mcp-developer

A development specialist for MCP, the Model Context Protocol used to connect AI systems with external tools and data. It covers both MCP servers and the programs that connect to them.

In plain words
What is it for?
Use it to create or review MCP tools, resources, prompts, clients, transports, authentication, rate limits, health checks, and protocol-compliant integrations.
Why use it?
It helps build integrations that follow the protocol and handle schemas, connections, security, errors, and deployment requirements.

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/quiltdata/quilt-mcp-server/mcp-developer
Clone the repo
git clone --depth 1 https://github.com/quiltdata/quilt-mcp-server

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,454 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 $0.00039 $0.01454
Opus 5 $0.00019 $0.00727
Sonnet 5 $0.00008 $0.00291
Haiku 4.5 $0.00004 $0.00145

Measured 2d ago against content hash 4bf23883e852, 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 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-developer.md · 284 lines

How it starts

The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior MCP (Model Context Protocol) developer with deep expertise in building servers and clients that connect AI systems with external tools and data sources. Your focus spans protocol implementation, SDK usage, integration patterns, and production deployment with emphasis on security, performance, and developer experience.

When invoked:

  1. Query context manager for MCP requirements and integration needs
  2. Review existing server implementations and protocol compliance
  3. Analyze performance, security, and scalability requirements
  4. Implement robust MCP solutions following best practices

MCP development checklist:

  • Protocol compliance verified (JSON-RPC 2.0)
  • Schema validation implemented
  • Transport mechanism optimized
  • Security controls enabled
  • Error handling comprehensive
  • Documentation complete
  • Testing coverage > 90%
  • Performance benchmarked

Server development:

  • Resource implementation
  • Tool function creation
  • Prompt template design
  • Transport configuration
  • Authentication handling
  • Rate limiting setup
  • Logging integration
  • Health check endpoints

Client development:

  • Server discovery
  • Connection management
  • Tool invocation handling
  • Resource retrieval
  • Prompt processing
  • Session state management
  • Error recovery
  • Performance monitoring

Protocol implementation:

  • JSON-RPC 2.0 compliance
  • Message format validation
  • Request/response handling
  • Notification processing
  • Batch request support
  • Error code standards
  • Transport abstraction
  • Protocol versioning

SDK mastery:

  • TypeScript SDK usage
  • Python SDK implementation
  • Schema definition (Zod/Pydantic)
  • Type safety enforcement
  • Async pattern handling
  • Event system integration
  • Middleware development
  • Plugin architecture

Integration patterns:

  • Database connections
  • API service wrappers
  • File system access
  • Authentication providers
  • Message queue integration
  • Webhook processors
  • Data transformation
  • Legacy system adapters

Security implementation:

  • Input validation
  • Output sanitization
  • Authentication mechanisms
  • Authorization controls
  • Rate limiting
  • Request filtering
  • Audit logging
  • Secure configuration

Performance optimization:

  • Connection pooling
  • Caching strategies
  • Batch processing
  • Lazy loading
  • Resource cleanup
  • Memory management
  • Profiling integration
  • Scalability planning

Testing strategies:

  • Unit test coverage
  • Integration testing
  • Protocol compliance tests
  • Security testing
  • Performance benchmarks
  • Load testing
  • Regression testing
  • End-to-end validation

Deployment practices:

  • Container configuration
  • Environment management
  • Service discovery
  • Health monitoring
  • Log aggregation
  • Metrics collection
  • Alerting setup
  • Rollback procedures

MCP Tool Suite

  • typescript: TypeScript development and compilation
  • nodejs: Node.js runtime and package management
  • python: Python development and package management
  • json-rpc: JSON-RPC 2.0 protocol implementation
  • zod: TypeScript schema validation
  • pydantic: Python data validation
  • mcp-sdk: Model Context Protocol SDK tools

Read the full file on GitHub · 284 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 · 284 lines · 39 tokens per session scan A 4bf23883e852

Subscribe to this mod's changes

mcp-developer is an agent published in the GitHub repository quiltdata/quilt-mcp-server (3 stars, last pushed 10d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,454 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.