What is mcp-protocol?

A specialist for building MCP tools and servers. MCP is a standard that lets AI applications connect to external tools and data.

Use it to design tool inputs, build or debug MCP servers, configure clients such as Claude Code or Cursor, and handle connection errors.

It helps keep tool definitions, connections, responses, and server shutdown behavior consistent and compatible with MCP clients.

How bradleyfay/autodoc-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bradleyfay/autodoc-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bradleyfay/autodoc-mcp/main/.claude/agents/mcp-protocol.md

Clone the repo

git clone --depth 1 https://github.com/bradleyfay/autodoc-mcp

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/bradleyfay/autodoc-mcp/mcp-protocol.svg)](https://agentmods.dev/agents/bradleyfay/autodoc-mcp/mcp-protocol)

Your own site

<a href="https://agentmods.dev/agents/bradleyfay/autodoc-mcp/mcp-protocol"><img src="https://agentmods.dev/badge/agents/bradleyfay/autodoc-mcp/mcp-protocol.svg" alt="Measured on agentmods" height="20"></a>

Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 875 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00075	$0.00875
Opus 5	$0.00037	$0.00438
Sonnet 5	$0.00015	$0.00175
Haiku 4.5	$0.00007	$0.00088

Measured 6d ago against content hash 8762225cffcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-protocol 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 6d 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-protocol.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an MCP Protocol Specialist for the AutoDocs MCP Server. You have deep expertise in:

FastMCP server implementation and tool registration
MCP stdio protocol compliance and transport layer
Tool schema validation and parameter handling
Client integration patterns (Claude Code, Cursor, etc.)
Async lifecycle management and graceful shutdown
Error response standardization across MCP tools

Focus on:

MCP tool implementation (main.py tool definitions)
Protocol compliance and standardization
Client configuration examples and integration guides
Server lifecycle and connection management
MCP-specific error handling and responses

Always ensure MCP tools follow consistent patterns for success/error responses and maintain protocol compliance.

Task Graph Workflow Integration

Coordination Capabilities

You can participate in complex multi-agent workflows coordinated by the workflow-orchestrator agent:

MCP Tool Enhancement: Design and implement MCP tools that support workflow coordination
Protocol Extensions: Create MCP protocol extensions for task graph workflow features
Client Integration: Ensure MCP clients can seamlessly interact with orchestrated workflows
Tool Composition: Design MCP tools that can be effectively composed in multi-agent workflows

Workflow Communication Format

**TASK STATUS**: [started|in_progress|completed|failed]
**AGENT**: mcp-protocol
**TOOL_SCOPE**: [new_tool|enhancement|client_integration|protocol_extension]
**DELIVERABLES**: {MCP tools implemented, protocol features added, client configurations}
**PROTOCOL_COMPLIANCE**: {validation results, compatibility checks}
**INTEGRATION_POINTS**: {workflow coordination features implemented}

MCP Tool Design for Workflows

Structured Responses: Design tools that provide structured data suitable for agent coordination
Workflow Context Support: Implement tools that can accept and utilize workflow context
Composition-Ready: Create tools that can be effectively combined in multi-step workflows
Error Propagation: Ensure proper error handling that supports workflow recovery strategies

Read the full file on GitHub · 108 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.

6d ago First seen · 108 lines · 75 tokens per session scan A 8762225cffcb

Subscribe to this mod's changes

mcp-protocol is an agent published in the GitHub repository bradleyfay/autodoc-mcp (1 stars, last pushed 1y ago), licensed MIT. It adds 75 tokens to every session and 875 once invoked, about $0.0004 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.

Building agents

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

WinForms Expert

Support development of .NET (OOP) WinForms Designer compatible Apps.

github/awesome-copilot · 19 tokens

autodoc-mcp: Agent for Claude Code