# Studocu (remote · agent-os-mcp.alpha.studocu.com)

Find Studocu study documents, courses and institutions, and manage study projects and quizzes.

- Trust score: 68/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `agent-os-mcp.alpha.studocu.com`: 68/100 (this document), [markdown](https://verifymcp.io/servers/com-studocu-studocu/agent-os-mcp.md), [page](https://verifymcp.io/servers/com-studocu-studocu/agent-os-mcp)

## Channel facts

- Endpoint: `https://agent-os-mcp.alpha.studocu.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (write-memory).
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2984 tokens (~135/item across 22 items; 20 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 76% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 22 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.
  - Supports UI / widget rendering.

## Install

### How do I install the Studocu MCP server?

Studocu is a hosted endpoint at https://agent-os-mcp.alpha.studocu.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http com-studocu-studocu 'https://agent-os-mcp.alpha.studocu.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-studocu-studocu": {
      "url": "https://agent-os-mcp.alpha.studocu.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-studocu-studocu": {
      "type": "http",
      "url": "https://agent-os-mcp.alpha.studocu.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-studocu-studocu]
url = "https://agent-os-mcp.alpha.studocu.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-studocu-studocu": {
      "type": "remote",
      "url": "https://agent-os-mcp.alpha.studocu.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-studocu-studocu --url 'https://agent-os-mcp.alpha.studocu.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-studocu-studocu:
    url: "https://agent-os-mcp.alpha.studocu.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-studocu-studocu": {
      "Transport": "http",
      "Url": "https://agent-os-mcp.alpha.studocu.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-studocu-studocu -t streamable-http -u 'https://agent-os-mcp.alpha.studocu.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-studocu-studocu": {
      "type": "http",
      "url": "https://agent-os-mcp.alpha.studocu.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 68, +1)

- [security] Resource “search-documents” now points somewhere else: ui://views/apps-sdk/search-documents.html?v=0e30fa45 → ui://views/ext-apps/search-documents.html?v=0e30fa45

### 2026-10-17 (score 67, 0)

- [security] Resource “search-documents” now points somewhere else: ui://views/apps-sdk/search-documents.html?v=0e30fa45 → ui://views/ext-apps/search-documents.html?v=0e30fa45

### 2026-10-16 (score 67, +1)

- [security] Resource “search-documents” now points somewhere else: ui://views/apps-sdk/search-documents.html?v=0e30fa45 → ui://views/ext-apps/search-documents.html?v=0e30fa45

### 2026-10-15 (score 66, 0)

- [security] Resource “search-documents” now points somewhere else: ui://views/apps-sdk/search-documents.html?v=0e30fa45 → ui://views/ext-apps/search-documents.html?v=0e30fa45

### 2026-10-14 (score 66, +1)

- [security] Resource “search-documents” now points somewhere else: ui://views/apps-sdk/search-documents.html?v=0e30fa45 → ui://views/ext-apps/search-documents.html?v=0e30fa45

### 2026-10-13 (score 65, 0)

- [security] Resource “search-documents” now points somewhere else: ui://views/apps-sdk/search-documents.html?v=0e30fa45 → ui://views/ext-apps/search-documents.html?v=0e30fa45
- [functional improvement] Stability: unverified → 0.03

### 2026-10-12 (score 65)

First indexed and scored.

## MCP tools (20)

### `search-documents` (~464 tokens)

Document Search

Use 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. For open-web sources outside Studocu, use search-web instead.

Input parameters:

- `course` (string): Course name or code only, e.g. "Economics" or "ECON101". Use when you do not have `course_id`. Never put a numeric id here. Optional extra if you also have `course_id`. Omit entirely if unknown.
- `course_id` (integer): Numeric Studocu course ID from search-courses `course_id`. Prefer this: it pins the course and overrules `course` name/code. Omit if you only have a name/code.
- `institution` (string): Institution display name only, e.g. "University of Amsterdam". Not an id — this tool has no `institution_id`. Infer it from the user message or conversation context when available; omit entirely if u…
- `limit` (integer): Number of results to return (1-50, default: 10).
- `query` (string, required): Topic/keywords only (e.g. "supply and demand", "microeconomics midterm 2025"). Never put course name, course id, or institution name here — use `institution`, `course`, and `course_id` instead.

