusare public tools: call them withno Authorizationheader. An invalidor expiredbearer on any /mcp request fails closed with HTTP 401 and blocks public tools too — omit Authorizationforanonymous search. Authenticated tools are advertised in tools/list without a bearer (oauth2 mcp:use) so clients can plan Connect; calling them without a valid JWT returns a Connect challenge. Authenticated tools (agent-os-session, read-artifact, read-detached-document, write-artifact, get-context, get-project-state, get-course-mastery, add-document-sources, create-project, update-project, request-creation, read-memory, write-memory, delete-memory) require a valid Core-issued JWT withtherequired MCP scopes. Prefersearch-institutionsandsearch-courseswhen establishing or correcting education context; do not require thembefore everysearch-documents call. Use search-documents for Studocu study materials.AfterSearch Studocu and, after the learner signs in, work with their projects. search-documents, search-institutions, search-courses, and get-course-syllabus need no login; every other tool needs a signed-in Studocu account. Leave the Authorization header off when the learner is not signed in: a bad or expired token is rejected, even for the no-login tools. Do not call search-institutions or search-courses before every search-documents.
-
1 tool changed.
Details, 27 Oct 2026, 11:59 UTC
Changed 1
read-artifactdescriptionBeforeRead a Studocu project source or creation by its studocu://project/{project_id}/{kind}/{uuid} URI. Returns normalized metadata with explicitly mapped inline content.
AfterRead a Studocu project source or creation by its studocu://project/{project_id}/{kind}/{uuid} URI. Returns normalized metadata with explicitly mapped inline content. file/image sources also include the photo as an image content block when a viewable image, or an original upload under 5 MB, is available.
-
1 tool changed.
Details, 22 Oct 2026, 10:42 UTC
Changed 1
write-artifactinput schema and output schema
-
1 tool changed.
Details, 21 Oct 2026, 13:41 UTC
Changed 1
search-documentsdescription and output schemaBeforeUse this when the user wants to find, search, or browse study documents, lecture notes, summaries, or course materials on Studocu. Pass topic/keywords as `query` only — never put course name, course id, or institution name in `query`. `institution` is a display name only (this tool has no institution_id). Prefer numeric `course_id` from search-courses when you have it: it pins the course and overrules `course`. If both `course_id` and `institution` are sent, `course_id` wins; result institution is that course's university, not the name you passed. Otherwise pass `course` as name or code, never as a numeric id. `course` is optional extra if you already have `course_id`. Omit unknown filters. Returns matching documents with titles, course and institution info, ratings, and a link to view each on Studocu.
AfterUse this when the user wants to find, search, or browse study documents, lecture notes, summaries, or course materials on Studocu. Pass topic/keywords as `query` only — never put course name, course id, or institution name in `query`. `institution` is a display name only (this tool has no institution_id). Prefer numeric `course_id` from search-courses when you have it: it pins the course and overrules `course`. If both `course_id` and `institution` are sent, `course_id` wins; result institution is that course's university, not the name you passed. Otherwise pass `course` as name or code, never as a numeric id. `course` is optional extra if you already have `course_id`. Omit unknown filters. Returns matching documents with titles, course and institution info, ratings, and a link to view each on Studocu. Results with `match_type: semantic` are closest matches, not exact keyword hits, and may be only loosely related; check them against the request.
-
1 tool changed.
Details, 20 Oct 2026, 13:36 UTC
Changed 1
search-documentsThe 10 newest entries show every detail; older ones show names only.
-
2 tools removed and 1 tool changed. Server instructions changed.
New server instructions
Details, 20 Oct 2026, 10:33 UTC
Removed 2
read-web-urlsearch-webChanged 1
search-documentsThe 10 newest entries show every detail; older ones show names only.
-
1 tool changed.
Details, 19 Oct 2026, 16:39 UTC
Changed 1
get-course-syllabusThe 10 newest entries show every detail; older ones show names only.
-
20 tools changed.
Details, 15 Oct 2026, 13:34 UTC
Changed 20
add-document-sourcesagent-os-sessioncreate-projectdelete-memoryget-contextget-course-masteryget-course-syllabusget-project-stateread-artifactread-detached-documentread-memoryread-web-urlrequest-creationsearch-coursessearch-documentssearch-institutionssearch-webupdate-projectwrite-artifactwrite-memoryThe 10 newest entries show every detail; older ones show names only.
-
Tracking started: 20 tools.
FAQ
Can I paste mcp.tc/i/studocu into my MCP client?
No. mcp.tc links are pages, not server addresses. Connect with https://agent-os-mcp.alpha.studocu.com/mcp, so your client talks to Studocu directly. The quick link is for sharing: it opens this page, with setup steps for every client.
Does Studocu need an API key or a sign-in?
No. Studocu doesn’t ask for an account or key.
Is Studocu a remote or a local server?
Remote. Studocu hosts it at https://agent-os-mcp.alpha.studocu.com/mcp, and it speaks Streamable HTTP. There’s nothing to install.
What can Studocu do?
It has 19 tools, including search-documents, search-institutions and search-courses. You can search Studocu documents, notes and summaries by topic, find institutions and courses to set education context and get a generated course syllabus as markdown.
Which clients can use it?
Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.
Does mcp.tc track changes to Studocu?
Yes. Studocu’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.
Who wrote this page?
mcp.tc’s robot read Studocu’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.
mcp.tc isn’t affiliated with Studocu. This page was built from Studocu’s public metadata, last checked on 18 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.