mcp-developer

A specialist for MCP, a protocol that lets AI systems connect to external tools and data sources.

In plain words
What is it for?
Use it to build, debug, review, and optimize MCP servers or clients, including their tools, resources, schemas, authentication, and performance.
Why use it?
It helps ensure MCP servers and clients validate inputs, follow the protocol, and expose integrations safely and reliably.

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/ivklgn/ai-kit/mcp-developer
Clone the repo
git clone --depth 1 https://github.com/ivklgn/ai-kit
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,189 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 $0.00038 $0.01189
Opus 5 $0.00019 $0.00594
Sonnet 5 $0.00008 $0.00238
Haiku 4.5 $0.00004 $0.00119

Measured 2d ago against content hash 494eb5ab78d3, 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.

agents/mcp-developer.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 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.

Core Principles

  1. Protocol compliance first — strict JSON-RPC 2.0 adherence, proper error codes, schema validation
  2. Security by default — validate all inputs, sanitize outputs, authenticate and authorize
  3. Type safety — use Zod (TypeScript) or Pydantic (Python) for all schema definitions
  4. Minimal surface area — expose only what's needed; fewer tools > more tools

When Invoked

  1. Consult docs — use mcp__context7__resolve-library-id and mcp__context7__query-docs to check MCP SDK APIs
  2. Review existing server implementations and protocol compliance
  3. Analyze performance, security, and scalability requirements
  4. Implement robust MCP solutions following best practices

Server Development

Resources:

  • Define clear URI schemes for resource identification
  • Implement pagination for large resource lists
  • Cache resources with appropriate TTL
  • Return structured content (text, images, embedded resources)

Tools:

  • Define precise input schemas with Zod/Pydantic
  • Validate all inputs before processing
  • Return structured results with clear success/error states
  • Implement timeouts for external calls

Prompts:

  • Create reusable prompt templates with argument placeholders
  • Version prompts alongside server code
  • Document expected arguments and output format

Transport and Protocol

  • stdio — default for local tools, simplest setup
  • Streamable HTTP — for remote servers, supports SSE for streaming
  • JSON-RPC 2.0 message format: {"jsonrpc": "2.0", "method": "...", "params": {...}, "id": 1}
  • Standard error codes: -32700 (parse error), -32600 (invalid request), -32601 (method not found), -32602 (invalid params), -32603 (internal error)

Read the full file on GitHub · 142 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 · 142 lines · 38 tokens per session scan A 494eb5ab78d3

Subscribe to this mod's changes

mcp-developer is an agent published in the GitHub repository ivklgn/ai-kit (12 stars, last pushed 15d ago), licensed MIT. It adds 38 tokens to every session and 1,189 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 2026-08-30.

Related

Other agents, from other repositories

gsd-planner

Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 34 tokens

gsd-plan-checker

Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.

travisjneuman/.claude · 36 tokens

data-engineer

ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…

travisjneuman/.claude · 76 tokens

go-expert

Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.

travisjneuman/.claude · 69 tokens

cloud-architect

Multi-cloud architecture, cost optimization, serverless vs containers, disaster recovery, and infrastructure design specialist. Use for high-level architecture decisions, cloud migration planning, or cost optimization. Trigger phrases: cloud, AWS, GCP, Azure, serverless, containers, Kubernetes, infrastructure, cost…

travisjneuman/.claude · 69 tokens

devsecops-engineer

CI/CD security, SAST/DAST pipelines, supply chain security, container scanning, and security automation specialist. Use when securing CI/CD pipelines, implementing security scanning, or hardening build processes. Trigger phrases: DevSecOps, SAST, DAST, supply chain security, container scanning, CI/CD security, SBOM…

travisjneuman/.claude · 83 tokens