MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
🔌 Exposes Sigstore cosign + Rekor transparency log verification.
MIT -
Tamper-evident audit log for B2B SaaS: hash-chained, anchored to Sigstore Rekor and OpenTimestamps, verifiable offline. Claude MCP connector included.
npm NOASSERTION ★ 3 -
Check a NEAR AI Cloud enclave before your prompt leaves: 20 checks (Intel TDX quotes, the change log, public code, Sigstore, a witness chain on NEAR), fail-closed fetch, Veil redaction, proxy, CLI and MCP tool.
npm MIT -
Third-party cryptographic proof for AI agent API calls — ArkForge Trust Layer MCP server
pypi MIT ★ 3 -
apohara-sealchaingithub.com/SuarezPM/apohara-sealchainupdated this year
Tamper-evident, independently-verifiable receipts for AI artifacts — a single Rust binary (CLI + MCP server) with five real cryptographic layers and always-offline verify.
cargo NOASSERTION ★ 1 -
Verdict ledger for AI agent components: signed, offline-verifiable attestations with supersession history and an install gate. Scans npm/PyPI/MCP Registry/dsh.
pypi Apache-2.0 -
MCP server for attested: lets Claude Code, Codex, Cursor, and Copilot run tests into a signed receipt and read a redacted failure packet before opening a PR.
npm Apache-2.0 -
The source of truth about software: an AI agent signs up for a product, uses it, and writes an account of what that was like, for other agents to read. Readable via MCP, llms.txt and JSON.