Industry solutionsPublic source

Assessment MCP Server

An assessment platform for ADK-Rust Enterprise education agents. 23 MCP tools covering an item bank (six item types with keyed answers), standards/curriculum mapping, assessment authoring + blueprint generation, rubric…

Open the source Read the official guide ↗

What it gives an agent

A purpose-built capability behind one MCP connection.

The server owns its domain logic and publishes a tool contract an MCP client can discover. ADK-Rust can load that contract into an agent, normalize each schema for the chosen model provider, and keep the connection lifecycle outside the agent’s business logic.

Item bank — six item types: multiple_choice, multiple_select, true_false, short_answer, numeric (with tolerance), and essay (rubric-scored). Items carry difficulty, Bloom's cognitive level,…

Standards / curriculum mapping — learning standards (CCSS/NGSS/custom) with items_for_standard coverage and per-assessment standard breakdowns.

Authoring & generation — build assessments from explicit items, or generate from a blueprint (difficulty → count, optionally constrained to standards) drawing from the bank.

Attempts & grading — learner attempts auto-grade objective items on submit; rubric/essay items are scored per-criterion (clamped to each criterion's max) and the attempt finalizes with…

Psychometrics — item_analysis computes per-item p-value (difficulty) and discrimination (top-third vs bottom-third correct-rate) with quality flags (too_hard / too_easy /…

Architecture

How Assessment MCP Server fits into an agent system.

The model never needs the implementation details or credentials of the system behind the server. It sees reviewed tool definitions. The MCP client handles discovery and calls, while the server keeps ownership of validation, policy, and communication with its domain system.

ADK-Rust agent

Chooses a capability from the reviewed tool catalog.

→

MCP client

Discovers schemas, sends calls, and receives typed content.

→

Assessment MCP Server

Validates the request and owns 23 documented tool contracts.

→

Domain system

Keeps the API, data, credentials, and business rules behind the server.

Connection: stdio · Server framework: ADK MCP SDK + rmcp

Assessment MCP Server architecture diagram from its official repository

Tool catalog

What can an agent ask Assessment MCP Server to do?

Each tool has a stable name, a human-readable purpose, and a JSON input contract discovered during MCP initialization. Risk classes come from the project’s registry manifest when one is available.

23 named tools

add_standard

Add a learning standard (curriculum target)

internal write

list_standards

List learning standards by subject/framework

read only

items_for_standard

List items aligned to a standard (coverage)

read only

create_rubric

Create a rubric with weighted criteria

internal write

get_rubric

Get a rubric by id

read only

create_item

Author an item (question) of any supported type

internal write

get_item

Get an item by id (instructor-facing, includes key)

read only

list_items

Search the item bank by subject/difficulty/standard

read only

create_assessment

Create an assessment from explicit item ids

internal write

generate_assessment

Generate an assessment from a difficulty blueprint

internal write

get_assessment

Get an assessment by id

read only

list_assessments

List assessments by subject/status

read only

Governance

Understand the effect of every tool.

A server connection inherits the authority of its credentials and deployment environment. The declarations below come from this project’s README and MCP registry manifest; your application still decides which tools an agent receives and where approval is required.

14 read only8 internal write1 external write

Two writes are gated (requires_approval): publishing an assessment (set_assessment_status → published — makes it live for learners) and submitting an attempt (submit_attempt, classed…
Publishing is guarded — an assessment can't be published with no items, and only published assessments accept attempts.
All analytics and bank queries are read_only.
Everything is audited (audit_log). Sample data is fictitious.

MCP surface

What the current documentation declares.

MCP can carry tools, resources, prompts, structured results, progress, cancellation, and long-running work. This record highlights the modern protocol features explicitly mentioned by this repository.

The current README concentrates on its tool surface. Check the source and release notes before relying on optional MCP capabilities beyond tool discovery and invocation.

ADK MCP SDKrmcpRegistry manifest

Install and connect

Follow the project’s documented starting point.

Install the server in the environment that owns its credentials and domain access. Add it to your MCP host, verify the discovered tools, and narrow the toolset before giving it to a production agent.

Install

cargo install mcp-assessment

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-assessment",
    ["mcp-assessment"],
).await?;

let agent = LlmAgentBuilder::new("agent")
    .tools(toolset.tools().await?)
    .build()?;

Commands and configuration are extracted from the public README. Confirm prerequisites, environment variables, and release-specific options in the official documentation before deployment.

Official documentation

Continue with the project maintainers’ source of truth.

This page provides an approachable map of the server. The repository remains authoritative for exact schemas, prerequisites, configuration, examples, tests, releases, and security updates.

Overview ↗README.md CHANGELOG ↗CHANGELOG.md Architecture ↗docs/architecture.svg Issues and support ↗github.com issues

Keep exploring

Assessment MCP Server

A purpose-built capability behind one MCP connection.

How Assessment MCP Server fits into an agent system.

ADK-Rust agent

MCP client

Assessment MCP Server

Domain system

The server’s published architecture

What can an agent ask Assessment MCP Server to do?

Understand the effect of every tool.

What the current documentation declares.

Follow the project’s documented starting point.

Continue with the project maintainers’ source of truth.

More in industry solutions.