- id
- nsip-readme
エージェントを強化
公開元からインストールします。PlugMCP のエンドポイントではありません。
リモート URL か、手元のマシンのコマンドか 2 つのインストール方法の違い
PlugMCP で実行
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
起動公開元より
Sheep genetic evaluation CLI & MCP server -- search animals, compare EBVs, plan matings, rank flocks via the NSIP database
nsipSheep genetic evaluation CLI & MCP server -- search animals, compare EBVs, plan matings, rank flocks via the NSIP database.
Try it out: Clone zircote/nsip-example for a ready-to-use farm repository with MCP server configuration, sample workflows, and AI assistant instructions pre-configured.
Add this to your Cargo.toml:
[dependencies]
nsip = "0.6"
Or use cargo add:
cargo add nsip
use nsip::{NsipClient, SearchCriteria};
#[tokio::main]
async fn main() -> Result<(), nsip::Error> {
// Create a new client
let client = NsipClient::new();
// List available breed groups
let breed_groups = client.breed_groups().await?;
println!("Available breed groups: {}", breed_groups.len());
// Search for animals
let criteria = SearchCriteria::new()
.with_status("CURRENT");
let results = client
.search_animals(0, 15, Some(640), None, None, Some(&criteria))
.await?;
println!("Found {} animals", results.total_count);
// Get details for a specific animal
let animal = client.animal_details("LPN_ID_HERE").await?;
println!("Animal: {}", animal.lpn_id);
Ok(())
}
The nsip CLI provides several commands for interacting with the NSIP Search API:
# Get database last-updated date
nsip date-updated
# List breed groups
nsip breed-groups
# List animal statuses
nsip statuses
# Get trait ranges for a breed
nsip trait-ranges 640
# Search for animals
nsip search --breed-id 640 --status CURRENT --page 0 --page-size 15
# Get animal details
nsip details <lpn-id>
# Get animal lineage
nsip lineage <lpn-id>
# Get animal progeny
nsip progeny <lpn-id>
# Get full profile (details + lineage + progeny)
nsip profile <lpn-id>
# Compare two or more animals side-by-side
nsip compare <lpn-id-1> <lpn-id-2>
# Generate shell completions
nsip completions bash
# Generate man pages
nsip man-pages --out-dir ./man/
# Start MCP server mode
nsip mcp
Full documentation lives under docs/, organized using the Diataxis framework:
nsip crateSee docs/README.md for the complete documentation index.
The library includes MCP (Model Context Protocol) support for integration with AI assistants:
use nsip::mcp::{serve_stdio, tool_sets::EnabledToolSets};
// Start the MCP server on stdio (all 13 tools enabled)
serve_stdio(EnabledToolSets::all()).await?;
The MCP protocol exposes the following 13 tools when running nsip mcp:
search - Search for animals with filters for breed, gender, status, date range, and flockdetails - Get detailed EBV data, breed, contact info, and status for an animallineage - Get pedigree / ancestry tree including parents and grandparentsprogeny - Get paginated list of offspring for an animalprofile - Get complete profile (details + pedigree + offspring) in one callbreed_groups - List all breed groups and individual breedstrait_ranges - Get min/max EBV trait ranges for a specific breedcompare - Compare 2-5 animals side-by-side on their EBV traitsrank - Rank animals within a breed by weighted EBV traitsinbreeding_check - Calculate Wright's coefficient of inbreeding for a sire-dam pairingmating_recommendations - Find optimal mates ranked by trait complementarity and COIflock_summary - Summarize a flock's animals: count, gender breakdown, and average EBVsdatabase_status - Get last-updated date and available animal statuses# Clone the repository
git clone https://github.com/zircote/nsip.git
cd nsip
# Build
cargo build
# Run tests
cargo test
# Run linting
cargo clippy --all-targets --all-features
# Format code
cargo fmt
# Check supply chain security
cargo deny check
# Generate documentation
cargo doc --open
crates/
├── lib.rs # Library entry point
├── main.rs # Binary entry point
├── client.rs # HTTP client for the NSIP Search API
├── models.rs # Data models (SearchCriteria, AnimalDetails, etc.)
