A quick reference for the Model Context Protocol (MCP), a standard way for AI applications to exchange context, tools, and resources with servers. It covers protocol concepts, versions, message transport, cancellation, progress, and related features.

Use it to check MCP terminology, understand protocol behavior, compare specification versions, and follow implementation guidance.

It reduces the need to search through MCP specifications when building or debugging an MCP client or server.

mcp — Cursor rule by jhgaylor

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 rules/jhgaylor/node-candidate-mcp-server/mcp

Clone the repo

git clone --depth 1 https://github.com/jhgaylor/node-candidate-mcp-server

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.

When invoked 535 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00535
Opus 5	$0.00000	$0.00267
Sonnet 5	$0.00000	$0.00107
Haiku 4.5	$0.00000	$0.00053

Measured 2d ago against content hash 69ce09a659da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

mcp — 100% identical, 0 lines differ

.cursor/rules/mcp.mdc · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Context Protocol (MCP)

MCP is a standard protocol to exchange contextual data between clients, servers, and LLMs. This rule provides an at-a-glance reference for key concepts, spec versions, tooling, and best practices.

Core Concepts

Lifecycle: Define session start/end, request and response phases.
Messages: JSON-encoded context, prompts, and completions.
Transports: HTTP, WebSocket, gRPC—pluggable transports for message delivery.
Cancellation: Send cancellation messages to abort in-progress requests.
Ping (Heartbeat): Keep connections alive; detect timeouts.
Progress: Stream partial results and progress updates.
Roots: External content references (e.g. code, docs) managed by ID.
Sampling: Control streaming vs. non-streaming completions; fine-tune sampling parameters.
Tools: Plugin external actions and APIs into LLM workflows.

Specification Versions

Basic 2024-11-05: Overview, lifecycle, messages, transports, utilities (cancellation, ping, progress).
Server/Client 2024-11-05: Prompts, resources, roots, sampling, tools, logging, pagination.
Extended 2025-03-26: Authorization, architecture refinements, changelog.
Drafts: Early designs; consult changelog for breaking changes.

SDKs & Examples

TypeScript SDK: https://github.com/modelcontextprotocol/typescript-sdk
Python SDK: https://github.com/modelcontextprotocol/python-sdk
Java/Kotlin/C# SDKs: Refer to https://modelcontextprotocol.io
Example Clients & Servers: https://modelcontextprotocol.io/examples.md

Best Practices

Always annotate messages with spec version and timestamp.
Use roots to manage large contexts; avoid embedding bulky data inline.
Gracefully handle cancellation and errors; propagate clear error codes.
Emit progress events for long-running streams to improve UX.
Maintain a ping schedule to detect and recover dropped connections.
Leverage tools to encapsulate external API calls and side effects.
Follow spec utilities: logging, pagination, and completion conventions.
Review the official spec and changelog regularly to stay up to date.

Read the full file on GitHub · 48 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.

2d ago First seen · 48 lines · 0 tokens per session scan A 69ce09a659da

Subscribe to this mod's changes

mcp is a cursor rule published in the GitHub repository jhgaylor/node-candidate-mcp-server (81 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 535 tokens. 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.

Data and AI Planning mcp server

mcp