scorecard-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
scorecard-mcp
A Model Context Protocol server for the OpenSSF Scorecard API. Scorecard scores public repositories from 0 to 10 on supply-chain and repository security practices: branch protection, code review, pinned dependencies, least-privilege workflow tokens, signed releases, known vulnerabilities and more. The public API needs no key.
The Scorecard API has a single read endpoint that returns a large JSON document per repository. This server turns it into task-shaped tools: checks are ordered by risk rather than alphabetically, evidence lines are trimmed to the warnings that explain a score, each weak check comes with a short remediation note and a link to the upstream documentation, and several repositories can be compared in one call.
Setup
Requires Python 3.12+ and uv.
git clone <this repo> && cd scorecard-mcp
uv sync
uv run scorecard-mcp # stdio transportAdd it to any MCP client that launches stdio servers:
{
"mcpServers": {
"scorecard": {
"command": "uv",
"args": ["run", "--directory", "/path/to/scorecard-mcp", "scorecard-mcp"]
}
}
}For HTTP instead of stdio: MCP_TRANSPORT=streamable-http MCP_HOST=127.0.0.1 MCP_PORT=8000 uv run scorecard-mcp.
Related MCP server: SecurityScorecard MCP Server
Tools
All tools are read-only. A repository can be given as github.com/owner/name, a full or SSH URL, or just owner/name (GitHub is assumed). GitLab repositories use gitlab.com/group/name.
Tool | What it returns |
| The weak checks for a repository in priority order (risk weight times points lost), each with its risk level, the warning lines naming the files and settings behind the score, a remediation note and a docs link. Start here. |
| Overall score, scan date, scanned commit and the checks below 10, ordered by priority. |
| Evidence for one check (for example |
| Up to 30 repositories ranked lowest first, each with its three highest-priority weak checks and optional per-check columns. Repositories with no stored result are listed under |
| Reference table of every check with risk level and remediation. No network call. |
An optional commit argument fetches a stored result for a specific 40-character commit SHA instead of the latest scan.
Configuration
All optional environment variables:
Variable | Default | Meaning |
|
| API root (for a mirror or proxy) |
|
| Request timeout in seconds |
|
| Retries on HTTP 429, 502, 503, 504 and timeouts |
|
| In-process cache of results (the API sends |
|
| Responses longer than this are cut with a notice |
|
|
|
Limits
The public API only returns repositories that Scorecard has already scanned: widely used projects and repositories that publish their own results from CI. Anything else comes back as a clear "no stored result" message. Scanning a private or unlisted repository needs the Scorecard CLI.
Results are a snapshot. The scan date is included in every response and can be days or weeks old.
A score of -1 means a check could not be evaluated (for example Branch-Protection when the scan could not read repository settings); those checks are listed under
not_evaluatedand are left out of priorities.The risk levels and remediation notes in
list_checkssummarise the upstream documentation; always follow the docs link in a result for the authoritative wording.compare_reposruns up to 6 requests at once. The Scorecard API does not document rate limits, so the server retries politely but does not queue requests.Scorecard measures practices, not security. A high score does not mean a project is free of vulnerabilities.
Development
uv sync
uv run pytestTests mock all HTTP traffic with respx; no network access is needed.
Licence
MIT. Copyright (c) 2026 Ankur Kapuriya.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and supply-c.
Evaluates any GitHub repository for license risk, maintenance velocity, stars/forks, and security.
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals.
Security scanning for code, containers and IaC: request scans, read findings, report fixes.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables asking natural language questions about OpenSSF Scorecard security assessments for open source projects.4Apache 2.0
- AlicenseBqualityBmaintenanceIntegrates with the SecurityScorecard API to provide security metrics, risk analysis, asset discovery, and remediation planning through natural language.971 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables maintainers to prioritize maintenance across GitHub repositories by converting repository, branch, CI, security, and release signals into deterministic, evidence-backed scores and ranked actions.MIT
- AlicenseNot gradedqualityDmaintenanceEnables users to query dependency security data in natural language, including trust scores for individual packages, full project scans, blast radius analysis, zombie and typosquat detection, package comparisons, and safer migration suggestions. Results can be returned inline or written as JSON reports.109 npmMIT