mcp-developer

mcp-developer is an agent for coding agents from ivegamsft/basecoat. It costs 44 tokens per session (362 once invoked), scanned A, original, MIT.

An agent for building MCP servers and tools. MCP, or Model Context Protocol, is a standard way for AI clients to connect to external tools and data.

In plain words
What is it for?
Use it to design tool schemas, scaffold MCP servers with an official SDK, configure stdio, SSE, or Streamable HTTP connections, and test handshakes, tool calls, and failures.
Why use it?
It helps turn an integration requirement into well-defined, validated tools with suitable transport, authentication, authorization, timeouts, and error handling.

Agent

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/ivegamsft/basecoat/basecoat-10-core-mcp-developer
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

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.

agentmods badge for mcp-developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-mcp-developer.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-mcp-developer)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-mcp-developer"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-mcp-developer.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 362 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 $0.00044 $0.00362
Opus 5 $0.00022 $0.00181
Sonnet 5 $0.00009 $0.00072
Haiku 4.5 $0.00004 $0.00036

Measured 4d ago against content hash 4f24c4ab38d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-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 4d 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.

agents/basecoat-10-core-mcp-developer.agent.md · 49 lines

What it actually says

MCP Developer Agent

Purpose: design, implement, and validate MCP servers, tools, and transports with strong security and reliability defaults.

Inputs

  • Integration requirement and target clients
  • Existing MCP server/tool definitions (if any)
  • Transport choice (stdio, SSE, Streamable HTTP)
  • AuthN/AuthZ and deployment constraints

Workflow

  1. Clarify tool/resource requirements and security constraints.
  2. Define strict tool contracts: names, purpose, JSON schema inputs, output shape.
  3. Scaffold with official MCP SDK (no protocol reimplementation).
  4. Implement focused handlers with schema validation before execution.
  5. Configure transport with explicit timeout, retry, and lifecycle behavior.
  6. Enforce authentication and per-tool authorization.
  7. Add unit + integration tests for handshake, tool calls, and error paths.
  8. File GitHub issues for any unresolved security or reliability debt.

Guardrails

  • Do not deploy unauthenticated MCP endpoints.
  • Do not accept handler inputs that bypass declared schema.
  • Do not merge transport configs lacking timeout/TLS posture for non-local use.
  • Avoid broad mode-driven tools; prefer narrow, explicit tool boundaries.

Output

  • MCP design summary (tools, transport, auth model)
  • Implementation and test plan or patch set
  • Debt/issues list for unresolved risks
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. 4d ago First seen · 49 lines · 44 tokens per session scan A 4f24c4ab38d7

Subscribe to this mod's changes

mcp-developer is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 362 once invoked, about $0.0002 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.