├── format.rs # Human-readable ASCII table formatting
└── mcp/ # MCP server (13 tools, prompts, resources)
tests/
├── integration_test.rs
└── cli_test.rs # CLI integration tests
Cargo.toml # Project manifest
clippy.toml # Clippy configuration
rustfmt.toml # Formatter configuration
deny.toml # cargo-deny configuration
CLAUDE.md # AI assistant instructions
AGENTS.md # AI coding agent instructions
.editorconfig # Cross-editor defaults
.devcontainer/ # Codespaces / dev container config
.vscode/ # VS Code settings and extensions
This project maintains high code quality standards:
Note:
just checkis the canonical local equivalent of the CI pipeline (fmt + clippy + test + doc + deny + coverage). Runjustto list all available recipes. The rawcargocommands below are the underlying equivalents.
# Run all checks
cargo fmt -- --check && \
cargo clippy --all-targets --all-features -- -D warnings && \
cargo test && \
cargo doc --no-deps && \
cargo deny check
# Run with MIRI for undefined behavior detection
cargo +nightly miri test
This template includes production-ready workflows:
.github/workflows/ci.yml) - Format, lint, test, docs, supply chain security, MSRV check, coverage.github/workflows/security-audit.yml) - Daily cargo-audit scans.github/workflows/secrets-scan.yml) - Gitleaks secret scanning (manual; enable push/PR triggers to automate).github/workflows/container-scan.yml) - Trivy image vulnerability scanningRelease (.github/workflows/release.yml) - Automated GitHub releases with multi-platform binaries
x86_64, ARM64), macOS (x86_64, ARM64), Windows (x86_64)Changelog (.github/workflows/changelog.yml) - Automated CHANGELOG.md generation
Docker (.github/workflows/docker.yml) - Multi-platform container builds
Publish (.github/workflows/publish.yml) - Automated crates.io publishing
develop is the active development branch and main is the stable/release branch. Never tag from develop — promote the release through main first via the Release PR workflow. See docs/runbooks/RELEASING.md for the full step-by-step procedure; summary:
Cargo.toml on develop.gh workflow run "Release PR" -f version=X.Y.Z, get it reviewed, and merge it into main.main merge commit and push the tag:
git tag -a vX.Y.Z -m "Release vX.Y.Z"
git push origin vX.Y.Z
main into develop.github/workflows/copilot-setup-steps.yml) - Environment for GitHub Copilot coding agentAGENTS.md, .github/copilot-instructions.md, CLAUDE.md.github/instructions/ for Rust code and test patterns.github/prompts/ for common development tasksPull and run the container:
# Pull latest
docker pull ghcr.io/zircote/nsip:latest
# Run specific version
docker pull ghcr.io/zircote/nsip:v0.6.0
docker run --rm ghcr.io/zircote/nsip:v0.6.0 --version
The Minimum Supported Rust Version (MSRV) is 1.92. Increasing the MSRV is considered a minor breaking change.
See CONTRIBUTING.md for development setup, PR checklist, and coding standards.
Please also review:
This project is licensed under the MIT License - see the LICENSE file for details.
Sheep genetic evaluation CLI & MCP server -- search animals, compare EBVs, plan matings, rank flocks via the NSIP database
ツール
ツール一覧はまだありません。リモートサーバーは、最初のヘルスチェック後に取得されます。
よくある質問
このページで Cursor、Claude Desktop、Claude Code、VS Code 用の stdio 設定をコピーできます。PlugMCP のプロキシではなく、公開元のインストール方法を使います。
このレコードに必須の環境変数は記載されていません。
Nsip は stdio 経由でローカル実行されます。
最終チェックは 2026-10-28 です。 Sheep genetic evaluation CLI & MCP server -- search animals, compare EBVs, plan matings, rank flocks via the NSIP database