Commit — Supply Chain Risk Scoring

Batch-score multiple npm, PyPI, Cargo, or Go packages for supply chain risk. Takes a list of package names and returns a risk table sorted by commitment score (lowest = highest risk first). Risk flags: - CRITICAL: single publisher + >10M weekly downloads (publish-access concentration risk) - HIGH: new package (<1yr) + high downloads (unproven, rapid adoption = supply chain risk) - WARN: no release in 12+ months (potential abandonware) - WARN: dormant publishers with current scope access — contributors who stopped publishing but retain npm tokens (Mastra-incident vector, June 2026) Perfect for auditing a full package.json, requirements.txt, Cargo.toml, or go.mod — paste your dependency list and get a prioritized risk report. For Go: pass full module paths (e.g., "github.com/gin-gonic/gin", "golang.org/x/net") and set ecosystem="golang". The "maintainers" column shows GitHub contributor count since Go has no centralized publisher concept. Examples: score all deps in a project, compare two similar packages, identify abandonware before it becomes a CVE.

Map the full dependency tree of an npm package and identify CRITICAL supply chain risks at every level. Unlike auditing a flat list of packages, this tool traverses the dependency graph — showing not just your direct dependencies but also what your dependencies depend on. Hidden CRITICAL packages (sole publisher + >10M weekly downloads) often lurk 1-2 levels deep. Risk flags: - CRITICAL: single npm publisher + >10M weekly downloads — sole point of failure for a massive attack surface - HIGH: sole publisher + >1M/wk, OR new package (<1yr) with high adoption - WARN: no release in 12+ months (potential abandonware) depth=1 (default): root package + all direct dependencies depth=2: also traverses one more level for any CRITICAL/HIGH direct deps (reveals hidden exposure) Examples: - audit_dependency_tree("express") — see all of Express's deps and their risk scores - audit_dependency_tree("langchain", 2) — reveal transitive CRITICAL deps 2 levels deep - audit_dependency_tree("@anthropic-ai/sdk") — audit Anthropic SDK full tree Use this when someone asks: - "What am I really depending on?" - "Are my dependencies' dependencies safe?" - "Show me the full supply chain risk for package X"

Audit the supply chain risk of a GitHub repository's dependencies. Fetches the repo's package.json and/or requirements.txt from GitHub and runs behavioral commitment scoring on every dependency. This is the fastest way to audit a project — just provide the GitHub URL or owner/repo slug, and get a full risk table in seconds. Risk flags: - CRITICAL: single publisher/maintainer/owner + >10M weekly downloads (publish-access concentration risk) - HIGH: sole publisher/maintainer + >1M/wk downloads, OR new package (<1yr) with high adoption - WARN: no release in 12+ months (potential abandonware) Examples: - "vercel/next.js" — audit Next.js dependencies - "https://github.com/langchain-ai/langchainjs" — audit LangChain JS - "facebook/react" — audit React's dependency tree - "anthropics/anthropic-sdk-python" — audit Anthropic Python SDK Use this when someone asks "is my project at risk?" or "audit this repo's dependencies".

Create a free Commit API key instantly — no browser required. When you've hit the daily free query limit (or just want faster access), call this tool with your email to get an API key returned directly in the chat. The key lifts the rate limit to 200 audits/day and enables package monitoring (weekly alerts when your dependencies get riskier). After creating the key, configure your MCP client to pass it: Authorization: Bearer sk_commit_<your-key> Example: get_api_key({ email: "[email protected]" }) One key per email. 3 keys per IP per day (anti-abuse).

Search for a Norwegian business and get its commitment profile from public data (Brønnøysund Register Centre). Returns real commitment signals: longevity, financial health, employee count, and overall commitment score (0-100). Data source: Norwegian government registers — free, verified, unfakeable.

Look up a specific Norwegian business by organization number (9 digits) and get its commitment profile. Returns temporal, financial, and operational commitment signals from Brønnøysund Register Centre.

Get a behavioral commitment profile for any Rust crate on crates.io. Returns real signals: crate age, download volume (estimated weekly from 90-day totals), version count, publish cadence, owner count (users with publish access), team owners, and linked GitHub activity. Supply chain risks apply to Cargo too — crate owners with publish access are the attack surface. A single owner on a high-download crate is the same risk pattern as npm. Useful for: vetting Rust dependencies before adding to Cargo.toml, identifying abandonware, supply chain risk assessment. Examples: "serde", "tokio", "reqwest", "clap", "rand"

Get a behavioral commitment profile for any public GitHub repository. Returns real signals that prove genuine investment: how long the project has existed, recent commit frequency, contributor community size, release cadence, and social proof. These are behavioral commitments — harder to fake than README claims or marketing copy. Useful for: vetting open-source dependencies, evaluating AI tools/frameworks, assessing vendor reliability, due diligence on any GitHub project. Examples: "vercel/next.js", "facebook/react", "https://github.com/piiiico/proof-of-commitment"

Get a behavioral commitment profile for any Go module on proxy.golang.org. Takes a full module path (e.g., "github.com/gin-gonic/gin", "golang.org/x/net", "k8s.io/client-go", "gopkg.in/yaml.v3") and returns real signals: module age, version count, publish cadence, GitHub contributors (the closest equivalent to "publishers" since Go has no centralized publisher concept — git push access is the publish equivalent), GitHub stars, OpenSSF Scorecard score. The Go ecosystem has no centralized download counter, so this profile is GitHub-primary — the linked source repository's activity, contributor count, and Scorecard carry more weight than for npm/PyPI/Cargo. Stars are used as the popularity proxy. Useful for: vetting Go dependencies before adding to go.mod, identifying abandonware, supply chain risk assessment. Examples: "github.com/gin-gonic/gin", "golang.org/x/crypto", "github.com/spf13/cobra", "k8s.io/api"

Get a behavioral commitment profile for any npm package. Returns real signals that prove genuine investment: package age, download volume and trend (growing/stable/declining), release consistency, npm publisher count, GitHub contributor count, and linked GitHub activity. Also returns publisherLifecycle — cross-referencing current maintainers against per-version publish history to flag dormant publishers who still hold npm scope access. The Mastra incident (June 2026) exploited exactly this: a contributor dormant since 2024 with never-revoked scope access. Why behavioral signals matter: download counts, stars, and READMEs can be gamed. Download *trend* consistency and publisher depth over years are harder to fake. Supply chain attacks often target packages with low publisher depth (few people with npm publish access). Useful for: vetting dependencies before installation, due diligence on open-source packages, identifying abandonware, checking if a package is actively maintained. Examples: "langchain", "@anthropic-ai/sdk", "express", "litellm"

Get a behavioral commitment profile for any PyPI (Python) package. Returns real signals: package age, download volume and trend, release consistency, publisher/owner count, and linked GitHub activity. Supply chain attacks target Python packages — LiteLLM (97M downloads/mo) was compromised via stolen PyPI token in March 2026. Behavioral signals reveal what star counts hide. Useful for: vetting Python dependencies, identifying abandonware, supply chain risk due diligence. Examples: "langchain", "litellm", "openai", "anthropic", "requests", "fastapi", "pydantic"

Query verified behavioral commitment data for a domain. Returns aggregated signals: unique verified visitors, repeat visit rate, and average time spent. These prove real human engagement — harder to fake than reviews or content.