Output parameters:

- `documents` (array)

### `search-institutions` (~135 tokens)

Search Institutions

Search Studocu institutions by name when establishing or correcting education context (onboarding / context setup). Do not require this before every document search. Structured results include id, name, type, region_code, and country for follow-up tools. When talking to the user, present name/type/country/region only — do not show internal IDs. Auto-pick a clear top match; if the shortlist is ambiguous, ask the user to choose by name. Resolved IDs are conversation-scoped until a persistence capability owns them.

Input parameters:

- `limit` (integer)
- `query` (string, required)
- `type` (string)

Output parameters:

- `institutions` (array)

### `search-courses` (~170 tokens)

Search Courses

Search Studocu courses when establishing or correcting course context. Prefer institution_id from search-institutions to scope results. Omit institution_id only when the institution is unknown: results then include catalog institution_id, and institution_name when Algolia has it. Do not require this before every document search. Structured results include course_id, name, code (nullable), institution_id, and optional institution_name. When talking to the user, present name, course code, and institution name only — do not show internal IDs. Auto-pick a clear top match; if the shortlist is ambiguous, ask the user to choose by name/code. Resolved IDs are conversation-scoped until a persistence capability owns them.

Input parameters:

- `institution_id` (integer)
- `limit` (integer)
- `query` (string, required)

Output parameters:

- `courses` (array)

### `search-web` (~130 tokens)

Web Search

Answer open-web questions with a grounded response and citation URLs (news, reference sites, documentation). Use this for non-Studocu sources. For Studocu study documents, lecture notes, summaries, or course materials, use search-documents instead. Competitor study-material domains are excluded from results.

Input parameters:

- `query` (string, required): Open-web question or search prompt (external sources only). For Studocu study documents, lecture notes, or course materials use search-documents instead.
- `site` (string): Optional domain filter, e.g. "rijksoverheid.nl". Restricts search to that site when supported.

Output parameters:

- `citations` (array): Sources used for the answer, with title, URL, and domain.
- `text` (string): Grounded answer text, including inline citation links when present.

### `get-course-syllabus` (~56 tokens)

Get Course Syllabus

Return a generated course outline as markdown when this tool has one. This is the best grounding for high-quality study guidance. Requires course_id.

Input parameters:

- `course_id` (integer, required): Studocu course id whose published syllabus should be loaded.

Output parameters:

- `content` (string): Published syllabus text for this course.
- `course_id` (string): Course id whose published syllabus was loaded.

### `agent-os-session` (~29 tokens)

Agent OS Session

Use this proof tool to verify that the Agent OS MCP server received a valid delegated Studocu session.

Output parameters:

- `authenticated` (boolean)
- `clientId` (string)
- `scopes` (array)
- `subject` (string)

### `read-web-url` (~111 tokens)

Read Web URL

Read a specific public URL and return grounded page content for agent evidence. Use this when you already have the exact URL. For Studocu study documents use search-documents; for open-web discovery use search-web. Competitor study-material hosts are rejected.

Input parameters:

- `query` (string): Optional focus question or extraction instruction for the page content.
- `url` (string, required): Public http or https URL to read for agent evidence. For Studocu study documents use search-documents; for open-web discovery use search-web.

Output parameters:

- `text` (string): Grounded text extracted from the URL for agent use.
- `url` (string): The requested URL that was read.

### `read-artifact` (~82 tokens)

Read Studocu Artifact

Read a Studocu project source or creation by its studocu://project/{project_id}/{kind}/{uuid} URI. Returns normalized metadata with explicitly mapped inline content.

Input parameters:

- `artifact_id` (string, required): Artifact URI in the form studocu://project/{project_id}/{kind}/{uuid}.
- `cursor` (string): Opaque continuation cursor returned by a previous read.

Output parameters:

- `artifactId` (string)
- `continuations` (array)
- `details` (object)
- `projectId` (string)

### `read-detached-document` (~55 tokens)

Read Detached Studocu Document

Read a Studocu document directly, without requiring or creating a project source. Use read-artifact for documents attached to a project.

Input parameters:

- `document_id` (integer, required): Studocu document ID to read without creating a project source.

Output parameters:

- `content` (string): The raw full text content of the Studocu document.

### `get-context` (~253 tokens)

Studocu Agent OS Context

Return the unified Agent OS context manifest for the authenticated user: profile, followed courses, project metadata, and recent activity. Every project includes has_course_mastery and started_course_mastery (course supports Infinite Practice / learner has started it). Course mastery is visible only on projects, not followed_courses. Practised-topic detail (topic_masteries) is included only when a course is in scope (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.

