MCP Developer

A coding guide for building and maintaining an MCP server. MCP is a standard way for an AI assistant to call tools and use outside data.

In plain words
What is it for?
Use it when working on MCP tools, memory operations, session-start context loading, server API routes, or tool descriptions that help an AI choose the right tool.
Why use it?
It keeps tool inputs, outputs, descriptions, stored knowledge, and session startup behavior consistent. It also makes changes safer by requiring coordination when tool interfaces change.

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/shawnhack/exocortex/mcp-developer
Clone the repo
git clone --depth 1 https://github.com/shawnhack/exocortex

Made for: Claude Code.

Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 215 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 $0.00003 $0.00215
Opus 5 $0.00002 $0.00108
Sonnet 5 $0.00001 $0.00043
Haiku 4.5 $0.00000 $0.00021

Measured yesterday against content hash a0bdd09ce7f5, 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 yesterday.

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 · 30 lines

What it actually says

MCP Developer

Core Responsibilities

  • MCP server tools (memory_store, memory_search, memory_update, etc.)
  • Session-orient hook (session start context loading)
  • Server API routes
  • Tool description optimization for LLM trigger accuracy

Key Files

  • packages/mcp/src/ — MCP server implementation
  • packages/mcp/src/hooks/session-orient.js — SessionStart hook
  • packages/server/src/routes/ — REST API routes

Coding Constraints

  • Tool descriptions are prompt engineering — optimize for trigger accuracy
  • Validate all parameters before processing
  • Return structured JSON, not prose
  • Include attribution fields (provider, model_id, model_name, agent) on store operations
  • MCP tools accept tier parameter for knowledge tier scoping
  • Session-orient hook must complete within 3s timeout

Escalation

  • New MCP tools: discuss naming and description with user
  • Breaking changes to tool signatures: coordinate with all consumers
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. yesterday First seen · 30 lines · 3 tokens per session scan A a0bdd09ce7f5

Subscribe to this mod's changes

MCP Developer is an agent published in the GitHub repository shawnhack/exocortex (1 stars, last pushed 26d ago), licensed MIT. It adds 3 tokens to every session and 215 once invoked, about $0.0000 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.

Related

Other agents, from other repositories

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.

MinishLab/semble · 46 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.

MinishLab/semble · 47 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.

MinishLab/semble · 44 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.

MinishLab/semble · 44 tokens