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.
-
@heyamiko/amikonet-signergithub.com/hcf-s/amikonet-signer-mcp-serverupdated this year
Local DID signer for AmikoNet - manages private keys and creates cryptographic signatures (never transmits keys)
npm MIT -
Trustflow MCP server. Stdio tools for Trustflow Systems domain audits, did:web keys, and signed llms.txt. Binary: agentic-trust-mcp. Scaffold with npx @trustflow/cli@latest init.
npm MIT -
canon-mcpgithub.com/iwadd/canonupdated this year
Reference implementation of the Seal protocol (Web 2.5 — the AI communication layer for Web 2). Web 2.5 primitives only: envelope, did:key, payload schemas, content-addressed store, mirror, verify-on-receive fetch. No third-party APIs. No conversion. Brin
npm MIT -
wispgithub.com/erhnysr/wispactive
Independent signal and participation tool for the Technocore network: paste a did:key to see what the network's own data says, every signal with a proves/doesn't-prove note.
MIT -
xrpl-identity-mcpgithub.com/jarod-vyent/xrpl-identity-mcpupdated this year
First identity-focused MCP server for the XRP Ledger: DIDs (XLS-40), on-chain Credentials (XLS-70), and signer lists. Prepares, verifies, and submits transactions; never custodies keys.
npm MIT ★ 1 -
An MCP server that answers "did my deploy actually work?" — catches pages that return 200 and render nothing, broken links, stray noindex, and staging that never updated. Zero config, no API key.
MIT -
Verify what an AI agent did on someone's behalf. Resolves a signed agent receipt at a neutral registry, showing what was asked, what was done, what money moved, and what commercial influence the operator disclosed. Read only, no API key.
npm MIT -
Vorim AIno update data
Identity, permissions, and signed audit trails for AI agents. Every agent gets an Ed25519 cryptographic identity, scoped permissions, and an append-only audit trail. Permission checks run in under 5 milliseconds. Audit events export with a SHA-256 manifest for tamper-evident, offline verification. Trust scores and identity verification are publicly accessible via REST endpoint. Anchored to the IETF Internet-Draft for VAIP (the Vorim Agent Identity Protocol). **17 tools** covering agent registration, ephemeral agents (W3C did:key), permissions, audit events, audit export, credential delegation, scoped token issuance, and public trust verification. **Get an API key:** [vorim.ai/settings/api-keys](https://vorim.ai/settings/api-keys) **Docs:** [vorim.ai/docs](https://vorim.ai/docs) **Open protocol:** [github.com/Kzino/vorim-protocol](https://github.com/Kzino/vorim-protocol)
smithery -
Encrypted, DID-signed cross-session memory for MCP agents over FLOP Labs Technocore.
Apache-2.0 -
The Mage's read tools and the Swordsman that signs — the privacy guide, the 64-vertex sovereignty lattice and the City Key as MCP tools. Zero dependencies.
MIT -
A decentralized cooperative memory & research layer for AI agents — collectively and cooperatively learning and advancing as a community.
MIT ★ 4 -
Three AI agents that detect, diagnose and fix Kubernetes incidents with bounded authority. A2A between agents, MCP for tools, signed AgentFacts and discovery on the NANDA Index.
Apache-2.0 -
@prmaat/github-anchorgithub.com/prmaat/github-anchorupdated this year
Verifiable audit trails for AI agent actions on GitHub. MCP server that lets an AI agent post PR comments/reviews with a PrMaat-anchored receipt — any third party can verify which agent passport, device key, and model produced the comment without trusting
npm MIT