Skip to main content
Glama

Create Issue

create_issue

Create a new issue in MantisBT with required summary, description, project ID, and category; optional fields include priority, severity, assignee, versions, and custom fields.

Instructions

Create a new MantisBT issue. Returns the full created issue object including the assigned id, summary, status, priority, severity, category, reporter, created_at, and view_url.

Required fields: summary, description, project_id, category. All other fields are optional with sensible defaults (priority: "normal", severity: "minor").

Recommended workflow:

  1. Call get_project_categories to obtain a valid category name

  2. Optionally call get_project_versions to obtain version names

  3. Optionally call find_project_member to resolve the assignee's username

Both priority and severity accept canonical English names or localized labels from the connected MantisBT instance — call get_issue_enums to see all available values.

For the handler, prefer the username field (resolved server-side) over handler_id when working interactively.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
handlerNoMantisBT login name of the assignee. The server resolves the name to a user ID from the project member list. Use find_project_member or get_project_users to look up valid login names.
summaryYesIssue summary/title (required)
versionNoAffected product version name. Use get_project_versions to list available version names for the project.
categoryYesCategory name (required). Use get_project_categories to list available categories for the project.
priorityNoPriority level. Canonical English names: none, low, normal, high, urgent, immediate. Default: "normal". Use get_issue_enums to see localized labels.normal
severityNoSeverity level. Canonical English names: feature, trivial, text, tweak, minor, major, crash, block. Default: "minor". Use get_issue_enums to see localized labels.minor
handler_idNoNumeric user ID of the assignee. Alternative to the handler field — use one or the other, not both.
project_idYesProject ID the issue belongs to — use list_projects to discover project IDs
view_stateNoVisibility of the issue: "public" (visible to all, default) or "private" (restricted to higher-access users).
descriptionYesDetailed issue description (required). Do not create issues without a description. Plain text or Markdown.
custom_fieldsNoCustom field values: [{field: {id|name}, value: "<string>"}]. Use get_issue_fields or get_metadata to discover available custom fields per project.
target_versionNoTarget fix version — version in which the issue is planned to be resolved. Use get_project_versions to list available version names.
reproducibilityNoHow reliably the issue reproduces. Canonical English names: always, sometimes, random, have not tried, unable to reproduce, N/A. Use get_issue_enums to see localized labels.
fixed_in_versionNoVersion in which the issue was fixed. Use get_project_versions to list available version names.
steps_to_reproduceNoStep-by-step instructions to reproduce the issue. Plain text or Markdown.
additional_informationNoAdditional context or notes about the issue. Plain text or Markdown.
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are consistent (readOnlyHint=false, idempotentHint=false, destructiveHint=false). Description adds that the tool creates an issue and returns the full object with id, summary, etc. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured: purpose/return first, then required fields, then workflow, then parameter notes. Every sentence adds value; no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 16 parameters and no output schema, the description covers return values and provides workflow guidance. Slightly missing error handling or failure cases, but sufficient for agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds value by explaining canonical vs localized names for priority/severity, recommending get_issue_enums, and clarifying handler vs handler_id usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a new MantisBT issue' with a specific verb and resource. It distinguishes from sibling tools like update_issue and delete_issue by focusing on creation and describing the returned object.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit workflow: call get_project_categories first, optionally get_project_versions and find_project_member. Also explains when to use handler vs handler_id, and mentions sensible defaults for optional fields.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/dpesch/mantisbt-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server