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.
-
Local-first MCP server: hash-chained document store with signed retrieval receipts and an agent orient (staleness/drift) protocol.
npm Apache-2.0 -
org-as-codegithub.com/SYNTRIAD/org-as-codeupdated this year
The missing governance layer for AI agent teams. P↔V protocol, hash-chain audit trails, 21 MCP tools.
MIT ★ 1 -
CLI, library, and MCP server for signing, hash-chaining, and verifying compute usage receipts across any provider.
go Apache-2.0 -
🔐 Cryptographic audit trails for AI decisions — hash chains, Merkle trees, RFC 3161 timestamps, compliance presets for HIPAA/GDPR/SOC2
MIT ★ 1 -
Local-first MCP server: hash-chained document store, signed retrieval receipts, and an orient protocol that tells your agent when its beliefs went stale.
Apache-2.0 ★ 1 -
A tamper-evident record of what an agent actually did — hash-chained, signed, anchored, and honest about what that does not prove.
MIT -
conduit-browsergithub.com/bkauto3/conduitupdated this year
Headless browser with SHA-256 hash chain + Ed25519 audit trails. MCP server for AI agents. Stealth. Self-verifiable proof bundles.
pypi MIT -
Mycorrhiza-MCPgithub.com/sfaustodev/Mycorrhiza-MCPupdated this year
Persistent memory MCP server (SHA-256 hash chain, local SQLite) — gives your AI the power of continuity, of remembering itself as if having a life, like you.
MIT ★ 2 -
MCP work queue for parallel coding agents: claim fencing, path-scoped claims, typed links, atomic batches, hash-chained history (composes with kronicle-lite).
npm Apache-2.0 -
Mount the AI-safety literature. A deterministic coverage engine shows which of ten risk classes your reading volume actually covers, sealed into a replayable hash chain.
NOASSERTION -
Signed, tamper-evident audit log — as a service. ECDSA hash-chained events + MCP server for AI agents (Claude Desktop, Claude Code, Cursor). Any tampering breaks the chain visibly. Auditors verify offline against the public key. Regulated-industries-first, MIT-licensed.
MIT -
mcp-evidence-ledgergithub.com/brianpelow/mcp-evidence-ledgerupdated this year
An MCP server providing an append-only, hash-chained evidence ledger for agent actions. Tamper-evident receipts over real local state; deterministic, no LLM. Agents are non-deterministic; their audit trail should not be.
Apache-2.0 ★ 1 -
mcp-eu-complyupdated this year
Runtime EU AI Act compliance wrapper for MCP servers. Audit logging with hash chain, human oversight, risk classification, and PII redaction — designed to meet Article 12, 14, and 19 requirements.
npm MIT -
Fast, deterministic verifier and gate for AI agents: exact math, claim and citation checks, shell/write policy, hash-chained step ledger and a Temporal Router. Local MCP server + CLI in Rust. Preview.
NOASSERTION ★ 44 -
TypeScript SDK + MCP server for Tersign, the record layer for the machine age — counter-signed EIP-712 receipts, hash-chained action and disclosure records, refunds, disputes, venue-formatted evidence envelopes. npm: tersign
npm Apache-2.0 ★ 1 -
The model proposes, deterministic code disposes, a human signs. Content-addressed envelopes, hash-chained audit, signed approval — for ledgers, Lean proofs, manuscript claims, reproductions, benchmarks, peer review. Conformance-tested; byte-compatible with @kernel.chat/kbot-finance.
MIT -
kbot-financegithub.com/isaacsight/kbot-financeupdated this year
Audit-grade AI infrastructure for AI agents in regulated industries. Content-addressed envelopes, hash-chained audit log, jurisdiction-aware regulatory verifier, MCP server. The AI Intelligence Layer never produces the number — engines do.
