Skip to main content
Glama
mcp-github-project-manager

mcp-github-project-manager

by kunwarVivek

Manage Issues

manage_issues
Destructive

Create, list, update, and search GitHub issues, manage comments, drafts, and sub-issues, and track dependencies using an action-based interface.

Instructions

Manage GitHub Issues: create, list, get, update issues; manage comments and drafts; search with advanced filters; manage sub-issues. Use the action field to select the operation.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "manage_issues"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNo
repoNo
sortNo
typeNoThe issue type: a native organization issue type (its name or `IT_…` id) or one of bug/feature/enhancement/documentation for the label emulation
afterNo
firstNo
limitNo
ownerNo
queryNo
titleNo
actionYesThe issue operation to perform
cursorNoCursor from a previous page's `nextCursor`; omit for the first page
itemIdNo
labelsNo
statusNo
issueIdNo
perPageNo
assigneeNo
priorityNo
assigneesNo
commentIdNo
directionNo
milestoneNo
projectIdNo
assigneeIdsNo
descriptionNo
issueNumberNo
milestoneIdNo
draftIssueIdNo
replaceParentNo
idempotencyKeyNoIdempotency key (1-128 chars) for create actions: retrying with the same key and arguments returns the first result instead of creating a duplicate; reusing it with different arguments is an error. Kept for 24 hours.
subIssueNumberNo
blockingIssueIdNoThe issue that blocks the given issue (native `blocked by` edge)
afterIssueNumberNo
parentIssueNumberNo
dependencyDirectionNo`blocked_by` lists the issues that block this one, `blocking` the ones it blocks

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv4.0.0
    • addedInput schema / properties / cursor
      Added value: +{
      +  "description": "Cursor from a previous page's `nextCursor`; omit for the first page",
      +  "type": "string"
      +}
    • addedInput schema / properties / idempotencyKey
      Added value: +{
      +  "description": "Idempotency key (1-128 chars) for create actions: retrying with the same key and arguments returns the first result instead of creating a duplicate; reusing it with different arguments is an error. Kept for 24 hours.",
      +  "maxLength": 128,
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. Addedv3.0.0

TDQS

B3.2/5.0
Behavior2/5

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

Annotations already tell the agent this is destructive, non-idempotent, and open-world, which sets a lower bar. However, the tool bundles 22 actions with very different risk profiles and the description discloses none of them — it never says that delete_comment, delete_draft, remove_sub_issue, or remove_blocker are irreversible, nor which actions honor idempotencyKey. For a destructive mega-tool, this is a meaningful gap.

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

Conciseness4/5

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

Two tight sentences, front-loaded with the verb and capability list, ending with the dispatch instruction. No wasted words. The brevity is arguably over-aggressive for a 22-action tool, but nothing extraneous is present.

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

Completeness2/5

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

For a dispatcher spanning 22 actions, 36 parameters (17% described), no output schema, and destructive semantics, the description covers only a fraction of what an agent needs. It never maps parameters to actions, lists required per-action inputs, or explains pagination, so successful invocation depends almost entirely on guesswork from the schema.

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 17%, so the description must compensate and it does not. Beyond naming the required `action` dispatcher, it gives no meaning to repo, owner, issueNumber, cursor, perPage, type, dependencyDirection, or the many action-specific fields — an agent must infer which of the 36 parameters apply to each action purely from the schema, where most have no description either. This warrants the lowest tier. (Corrected score: 2.)

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

Purpose4/5

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

Names a specific verb and resource ('Manage GitHub Issues') and enumerates the main capability clusters: CRUD, comments, drafts, search, sub-issues. It is clearly distinguishable from siblings like manage_prs or manage_labels. It falls short of 5 because the enumeration is incomplete against the 22-action enum — dependencies/blockers, issue types, and reprioritization are never hinted at.

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

Usage Guidelines2/5

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

The only guidance is 'Use the `action` field to select the operation,' which is a mechanical instruction, not a when-to-use rule. There is no advice on choosing between 22 actions, no note on which actions require which parameters, and no differentiation from siblings such as manage_project (for project fields) or manage_labels (for label definitions).

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