Skip to main content
Glama
Inflectra Spira MCP Server

Inflectra Spira MCP Server

Official
by Inflectra

MCP Inflectra Spira Server

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.


Table of Contents


Related MCP server: TestRail MCP Server

Quick Start

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"

Configuration

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

SPIRA_CREATE_TAGS

No

Comma-separated tag string merged into Tags on every artifact the MCP creates; empty or unset disables injection

SPIRA_UPDATE_TAGS

No

Comma-separated tag string merged into Tags on every artifact the MCP updates; empty or unset disables injection


Available Tools

13 tools organized by scope. All data-retrieval tools return structured JSON with field projection, filtering, and a consistent response envelope.

Search Tools

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)

Write Tools

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)

Workspace & Configuration Tools

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)


Usage Examples

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

License

MIT — see LICENSE.

Built with MCP Python SDK · Spira REST API v7.0

Available Tools

13 tools
create_associationA

Link two artifacts. association_type: related-to, depends-on, coverage.

Valid source->dest (related-to/depends-on): document->automation_host,incident,release,requirement,risk,task,test_case,test_run,test_set,test_step; incident->incident,requirement,risk,task,test_step; release->release,requirement; requirement->incident,release,requirement,risk; risk->incident,requirement,risk,test_case; task->incident,task; test_case->risk,task. Coverage: release->test_case, requirement<->test_case, requirement->test_step.

Inputs: dest_artifact_id (required), dest_artifact_type (required), source_artifact_id (required), source_artifact_type (required… Returns: result

create_commentB

Add a comment to an artifact.

Use product_get_artifact with include=["comments"] to read existing comments.

Inputs: text (required), artifact_id (required), artifact_type (required), product_id. Returns: result

get_artifact_schemaA
Read-only

Returns the field schema for a Spira artifact type as JSON.

artifact_type: task, incident, requirement, test_case, release, risk, test_set, test_run, automation_host, capability, milestone Returns: {artifact_type, fields: [{name, type, description}]} or {error, valid_types}.

Inputs: artifact_type (required). Returns: result

mywork_search_artifactsC
Read-only

Retrieve the current user's assigned artifacts.

artifact_type: [incident, task, test_case, requirement, test_set]

Inputs: limit, fields, offset, status, +2 more. Returns: result

product_create_artifactA

Create artifacts in a Spira product.

Name and Description are required for most types. Sub-artifacts (test_step, mitigation, requirement_step) require parent_id. Builds require release_id. Use get_artifact_schema to discover optional writable fields.

Inputs: fields (required), artifact_type (required), parent_id, product_id, +1 more. Returns: result

product_get_artifactA
Read-only

Retrieve a single artifact by ID from a Spira product.

artifact_type: incident|task|test_case|requirement|risk|release|test_set|test_run|automation_host|build|document release_id: required when artifact_type='build' include: test_steps (test_case), mitigations (risk), steps (requirement), comments (most types), associations (most types), coverage (requirement, test_case, release)

Inputs: artifact_id (required), artifact_type (required), include, product_id, +1 more. Returns: result

product_record_test_runB

Record an automated test result in Spira.

execution_status_id: 1=Failed, 2=Passed, 3=Not Run, 4=N/A, 5=Blocked, 6=Caution. test_case_id is the numeric ID without TC prefix (e.g. 12 for TC:12). short_message should be 50 chars or less.

Inputs: test_name (required), error_count (required), long_message (required), test_case_id (required), +3 more. Returns: result

product_search_artifactsB
Read-only

Search artifacts in a Spira product.

filters: [{{"field": "Name", "operator": "contains", "value": "login"}}] — use get_artifact_schema for fields. release_id: required for builds.

Inputs: artifact_type (required), state, fields, status, +12 more. Returns: result

product_update_artifactA

Update a single artifact by ID in a Spira product.

Sub-artifacts (test_step, mitigation, requirement_step) require parent_id. Use get_artifact_schema to discover writable fields for each type. To clear a custom property, set its value to null.

Inputs: fields (required), artifact_id (required), artifact_type (required), parent_id, +1 more. Returns: result

program_search_artifactsC
Read-only

Search artifacts in a Spira program.

artifact_type: [capability, milestone] program_id: required, no default

Inputs: program_id (required), artifact_type (required), fields, status, +4 more. Returns: result

template_get_metadataA
Read-only

Retrieves template metadata sections for a product template.

template_id: numeric ID (e.g. 45 for PT:45). metadata_type: sections to fetch (see enum). Omit for all. artifact_type: filter to one kind (e.g. "Requirement"). Omit for all. Some sections are artifact-specific (e.g. severities→Incident, importances→Requirement). Returns JSON: {template_id, sections, warnings}.

Inputs: template_id (required), artifact_type, metadata_type. Returns: result

workspace_getB
Read-only

Retrieve a single workspace entity by its numeric ID.

workspace_type: 'product', 'program', 'product_template'

Inputs: workspace_id (required), workspace_type (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 13 tools

    Disambiguation4/5

    Most tools target distinct scopes/actions, but the presence of three search_artifacts tools (mywork, product, program) and several get-style tools (product_get_artifact, workspace_get, template_get_metadata, get_artifact_schema) creates some potential for misselection if the agent does not carefully check scope. The descriptions do help clarify boundaries, so confusion is limited to a few adjacent tools.

    Naming Consistency4/5

    Names are predominantly snake_case and follow a scope_verb_noun pattern for product/program/template tools, but several tools omit the scope prefix (create_comment, create_association, get_artifact_schema) and workspace_search/workspace_get omit the resource noun. These are minor deviations in an otherwise predictable convention.

    Tool Count5/5

    The 13 tools are well within a reasonable range for a multi-resource artifact management server, and each tool appears to serve a distinct role in search, retrieval, creation, updates, test recording, linking, commenting, or schema discovery. No tool feels redundant or extraneous.

    Completeness4/5

    The surface covers search/retrieval/creation/update across products, programs, workspaces, artifacts, comments, associations, and test runs, but lacks delete operations for artifacts, comments, and associations. These are minor gaps that agents can largely work around, but full lifecycle coverage would require them.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Enables AI assistants to interact with TestRail test management systems through comprehensive API integration. Supports retrieving and updating test cases, projects, suites, runs, and results, plus adding attachments and managing test data through natural language commands.
      18
      31 npm
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Enables AI assistants to interact directly with TestRail instances for managing test projects, suites, cases, runs, results, plans, milestones, and attachments through the TestRail API with secure authentication.
      77
      55 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to interact with Targetprocess for search, create, update, and query of entities like User Stories and Bugs, with support for complex filters and data model discovery.
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Enables AI assistants to interact with TestRail test management system, supporting full CRUD operations on projects, suites, sections, test cases, runs, results, plans, and milestones.
      35
      327 npm
      1
      MIT