What is mcpc-builder-agent?

An agent that creates custom tools by selecting servers and tools from the mcpc.tech registry, a catalogue of tool connections for agents.

Use it to find MCP servers, choose their tools, and compose interactive, autonomous, or coding-agent tool setups.

It guides the search, checks required environment variables, and assembles the selected connections into an agent configuration.

mcpc-builder-agent — Agent for Claude Code by mcpc-tech/mcpc

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.

Clone the repo

git clone --depth 1 https://github.com/mcpc-tech/mcpc

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/mcpc-tech/mcpc/mcpc-builder-agent/github.svg)](https://agentmods.dev/agents/mcpc-tech/mcpc/mcpc-builder-agent)

Your own site

<a href="https://agentmods.dev/agents/mcpc-tech/mcpc/mcpc-builder-agent"><img src="https://agentmods.dev/badge/agents/mcpc-tech/mcpc/mcpc-builder-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/mcpc-tech/mcpc/mcpc-builder-agent"><img src="https://agentmods.dev/badge/agents/mcpc-tech/mcpc/mcpc-builder-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 525 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00072	$0.00525
Opus 5.5	$0.00029	$0.00210
Sonnet 5.5	$0.00014	$0.00105
Haiku 4.5	$0.00007	$0.00052

Measured 1mo ago against content hash 2a09ea54a2a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcpc-builder-agent 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 1mo 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.

packages/mcpc-builder/agents/mcpc-builder-agent.md · 62 lines

What it actually says

Manual

Workflow

Search: search_mcp_servers - ALWAYS append "-mcp" suffix (e.g., "github-mcp", "filesystem-mcp")
- serverQuery: server name keyword
- toolQuery: tool name keyword (e.g., "read_file")
Check: get_env_var_schemas - get required API keys/tokens before composition
Compose: compose_mcpc_config - generate config with selected servers/tools

compose_mcpc_config Parameters

serverName: Agent identifier (e.g., "code-reviewer")
toolName: Main tool name users invoke
description: What the agent does
serverDeps: Full server names from search results
toolSelection: [{ serverName, tools }] - use "__ALL__" or specific tool array
mode: "agentic" (interactive) | "ai_sampling" (autonomous) | "ai_acp" (coding agents)

Example

{
  "serverName": "code-reviewer",
  "toolName": "review_code",
  "description": "Reviews code using GitHub and filesystem tools",
  "serverDeps": [
    "github.com/modelcontextprotocol/servers/github",
    "io.github.wonderwhy-er/desktop-commander"
  ],
  "toolSelection": [
    { "serverName": "github", "tools": ["get_file_contents", "list_commits"] },
    { "serverName": "desktop-commander", "tools": ["read_file"] }
  ]
}

Rules

Always search before suggesting - don't assume server availability
Check env vars before composition - user needs prerequisites
Prefer specific tool selection over __ALL__ - avoid bloating agents
Prefer official servers: github.com/modelcontextprotocol/servers/*
Output includes install commands for VS Code, Cursor, Claude Code, Codex, Gemini

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.

1mo ago First seen · 62 lines · 72 tokens per session scan A 2a09ea54a2a1

Subscribe to this mod's changes

mcpc-builder-agent is an agent published in the GitHub repository mcpc-tech/mcpc (104 stars, last pushed 13d ago), licensed MIT. It adds 72 tokens to every session and 525 once invoked, about $0.0003 per session on Opus 5.5. 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.

Building agents agentic-mcp code-mode-mcp mcp-compose mcp-server mcpc

FAI Browser Agent

Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.

frootai/frootai · 41 tokens

chainaware-token-launch-auditor

Audits a new token launch for launchpads by combining rug pull detection on the contract with fraud and behavioral analysis on the deployer wallet. Returns a composite Launch Safety Score, a APPROVED / CONDITIONAL / REJECTED listing verdict, a public-facing safety badge, and specific conditions the launchpad should…

ChainAware/behavioral-prediction-mcp · 247 tokens

mcpc-builder-agent