A TypeScript server that lets Donut provide note-search and note-relationship tools through the Model Context Protocol, a standard way for AI assistants to use external tools.

Use it to search Donut notes, inspect connections between notes, and test the server's tool handling and supporting code.

It gives an AI assistant a defined way to read relevant notes from Donut instead of requiring custom integration for every request.

mcp-server — Cursor rule by nerds-odd-e

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/nerds-odd-e/doughnut/mcp-server

Clone the repo

git clone --depth 1 https://github.com/nerds-odd-e/doughnut

Made for: Cursor.

Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,091 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	$0.00016	$0.01091
Opus 5	$0.00008	$0.00545
Sonnet 5	$0.00003	$0.00218
Haiku 4.5	$0.00002	$0.00109

Measured 2d ago against content hash 22d84b264484, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server 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.

.cursor/rules/mcp-server.mdc · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

donut-mcp-server MCP Server

A Model Context Protocol server for Donut.

Is in the mcp-server folder.

This is a TypeScript-based MCP server that demonstrates core MCP concepts by providing:

Tools that read note context from the Donut backend API (search and graph).

Structure (minimal)

mcp-server/
  src/                    # Production source code
    index.ts              # boot: create context, start stdio
    server.ts             # assemble server, list tools, route calls
    context.ts            # read env, create DonutApi
    api.ts                # DonutApi factory
    schemas.ts            # tool input schemas (shared)
    tools/index.ts        # tool registry + handlers
    types.ts              # shared types
    utils.ts              # error + validation helpers
  tests/                  # Unit tests (separate from production code)
    server.test.ts        # Server and tools tests
    utils.test.ts         # Utility functions tests
  vitest.config.ts        # Test configuration
  tsconfig.json           # TypeScript configuration
  package.json            # Dependencies and scripts

Important: Tests are kept in a separate tests/ folder, not mixed with production code in the src/ folder. This maintains clean separation between production and test code, making the codebase more organized and maintainable.

Development

Building the MCP Server

Run this command to build the mcp server:

CURSOR_DEV=true nix develop -c pnpm mcp-server:bundle

Note: Rebuild the bundle before running the e2e mcp_services.feature.

Running Unit Tests

The MCP server has Vitest unit tests under tests/ (not mixed with src/). Style ("small test" practice — stable boundary, data over mocks, focused assertions, concise makeMe): always-applied unit-testing.mdc.

CURSOR_DEV=true nix develop -c pnpm mcp-server:test

Test Organization

Production code: src/
Test files: tests/**/*.test.ts (see vitest.config.ts)
Drive high-level tool/server entry points; cover lower layers with realistic makeMe data. Mock only backend HTTP responses (external dependency), with makeMe for API-shaped payloads.

Read the full file on GitHub · 155 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 · 155 lines · 16 tokens per session scan A 22d84b264484

Subscribe to this mod's changes

mcp-server is a cursor rule published in the GitHub repository nerds-odd-e/doughnut (49 stars, last pushed 2d ago), licensed MIT. It adds 16 tokens to every session and 1,091 once invoked, about $0.0001 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.

Data and AI Research Testing

mcp-server

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

donut-mcp-server MCP Server

Structure (minimal)

Development

Building the MCP Server

Running Unit Tests

Test Organization

What this file has done since we first saw it

Other cursor rules, from other repositories

angular-20

dev-standard

typescript

coolify-ai-docs

python_lib

specs