NOASSERTION ★ 1 -
Sanchay is an immutable concurrent audit engine where an AI agent runs a full statutory revenue audit through MCP tools. Its hash-chained OCaml ledger and Go gateway feed a Python engine that uses Tarjan and Johnson cycle search for circular trading plus Benford's law for unusual amounts plus a sealed seed for reproducible sampling.
★ 1 -
Model Context Protocol server for TELOS AI Labs governance (scoring, unsigned integrity-hash receipts, audit chain, CCRS replay).
pypi Apache-2.0 -
MCP trust boundary — descriptor hash pinning and hash-chained evidence envelopes (optional signing) over third-party MCP tool calls.
go AGPL-3.0 -
🔌 Exposes Register content with cryptographic hashes and timestamps, verify integrity, search the registry, and track full provenance chains. Uses SHA-256 hashing.
pypi MIT -
@verdict-systems/mcpgithub.com/verdict-systems/verdict-mcpupdated this year
Verdict — the evidence layer for Claude legal workflows. Seal Claude AI outputs into court-preparable Sealed Evidence Records (hash, Merkle root, chain of custody, FRE 902(14) packet).
npm Apache-2.0 -
agent-audit-mcpgithub.com/Rumblingb/agent-audit-mcpupdated this year
Immutable audit trail for A2A via MCP. SHA-256 hash chain.
MIT ★ 3 -
A signed, hash-chained SQLite ledger of AI agent work, served over MCP.
MIT -
Zero-cloud agent sandbox runner: Go daemon, MCP tool gateway, hash-chained audit
MIT -
Tamper-evident audit-log aggregator with hash-chained attestation
NOASSERTION -
Security-tooling MCP server with SSRF guards, prompt-injection containment and a hash-chained audit log
MIT -
Local IntentLedger + MCP stdio proxy: propose, approve/deny, hash-chained ledger. Optional HMAC seals.
pypi MIT -
Four-layer memory substrate for long-horizon agents: write-gate admission, signed approvals, hash-chained ledger, revocable and portable.
MIT ★ 4 -
Read-only MCP catalog tools with host-assigned permissions, SQLite enforcement, audit hash chaining, and measured stdio misuse tests.
NOASSERTION -
@nobulex/mcp-servergithub.com/nobulexdev/nobulex-mcpupdated this year
Nobulex MCP compliance server — covenant rule checking, hash-chained audit logs, and integrity verification for any MCP-compatible agent.
npm MIT -
@kajaril/audit-event-mcpgithub.com/mightbesaad/audit-event-mcpupdated this year
Agent steward infrastructure — hash-chained audit log, Merkle notary, and GDPR/AI-Act compliance skill.
npm MIT -
MCP server for AI booking agents: rules in code, no double bookings, staff approval for late changes, hash-chained audit log.
MIT -
agent-audit-trail-mcpgithub.com/AiAgentKarl/agent-audit-trail-mcpupdated this year
Immutable audit logging for AI agents — hash-chained event log, integrity verification, EU AI Act compliance
pypi MIT ★ 1 -
consentledgergithub.com/cognis-digital/consentledgerupdated this year
Maintain a tamper-evident, hash-chained audit log of patient-data access and consent events.
NOASSERTION -
MCP server that adds a fail-closed quality gate and hash-chained receipt ledger to any AI agent workflow.
MIT ★ 3 -
Watch solar storms hit Earth live: NOAA+NASA feeds, deterministic risk engine, 3D globe, MCP agent tools, hash-chained seals.
MIT -
@rankigi/mcp-serverupdated this year
RANKIGI MCP server for Claude Desktop and other MCP clients. Every tool call is hashed into the RANKIGI chain.
npm MIT -
Minimal MCP server from scratch in Python stdlib: JSON-RPC 2.0, stdio/HTTP, HS256 bearer auth, SQLite memory, hash-chained audit log.
Apache-2.0 -
agentic-event-storegithub.com/Sanoy24/agentic-event-storeupdated this year
Append-only PostgreSQL event store for multi-agent AI systems: optimistic concurrency, CQRS projections, hash-chained audit ledger, and an MCP server.
