A Model Context Protocol (MCP) server enabling AI assistants to interact with Spira by Inflectra.
A Model Context Protocol (MCP) server that lets AI assistants interact with Inflectra Spira — covering project management, test management, and requirements management.
Works with SpiraTest, SpiraTeam, and SpiraPlan.
Install from PyPI:
pip install mcp-server-spira
Add to your MCP client config:
{
"mcpServers": {
"inflectra-spira": {
"command": "python",
"args": ["-m", "mcp_server_spira"],
"env": {
"INFLECTRA_SPIRA_BASE_URL": "https://myinstance.spiraservice.net",
"INFLECTRA_SPIRA_USERNAME": "mylogin",
"INFLECTRA_SPIRA_API_KEY": "{XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXX}"
}
}
}
}
For Cline, add "type": "stdio" to the server config. For Claude Desktop:
mcp install src/mcp_server_spira/server.py --name "Inflectra Spira Server"
Set these environment variables (or use a .env file):
| Variable | Required | Description |
|---|---|---|
INFLECTRA_SPIRA_BASE_URL | Yes | Base URL for your Spira instance |
INFLECTRA_SPIRA_USERNAME | Yes | Your Spira login name |
INFLECTRA_SPIRA_API_KEY | Yes | API Key (RSS Token) from your Spira user profile |
SPIRA_PROJECT_ID | No | Default product ID — avoids passing product_id on every call |
13 tools organized by scope. All data-retrieval tools return structured JSON with field projection, filtering, and a consistent response envelope.
| Tool | Description |
|---|---|
mywork_search_artifacts | Your assigned items (task, incident, requirement, test_case, test_set) with filtering and field projection |
product_search_artifacts | Search artifacts in a product (11 types). Supports cross-product fan-out, server-side filtering, and nested sub-artifact includes. |
product_get_artifact | Single artifact by ID with full details and optional sub-artifact includes |
program_search_artifacts | Search program-level artifacts (capability, milestone) |
| Tool | Description |
|---|---|
product_create_artifact | Create artifacts (incident, task, requirement, test_case, risk, release, test_set, build, test_step, mitigation, requirement_step) |
product_update_artifact | Update existing artifacts |
product_record_test_run | Record automated test results from CI/CD |
create_comment | Add a comment to an artifact |
create_association | Link two artifacts (related-to, depends-on, coverage) |
| Tool | Description |
|---|---|
workspace_search | List products, programs, or product templates with field projection |
workspace_get | Get a single product, program, or template by ID |
template_get_metadata | Types, statuses, priorities, severities, custom properties, and more for a template |
get_artifact_schema | Field schema for any artifact type (local-only, no API call) |
Try these prompts with your AI assistant:
Show me my assigned tasks in Spira
List all products in my Spira instance
Get the open incidents in product 55
Search for critical requirements across products 55 and 60
Get the field schema for incidents
MIT — see LICENSE.
Built with MCP Python SDK · Spira REST API v7.0
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
uvx mcp-server-spiraMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-inflectra-mcp-server-spira": {
"command": "uvx",
"args": [
"mcp-server-spira"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referenceio.github.Inflectra/mcp-server-spira works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.