Business operationsPublic source

Case Management MCP Server

A horizontal case-management layer for ADK-Rust Enterprise agents working investigations, complaints, disputes, deviations, and incidents across regulated industries. 18 MCP tools spanning the full case lifecycle —…

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.

One model, many domains — a single Case workflow (intake → triaged → investigating → pending_info/escalated → resolved → closed) fits investigation, complaint, dispute, deviation, and…

Defensible by construction — every mutation appends an immutable AuditEntry (actor, action, detail, timestamp). Investigations need a chain of custody.

Evidence by reference, not value — artifacts are stored by URI in a content store; the case never holds raw bytes or PII. Subjects/parties are opaque tokens/refs.

Statutory clocks — per-case_type SLA policies set acknowledge/resolve deadlines (e.g. RegE-10-day-provisional, DOI-15-day-response, PV-15-day-expedited, GxP-deviation-30-day) with breach…

Gated writes — closing a case (legally significant) requires approval in production; valid workflow transitions are enforced; closure is blocked while tasks remain open.

Configurable triage — keyword → case_type/queue/priority/severity rules are added at runtime, no code changes.

Architecture

How Case Management 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.

→

Case Management MCP Server

Validates the request and owns 18 documented tool contracts.

→

Domain system

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

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

Case Management MCP Server architecture diagram from its official repository

Tool catalog

What can an agent ask Case Management 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.

18 named tools

create_case

Create a case (investigation, complaint, dispute, deviation, or incident)

internal write

get_case

Get full case details including status, parties, evidence, notes, tasks, SLA, and audit trail

read only

search_cases

Search/filter cases by text, domain, type, status, assignee, or queue

read only

update_case

Update case priority, severity, queue, or tags

internal write

transition_case

Move a case through valid workflow states

internal write

assign_case

Assign a case to an investigator or handler

internal write

add_note

Add an internal or external note to the case journal

internal write

add_evidence

Attach an evidence/artifact reference to the case chain of custody

internal write

add_task

Add an investigation task or checklist item

internal write

complete_task

Mark an investigation task complete

internal write

link_entity

Link a related entity (account, transaction, meter, claim, batch, device, policy) to the case

internal write

close_case

Close a case with a disposition and resolution summary (legally significant)

internal write

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.

13 internal write5 read only

Defensible by construction — every mutation appends an immutable AuditEntry (actor, action, detail, timestamp). Investigations need a chain of custody.
Gated writes — closing a case (legally significant) requires approval in production; valid workflow transitions are enforced; closure is blocked while tasks remain open.

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.

Long-running tasks

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-case-management

ADK-Rust connection shape

let toolset = McpToolset::from_stdio(
    "mcp-case-management",
    ["mcp-case-management"],
).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