Input parameters:

- `active_only` (boolean): Limit the manifest to active context.
- `course_id`: Narrow context to a single followed course and its projects.
- `project_id` (string): Narrow context to a single project by id.
- `recent_only` (boolean): Limit the manifest to recently active context.

Output parameters:

- `aggregates` (object)
- `context_schema_version` (number)
- `data` (object)
- `generated_at` (string)
- `prompt_views` (object)
- `requested_filters` (object)

### `get-project-state` (~112 tokens)

Studocu Project State

Return sources and creations (project state) for one or more projects by id. Creation rows may include external_id (quizId or mockExamId) so a request-creation creating 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.

Input parameters:

- `ids` (array, required): The project ids to load sources and creations (project state) for. Only projects you can access are returned.

Output parameters:

- `projects` (array)

### `get-course-mastery` (~181 tokens)

Get Infinite Practice Course Mastery

Return practised-topic Infinite Practice mastery for a 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 matches the web 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_masteries means no IP attempts yet, not a separate client score. Requires course_id.

Input parameters:

- `course_id` (integer, required): Course id to load practised-topic Infinite Practice mastery for.

Output parameters:

- `course_id` (string): Course id whose mastery was loaded, matching followed_courses.course_id.
- `topic_masteries` (array): Practised topics only. Empty means this course was loaded and the learner has no IP attempts yet.

### `write-artifact` (~74 tokens)

Write Studocu Artifact

Create a Studocu artifact from typed content. Provide project_id and an artifact envelope; the artifact type defines the required content shape.

Input parameters:

- `artifact` (required): The artifact to create. Pick type; each type defines its own content shape.
- `project_id` (string, required): UUID of the Studocu project that will own the artifact.

Output parameters:

- `artifactId` (string): Canonical Studocu artifact URI for the created creation.
- `kind` (string): Artifact kind returned by the write operation.
- `projectId` (string): UUID of the Studocu project that owns the created artifact.
- `status` (string): Stable write status for successful creation writes.
- `title` (string): Human-readable title of the created artifact.
- `type` (string): Creation type that was written.

### `add-document-sources` (~84 tokens)

Add Studocu Document Sources

Attach up to 10 Studocu documents from search-documents to a project. Returns the sources that were successfully added; compare with document_ids if some were omitted.

Input parameters:

- `document_ids` (array, required): One to ten unique Studocu document IDs returned by search-documents.
- `project_id` (string, required): UUID of the Studocu project that will receive the document sources.

Output parameters:

- `project_id` (string)
- `sources` (array)

### `create-project` (~53 tokens)

Create Studocu Project

Create a Studocu project and optionally configure its emoji and course. A numeric course_id is validated before project creation.

Input parameters:

- `course_id` (integer)
- `emoji` (string)
- `title` (string)

Output parameters:

- `course_id`
- `emoji` (string)
- `institution_id`
- `is_mobile` (boolean)
- `project_id` (string): NOTE: These shared primitives are copied from the AI API spec and owned locally by Agent OS to keep this contract decoupled.
- `title` (string): Agent-displayable project title. Null Alpha names become "Untitled project".

### `update-project` (~86 tokens)

Update Studocu Project

Update a Studocu project title, emoji, or course. Use course_id null to clear the course and institution.

Input parameters:

- `course_id`
- `emoji` (string)
- `project_id` (string, required): NOTE: These shared primitives are copied from the AI API spec and owned locally by Agent OS to keep this contract decoupled.
- `title` (string)

Output parameters:

- `course_id`
- `emoji` (string)
- `institution_id`
- `is_mobile` (boolean)
- `project_id` (string): NOTE: These shared primitives are copied from the AI API spec and owned locally by Agent OS to keep this contract decoupled.
- `title` (string): Agent-displayable project title. Null Alpha names become "Untitled project".

### `request-creation` (~237 tokens)

Request Studocu Creation

Generate a Studocu quiz or mockExam from 1-10 project source artifacts. Waits up to ~3 minutes; returns artifact_id and external_id when created, status creating with external_id when persist is not yet visible, or outcome_unknown on client timeout or in-flight duplicate (check get-project-state before retrying). Optional idempotency_key is forwarded as Idempotency-Key; identical retries without a key still dedupe.

