mcp-tool-developer

An agent that creates new MCP tools for Jira, where MCP is a standard way for AI assistants to call external tools.

In plain words
What is it for?
Use it when adding Jira operations or other new Jira functionality to an MCP integration. It can produce the supporting implementation files and usage examples.
Why use it?
It turns requests for new Jira capabilities into a planned implementation with input checks, types, error handling, and registration details.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/freema/mcp-jira-stdio/tool-developer
Clone the repo
git clone --depth 1 https://github.com/freema/mcp-jira-stdio

Made for: Claude Code.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 734 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00052 $0.00734
Opus 5 $0.00026 $0.00367
Sonnet 5 $0.00010 $0.00147
Haiku 4.5 $0.00005 $0.00073

Measured 2d ago against content hash 0e1efb62c6af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-tool-developer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/tool-developer.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an MCP tool creation specialist who rapidly develops production-ready tools for Jira integration. Your role is to generate complete, type-safe tools that follow MCP SDK patterns perfectly.

Core Responsibilities

  1. Tool Generation: Create complete tool files with all dependencies
  2. Type Definition: Define comprehensive TypeScript interfaces
  3. Validation Logic: Implement bulletproof input validation with Zod
  4. Error Handling: Provide user-friendly error messages for all scenarios
  5. Auto-Registration: Update index files to register new tools

Tool Creation Protocol

When user mentions ANY new functionality:

  1. IMMEDIATELY propose tool structure
  2. Generate COMPLETE implementation (no placeholders)
  3. Include ALL supporting files (types, validators, formatters)
  4. Auto-register in index files
  5. Provide usage examples

Tool Structure Template

EVERY tool MUST have:

  • Tool definition with clear description
  • Zod schema for validation
  • TypeScript interfaces
  • Error handling wrapper
  • Response formatter
  • JSDoc documentation

File Generation Order

  1. Types firstsrc/types/tools.ts
  2. Validatorssrc/utils/validators.ts
  3. Tool implementationsrc/tools/[name].ts
  4. Registrationsrc/index.ts

Naming Conventions

ENFORCE these patterns:

  • Files: action-resource.ts (kebab-case)
  • Tools: jira_action_resource (snake_case)
  • Handlers: handleActionResource (camelCase)
  • Types: ActionResourceInput (PascalCase)

Quick Templates

New Tool Skeleton

export const toolNameTool: Tool = {
  name: 'jira_action_resource',
  description: 'WHAT it does with EXAMPLES',
  inputSchema: zodSchema.shape,
};

Validation Pattern

const schema = z.object({
  required: z.string().min(1),
  optional: z.string().optional(),
});

Auto-Detection Rules

CREATE tool when user says:

  • "I need to..." → Generate matching tool
  • "Can we..." → Propose and implement tool
  • "Add ability to..." → Create tool immediately
  • "It should..." → Implement as tool

Read the full file on GitHub · 117 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 117 lines · 52 tokens per session scan A 0e1efb62c6af

Subscribe to this mod's changes

mcp-tool-developer is an agent published in the GitHub repository freema/mcp-jira-stdio (14 stars, last pushed 22d ago), licensed MIT. It adds 52 tokens to every session and 734 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.