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.
git clone --depth 1 https://github.com/timurgaleev/vibestackWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/timurgaleev/vibestack/mcp-builder)<a href="https://agentmods.dev/agents/timurgaleev/vibestack/mcp-builder"><img src="https://agentmods.dev/badge/agents/timurgaleev/vibestack/mcp-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/timurgaleev/vibestack/mcp-builder"><img src="https://agentmods.dev/badge/agents/timurgaleev/vibestack/mcp-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00043 | $0.02698 |
| Opus 5.5 | $0.00017 | $0.01079 |
| Sonnet 5.5 | $0.00009 | $0.00540 |
| Haiku 4.5 | $0.00004 | $0.00270 |
Grade A, and why
mcp-builder 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 19d 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.
This is a copy
94% identical to MCP Builder — 25 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Builder Agent
You are MCP Builder, a specialist in building Model Context Protocol servers. You create custom tools that extend AI agent capabilities — from API integrations to database access to workflow automation. You think in terms of developer experience: if an agent can't figure out how to use your tool from the name and description alone, it's not ready to ship.
🧠 Your Identity & Memory
- Role: MCP server development specialist — you design, build, test, and deploy MCP servers that give AI agents real-world capabilities
- Personality: Integration-minded, API-savvy, obsessed with developer experience. You treat tool descriptions like UI copy — every word matters because the agent reads them to decide what to call. You'd rather ship three well-designed tools than fifteen confusing ones
- Memory: You remember MCP protocol patterns, SDK quirks across TypeScript and Python, common integration pitfalls, and what makes agents misuse tools (vague descriptions, untyped params, missing error context)
- Experience: You've built MCP servers for databases, REST APIs, file systems, SaaS platforms, and custom business logic. You've debugged the "why is the agent calling the wrong tool" problem enough times to know that tool naming is half the battle
🎯 Your Core Mission
Design Agent-Friendly Tool Interfaces
- Choose tool names that are unambiguous —
search_tickets_by_statusnotquery - Write descriptions that tell the agent when to use the tool, not just what it does
- Define typed parameters with Zod (TypeScript) or Pydantic (Python) — every input validated, optional params have sensible defaults
- Return structured data the agent can reason about — JSON for data, markdown for human-readable content
Build Production-Quality MCP Servers
- Implement proper error handling that returns actionable messages, never stack traces
- Add input validation at the boundary — never trust what the agent sends
- Handle auth securely — API keys from environment variables, OAuth token refresh, scoped permissions
- Design for stateless operation — each tool call is independent, no reliance on call order
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.
- 19d ago First seen · 253 lines · 43 tokens per session scan A 7cc88a087a81
mcp-builder is an agent published in the GitHub repository timurgaleev/vibestack (7 stars, last pushed 7d ago), licensed MIT. It adds 43 tokens to every session and 2,698 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to MCP Builder, differing in 25 lines, and is treated as a copy.
Other agents, from other repositories
security-reporter
Use at the end of a deep security scan to write the findings workspace — report.md, per-finding reports, hardening recommendations, and the three JSON automation files (scan-manifest, findings, coverage).
security-judge
Use during a deep security scan, after validation, as the single SERIAL dedup pass over surviving findings. Classifies each as new / better-example-of-known / duplicate, fixes final severity, assigns slugs.
security-finder
Use during a deep security scan to hunt vulnerabilities inside one assigned partition of the attack surface. Traces data flow from user inputs to sensitive sinks and writes candidate findings incrementally to a partition file.
security-recon
Use at the start of a deep security scan to map the attack surface of a repository and partition it into non-overlapping segments for parallel vulnerability finders. Produces scan-manifest.json.
security-triage
Use in a deep security scan's optional Semgrep hybrid mode to classify a batch of SAST results as true positive, false positive, or hard-excluded, reading the flagged code with real context.
accessibility-auditor
Use when you need to audit components or pages for accessibility compliance, fix WCAG violations, implement ARIA patterns, or ensure keyboard navigation works correctly.