Input parameters:

- `artifact_ids` (array, required): One to ten unique source artifact IDs (studocu://project/{project_id}/source/{uuid}) to generate from.
- `idempotency_key` (string): Optional retry key. Agent OS always sends Idempotency-Key to Alpha (this value, or a fingerprint of project/type/sources/instruction). Reuse with a different body is rejected.
- `instruction` (string): Optional free-text hint for the generating agent (e.g. "focus on chapter 3").
- `project_id` (string, required): UUID of the Studocu project that will own the new creation.
- `type` (string, required): The kind of creation to generate: quiz or mockExam.

Output parameters:

- `artifact_id` (string): Agent OS artifact ID of the new creation. Present when status is created.
- `external_id`: Kind-specific downstream id (quizId or mockExamId). Present on created and creating; match the same field on get-project-state creation rows. Omitted on timeout.
- `status` (string): created: persisted and linked (artifact_id and external_id). creating: generation finished but Alpha identity is not yet visible (external_id matches get-project-state creation rows). outcome_unknown…
- `type` (string)

### `read-memory` (~122 tokens)

Read Studocu Agent Memory

Read durable agent memory for the authenticated user. Returns one document per (scope, kind); use project_id for project-scoped memory. Identity comes from Core via the session bearer, not from input.

Input parameters:

- `kind` (string): Narrow the result to a single memory kind.
- `project_id`: Project UUID for project-scoped memory; null or omitted reads global (user-level) memory. Required when scope is project or both.
- `scope` (string): Memory scope to read: global, project, or both. Defaults to global unless project_id is set.

Output parameters:

- `memories` (array): Durable memory documents for the authenticated user.

### `write-memory` (~116 tokens)

Write Studocu Agent Memory

Upsert one durable memory document per (scope, kind) for the authenticated user. Provide project_id for project-local memory, or null/omit for global. Identity comes from Core via the session bearer, not from input.

Input parameters:

- `kind` (string, required): Memory kind, e.g. study_preference or project_learning_context.
- `project_id`: Project UUID for project-local memory; null or omitted stores global (user-level) memory.
- `value` (object, required): Freeform memory document. MVP convention is { content: string }.

Output parameters:

- `createdAt` (string): Creation timestamp of the row.
- `kind` (string): Memory kind that was written.
- `projectId`: Owning project UUID, or null for global memory.
- `updatedAt` (string): Last write timestamp of the row.
- `userId` (string): Owner of the memory document.
- `value` (object): Stored memory document.

### `delete-memory` (~98 tokens)

Delete Studocu Agent Memory

Delete one durable memory document identified by (scope, kind) for the authenticated user. Provide project_id for project-local memory, or null/omit for global. Identity comes from Core via the session bearer, not from input.

Input parameters:

- `kind` (string, required): Memory kind to delete, e.g. study_preference or project_learning_context.
- `project_id`: Project UUID for project-local memory; null or omitted deletes global (user-level) memory.

Output parameters:

- `deleted` (boolean): Always true when the delete succeeds.
- `kind` (string): Memory kind that was deleted.
- `projectId`: Owning project UUID, or null for global memory.
- `userId` (string): Owner of the deleted memory document.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-studocu-studocu/agent-os-mcp#diagnostics

## Score history

- 2026-10-18: 68
- 2026-10-17: 67
- 2026-10-16: 67
- 2026-10-15: 66
- 2026-10-14: 66
- 2026-10-13: 65
- 2026-10-12: 65

## Common questions

### What is the Studocu MCP server?

Studocu is an MCP server listed in the public MCP registry as com.studocu/studocu. Find Studocu study documents, courses and institutions, and manage study projects and quizzes. This page covers its hosted endpoint (https://agent-os-mcp.alpha.studocu.com/mcp).

### Is the Studocu MCP server safe to use?

Studocu scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Studocu MCP server expose?

Studocu exposes 20 tools: search-documents, search-institutions, search-courses, search-web, get-course-syllabus, and 15 more. Their descriptions and schemas cost roughly 2,648 tokens of context every time the server is loaded.

### Does the Studocu MCP server require authentication?

No. We connected to Studocu without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Studocu MCP server still maintained?

Studocu is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agent-os-mcp.alpha.studocu.com/mcp
- Website: https://www.studocu.com/mcp
- Changelog RSS feed: https://verifymcp.io/servers/com-studocu-studocu/agent-os-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-studocu-studocu/agent-os-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-studocu-studocu/agent-os-mcp