★ 1 -
Local Go daemon that gives AI tools persistent shared workspace state. Context assembly, multi-provider inference routing, hash-chained ledger, MCP server.
go MIT ★ 2 -
Phish.net/Phish.in MCP with a phased vault/live/cache design. Hash-locked supply chain, 80% coverage gate, dual Trivy scans. FastMCP, Streamable HTTP.
MIT ★ 1 -
MCP server that holds irreversible agent actions until a human approves them, with a hash-chained audit log.
MIT -
Read-only SQL gateway for AI agents (REST + MCP): AST validation, forced pagination, scoped auth, hash-chained audit log.
MIT -
Governed compliance evidence from AIops audit trails: HIPAA/PCI-DSS/SOC2/GDPR, hash-chain-sealed, 15 MCP tools (preview)
pypi MIT -
ledgerproofgithub.com/cognis-digital/ledgerproofupdated this year
Verifies double-entry ledger integrity and tamper-evidence by checking balance invariants and hash-chained journal entries.
NOASSERTION -
Live solar-storm + seismic ops globe: NOAA/USGS feeds, deterministic risk engine, MCP agent tools, hash-chained seals.
MIT -
Agent-first browser automation runtime — deterministic Chromium sessions with replay-equal hash chains, MCP-native tools, and a content-addressed action store.
Apache-2.0 ★ 1 -
Illustrative sample on synthetic data (no client relationship): MCP server with per-tool scopes, tenant isolation, human approval and a hash-chained audit log.
MIT -
spoorgithub.com/RECTOR-LABS/spoorupdated this year
Autonomous DFIR agent driving SANS SIFT forensic tools via an MCP server + LangGraph, with guardrails and a hash-chained audit trail.
MIT ★ 2 -
codegraph-mcpgithub.com/cognis-digital/codegraph-mcpupdated this year
No-train, on-prem code knowledge graph served to AI agents over MCP, with a hash-chained audit row for every read.
NOASSERTION ★ 7 -
arsaguardactive
Brakes for your trading agent: a deterministic rules MCP server between Claude, Cursor or Codex and Robinhood Agentic Trading. Every order checked, every decision hash-chained.
npm MIT -
agent-incident-reporter-mcpupdated this year
Signed, hash-chained, tamper-evident AI incident records (MCP server). EU AI Act Art 73 ready. By MEOK AI Labs / CSOAI.
pypi MIT -
Read-only MCP server for on-premises Microsoft SQL Server: SELECT-only gate, login permission check, hash-chained audit log
mcpb MIT -
MCP server for the Semantic Scholar Academic Graph - papers, authors, citations and recommendations, with hash-chained query receipts.
MIT ★ 2 -
MCP server for the OpenAlex API - works, authors, sources, institutions and citation relations, with hash-chained query receipts.
MIT ★ 1 -
Security layer for AI agents: real-time interception of pip/npm/cargo/gem/go installs via Hermes & OpenClaw plugins, Claude Code/Codex hooks, MCP, shell guard, PATH shim, execve, and index proxy. Checks CVEs (OSV/NVD/GitHub), typosquats, malware, licenses, provenance, trust, lockfile hashes. Offline mirror, hash-chained audit, SBOM/SARIF.
MIT ★ 4 -
Tamper-evident audit log for B2B SaaS: hash-chained, anchored to Sigstore Rekor and OpenTimestamps, verifiable offline. Claude MCP connector included.
npm NOASSERTION ★ 3 -
Valta-MCPgithub.com/Valta-hq/Valta-MCPupdated this year
Financial guardrails for AI agents — pre-call spend gates and a cryptographically hash-chained audit trail. Stops an agent before it overspends, not after.
MIT ★ 1 -
delboy-mcpupdated this year
DELBOY companion-MCP — neutral provenance/attestation layer for agentic finance. Witness only: signs, hash-chains, timestamps. Never holds funds, routes orders, recommends trades, or executes.
pypi Apache-2.0