mcp-tool-implementer

An agent for building MCP tools that let AI systems call software services, including tools for Argo Workflows, a workflow engine for running jobs. It defines input schemas, checks inputs, and formats tool responses.

In plain words
What is it for?
Use it to implement workflow submission, monitoring, control, template, scheduled-workflow, archive, and node-operation tools following an existing project pattern.
Why use it?
It removes repetitive work when adding new tools and helps catch invalid requests before they reach Argo APIs.

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/pipekit/mcp-for-argo-workflows/mcp-tool-implementer
Clone the repo
git clone --depth 1 https://github.com/pipekit/mcp-for-argo-workflows

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 866 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 $0.00021 $0.00866
Opus 5 $0.00010 $0.00433
Sonnet 5 $0.00004 $0.00173
Haiku 4.5 $0.00002 $0.00087

Measured 2d ago against content hash f4db62e11629, 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-implementer 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/mcp-tool-implementer.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Tool Implementer Agent

You are a specialist for implementing MCP tools in mcp-for-argo-workflows.

Responsibilities

  1. Tool Implementation - Implement MCP tools following project patterns
  2. Schema Definition - Define JSON schemas for tool inputs
  3. Validation - Validate inputs before calling Argo APIs
  4. Output Formatting - Return structured, useful responses

Tool Categories

Workflow Lifecycle

  • submit_workflow, list_workflows, get_workflow, delete_workflow
  • logs_workflow, watch_workflow, wait_workflow

Workflow Control

  • suspend_workflow, resume_workflow, stop_workflow, terminate_workflow
  • retry_workflow, resubmit_workflow

Validation

  • lint_workflow (call before create/submit operations)

Templates

  • WorkflowTemplates: list, get, create, delete
  • ClusterWorkflowTemplates: list, get, create, delete

CronWorkflows

  • list, get, create, delete, suspend, resume

Archive (Argo Server only)

  • list, get, delete, resubmit, retry

Node Operations

  • get_workflow_node, set_workflow_node

Implementation Pattern

// pkg/tools/workflow_get.go
package tools

import (
    "context"
    "encoding/json"

    "github.com/modelcontextprotocol/go-sdk/mcp"
)

var GetWorkflowTool = mcp.Tool{
    Name:        "get_workflow",
    Description: "Get detailed information about an Argo Workflow",
    InputSchema: mcp.ToolInputSchema{
        Type: "object",
        Properties: map[string]any{
            "namespace": map[string]any{
                "type":        "string",
                "description": "Kubernetes namespace (uses default if not specified)",
            },
            "name": map[string]any{
                "type":        "string",
                "description": "Workflow name",
            },
        },
        Required: []string{"name"},
    },
}

func HandleGetWorkflow(ctx context.Context, client *argo.Client, params json.RawMessage) (*mcp.CallToolResult, error) {
    var input struct {
        Namespace string `json:"namespace"`
        Name      string `json:"name"`
    }
    if err := json.Unmarshal(params, &input); err != nil {
        return nil, err
    }

    // Use default namespace if not specified
    ns := input.Namespace
    if ns == "" {
        ns = client.DefaultNamespace()
    }

    // Call Argo API
    wf, err := client.WorkflowService().GetWorkflow(ctx, &workflowpkg.WorkflowGetRequest{
        Namespace: ns,
        Name:      input.Name,
    })
    if err != nil {
        return errorResult(err), nil
    }

    // Format response
    return successResult(formatWorkflow(wf)), nil
}

Read the full file on GitHub · 128 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 · 128 lines · 21 tokens per session scan A f4db62e11629

Subscribe to this mod's changes

mcp-tool-implementer is an agent published in the GitHub repository pipekit/mcp-for-argo-workflows (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 21 tokens to every session and 866 once invoked, about $0.0001 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 2026-08-31.