Overview

The Inflectra Spira MCP server implements the Model Context Protocol (MCP) to let AI assistants and agentic tools interact with SpiraTest / SpiraTeam / SpiraPlan. It translates high-level assistant requests into calls against the Spira REST API so developers, QA, and automation systems can query and update Spira artifacts (requirements, test cases, incidents, tasks, releases, etc.) using conversational or programmatic workflows.

This server is useful when you want to integrate an assistant (for example, Claude or another MCP-capable agent) with your ALM instance to: surface the work assigned to a user, record automated test and build results, produce machine-readable product specifications, or automate common product- and program-level operations without hand-writing API plumbing.

Features

My Work: list and manage artifacts assigned to the current user (Tasks, Requirements, Incidents, Test Cases, Test Sets).
Workspaces: enumerate and modify Programs, Products, and Product Templates.
Program Artifacts: access program backlog items such as Capabilities and Milestones.
Product Artifacts: full CRUD-style operations for Requirements, Releases, Test Cases, Test Sets, Test Runs, Tasks, Incidents, and Automation Hosts.
Template Configuration: retrieve artifact types and custom properties from product templates.
Automation: record automated test runs and CI/CD build results into Spira.
Specifications: export product specification files (requirements.md, design.md, tasks.md, test-cases.md) suitable for agentic AI tooling and downstream automation.

Installation / Configuration

Prerequisites:

Python 3.10+
Active Inflectra Spira account with an API key (RSS Token)
mcp CLI (for local development and installation into MCP hosts)

Clone and install for development:

git clone https://github.com/Inflectra/mcp-server-spira.git
cd mcp-server-spira

# Install editable dev dependencies
pip install -e ".[dev]"

Install from PyPI:

pip install mcp-server-spira

Environment variables Create a .env file at the project root (or export these variables in your environment):

INFLECTRA_SPIRA_BASE_URL=https://mycompany.spiraservice.net
[email protected]
INFLECTRA_SPIRA_API_KEY=your_rss_token_here

Running the server

Development with MCP inspector:

mcp dev src/mcp_server_spira/server.py

Run directly (production/test):

python -m mcp_server_spira

Install into a desktop MCP host (e.g., Claude Desktop):

mcp install src/mcp_server_spira/server.py --name "Inflectra Spira Server"

Adding the server to a Cline configuration If your client uses a JSON configuration (for example cline_mcp_settings.json), add an entry for the server:

{
  "mcpServers": {
    "inflectra-spira": {
      "autoApprove": [
        "get_my_incidents",
        "get_my_tasks"
      ],
      "path": "src/mcp_server_spira/server.py"
    }
  }
}

Available Tools

The MCP server exposes logical groups of tools. Example categories and representative operations:

Category	Representative tools / operations
My Work	get_my_tasks, get_my_requirements, get_my_incidents, get_my_test_cases, get_my_test_sets
Workspaces	list_programs, list_products, get_product_template
Program Artifacts	list_capabilities, list_milestones
Product Artifacts	list_requirements, create_incident, list_test_cases, record_test_run
Template Configuration	get_artifact_types, get_custom_properties
Automation	record_automated_test_run, record_build
Specifications	get_specification_requirements, get_specification_design, get_specification_tasks, get_specification_test_cases

Use an MCP-capable client or the mcp CLI to invoke these tools once the server is running and authorized.

Use Cases

View your active work
- Scenario: A developer asks the assistant “What test cases are assigned to me this sprint?”
- Flow: Assistant calls get_my_test_cases → server queries Spira → returns assigned test cases filtered by user and iteration.
Report CI build and test results
- Scenario: A CI pipeline finishes and wants to push results to Spira.
- Flow: CI job invokes record_automated_test_run and/or record_build with test and build metadata → Spira test runs and build records created/updated.
Create an incident from a customer bug report
- Scenario: Support files a new bug that should be logged as an Incident.
- Flow: Assistant calls create_incident with summary, steps, severity, product → server creates the incident and returns the new artifact ID and link.
Generate product specification files for agentic generation
- Scenario: You want to feed formal product specs to an agentic tool (e.g., to scaffold code).
- Flow: Call get_specification_requirements, get_specification_design, etc., to produce requirements.md, design.md, tasks.md and test-cases.md for the product.
Inspect and adjust template configuration
- Scenario: A release manager needs to ensure custom properties are available for automation.
- Flow: get_artifact_types and get_custom_properties return the template schema for validation or automated migration.

Tips and Troubleshooting

Ensure the API key (RSS Token) is active in your Spira user profile; authentication failures are the most common issue.
Use the MCP inspector during development to see incoming/outgoing messages and to experiment with tool invocations.
When running in a hosted client (Claude Desktop, Cline, etc.), confirm the server path and autoApprove list in the client configuration to enable smooth automation.
For large product exports (full specification dumps), expect more API calls — run these operations during off-peak windows if your Spira instance rate-limits API access.

For code examples, issue-level details, and the full list of operations, consult the repository: https://github.com/Inflectra/mcp-server-spira.

Connect to Inflectra Spira MCP Server