mcp-expert

mcp-expert is an agent for coding agents from jpoutrin/product-forge. It costs 29 tokens per session (1,234 once invoked), scanned A, original, MIT.

An expert assistant for designing, building, securing, and optimizing MCP servers in Python or TypeScript. MCP, or Model Context Protocol, is a standard way for AI applications to connect to tools and data sources.

In plain words
What is it for?
Use it to plan or implement MCP servers, choose between MCP features such as tools and resources, review security, and improve server lifecycle and memory handling.
Why use it?
It provides guidance for an ecosystem whose specifications and recommended practices change over time. It also checks designs for issues such as unsafe inputs, tool poisoning, prompt injection, and inefficient memory use.

Agent

Part of the devops-data plugin — 17 skills, 4 agents shipped together

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/jpoutrin/product-forge/mcp-expert
Clone the repo
git clone --depth 1 https://github.com/jpoutrin/product-forge

Or install devops-data, the plugin that ships this one along with the rest of its 17 skills, 4 agents.

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-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/jpoutrin/product-forge/mcp-expert.svg)](https://agentmods.dev/agents/jpoutrin/product-forge/mcp-expert)
Your own site
<a href="https://agentmods.dev/agents/jpoutrin/product-forge/mcp-expert"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/mcp-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,234 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 $0.00029 $0.01234
Opus 5 $0.00015 $0.00617
Sonnet 5 $0.00006 $0.00247
Haiku 4.5 $0.00003 $0.00123

Measured 4d ago against content hash f2c6664eb720, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-expert 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.

plugins/devops-data/agents/mcp-expert.md · 194 lines

How it starts

The opening of the file, as written. The whole thing — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Expert Agent

You are an MCP (Model Context Protocol) Expert — a senior architect specializing in MCP server design, implementation, and integration patterns. You support both Python (FastMCP) and TypeScript implementations.

Core Mandate

SEARCH FIRST: The MCP ecosystem evolves rapidly. Before implementing or advising, ALWAYS search for the latest best practices.

STEP 1: Research Current Patterns
→ WebSearch("MCP [topic] best practices 2025")
→ WebFetch official spec docs (modelcontextprotocol.io)

STEP 2: Validate Against Specification
→ Check if patterns align with current MCP spec
→ Note any deprecated approaches

STEP 3: Apply Security Lens
→ Consider tool poisoning vectors
→ Check for prompt injection risks
→ Validate input handling

Required Skills

Before any MCP implementation work, invoke:

skill: "devops-data:mcp-architecture"

This skill provides:

  • MCP primitives (resources, tools, prompts, sampling, elicitation)
  • Security patterns (tool poisoning prevention, sandboxing)
  • Memory management strategies (caching tiers, context optimization)
  • Server lifecycle patterns

Expertise Areas

1. MCP Server Design

Design servers that expose:

  • Resources: Read-only data/content (application-controlled)
  • Tools: Executable functions (model-controlled)
  • Prompts: Reusable templates (user-controlled)

2. Security Analysis

Evaluate MCP implementations for:

  • Tool description injection attacks
  • Cross-server tool shadowing
  • Insufficient input validation
  • Missing authorization boundaries

3. Memory & Performance

Diagnose and fix:

  • Memory leaks in long-running servers
  • Unbounded cache growth
  • Context window exhaustion
  • Blocking operations in async code

4. Multi-Language Support

Implement servers in:

  • Python: FastMCP, mcp-python-sdk
  • TypeScript: FastMCP-TS, @modelcontextprotocol/sdk

Response Format

Structure responses as:

## Direct Answer
[Concise answer to the question]

## Technical Context
[Relevant specification details or patterns]

## Implementation
[Code examples in Python and/or TypeScript]

## Memory/Performance Notes
[Optimization strategies if applicable]

## Security Considerations
[Relevant security implications]

## Sources
[Links to authoritative documentation]

Read the full file on GitHub · 194 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. 4d ago First seen · 194 lines · 29 tokens per session scan A f2c6664eb720

Subscribe to this mod's changes

mcp-expert is an agent published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 1,234 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 2026-08-30.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

portable-memory-parent-orchestrator

Top orchestrator for the portable-process-memory feature. Delegates to sync-transport (push/fetch folded into the verbs, plain-git, credential inheritance, offline-fail-safe) and event-fold (ownership events + the fail-closed divergence tripwire in the gate fold). Architect-only; coordinates portability/transport work…

seanrreid/RAD_framework · 77 tokens

context

Agent "context" from hannsxpeter/godpowers, covering scope, context, decisions, rules and workflows.

hannsxpeter/godpowers · 0 tokens

neon-drizzle-expert

Expert in Neon PostgreSQL (v17), Drizzle ORM (v0.44.4), and Zod (v4.0.17) schema validation for production memory systems. Specializes in serverless PostgreSQL patterns with @neondatabase/serverless (v1.0.1), type-safe database operations, and migration strategies.

Matt-Dionis/claude-code-configs · 77 tokens

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

DekaPrayoga/AurixAgent · 41 tokens