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.
-
correctover-runtime-guardgithub.com/correctover/runtime-guardupdated this year
Real-time RCE/SSRF/credential leak interception for AI agents — 22µs P50, 99.7% detection rate. MCP Server mode with diagnose_error, fault patterns, repair suggestions.
pypi Apache-2.0 -
Agent runtime guard — full-stack runtime interception for AI agents (Agent 运行时全栈拦截). A zero-dependency MCP server that blocks destructive commands, credential theft, SSRF and injection in real time, with Ed25519 evidence receipts. Works with Claude Code,
npm Elastic-2.0 -
correctover-guard-referenceactive
Correctover Guard - Reference implementation for MCP runtime behavior protection. Integrates CCS verification, runtime guarding, and signed receipts into a complete security layer.
npm MIT -
MCP (Model Context Protocol) Server for TypeScript Type Guard Generation - Generate runtime validation functions from TypeScript types
npm MIT -
Enhanced distribution of HOL Guard: AI agent runtime security with MCP server, African threat intelligence, benchmarks, and architecture visualization
NOASSERTION -
GRADE ≠ GATE — MCP inventory grade is not a runtime gate. Synthetic demo for sentinelagent-guard.
NOASSERTION -
High-performance Rust MCP browser runtime for AI agents, built on Chromium/CDP with DOM interaction, screenshots, GPU/WebGPU acceleration, live browsing, media, authentication, security guards, and automatic Chrome runtime updates.
-
mcportalgithub.com/yonghwan1106/mcportalupdated this year
Quota-guarded runtime layer bridging Korean public data APIs (data.go.kr) into the MCP ecosystem
pypi Apache-2.0 -
Godot ↔ OpenAI Codex bridge with MCP tools, in-editor chat, visual grounding, guarded edits, and runtime verification.
MIT -
GenClass Runtime: a 10 MB in-browser model that detects race conditions, stale responses and duplicate requests in web apps; opt-in guard mode can prevent some of them. npm i @genclass/runtime
npm Apache-2.0 ★ 11 -
Zero-trust security runtime for AI agents with deterministic policy enforcement, guarded execution, approvals, redaction, MCP protection, and tamper-evident auditing.
Apache-2.0 ★ 5 -
🔌 Exposes GDPR Chapter V runtime guard for cross-region agent transfers. Adequacy + SCCs + BCRs + IDTA. MIT
pypi MIT -
🔌 Exposes AI agent prompt injection firewall over MCP — OWASP LLM Top 10 1 runtime guard. MIT.
pypi MIT -
Zero-dependency stdio MCP proxy & runtime context firewall: deterministic tools/list tree-shaking, oversized tools/call crash guard, and live secret redaction for Claude Code, OpenAI Codex, and Cursor.
npm MIT ★ 1 -
🎓 LEAP Framework — a state-driven agentic tutoring runtime for AI agents, exposed over MCP. Server-side State Guard, evidence-based mastery, FSRS retention.
MIT ★ 1 -
SSH, SFTP, PTY shells, host-to-host copies and remote screenshots for AI agents. One Rust binary, no runtime, ~2 ms warm exec. Guards, audit log, stateless MCP.
cargo MIT ★ 5 -
Your dashboard is data. Any AI can build it; any human can edit it. A protocol + runtime for agent-composable dashboards — layout-as-data, one guarded control plane, sandboxed agent-authored widgets, MCP server included.
npm MIT ★ 20 -
MCP server that drafts ISO management-system documents clause by clause (Annex SL): grounding on the client's Word documents, exact-fidelity .docx output, change tracking and a runtime fidelity guard. Clause 4 complete (ISO 9001/14001/45001/37001).
MIT -
SAP ABAP MCPgithub.com/Coaspe/sap-abap-mcpno update data
SAP ABAP MCP is a local-first Model Context Protocol server that enables AI coding agents to develop, test, analyze, and operate SAP ABAP systems through the official ABAP Development Tools HTTP services. It supports repository search and source editing, structured DDIC workflows, enhancement inspection, paged package navigation, source-backed object creation, semantic services, activation, ABAP Unit and ATC, transports, abapGit, RAP generation, debugging, bounded class and executable-program profiling, runtime dumps, traces and feeds, cross-system comparison, dependency analysis, guarded refactoring, and an opt-in same-origin Screen/GUI Status bridge. Curated compact, development, and assurance presets reduce tool-schema token use without removing capabilities from the default surface. The default local stdio mode can be extended with governed self-hosted Streamable HTTP, API-key roles, OIDC/JWT authentication, request-scoped SAP bearer forwarding, per-session isolation, rate limits, structured audit logs, or a side-effect-free embeddable Node.js API. It also includes browser OAuth Authorization Code with PKCE, a read-only transport assurance CLI and GitHub Action, BTP service-key profile import, and live-SAP evidence tooling. SAP profiles and credentials remain on the user's computer, with passwords and OAuth credentials protected by macOS Keychain or Windows DPAPI. SAP-dependent capabilities are validated against the user's own SAP release, configuration, and authorizations.
smithery -
Zero-dependency runtime control for production Python agents - stop loops, retry storms, and budget burn
pypi MIT -
vaikora-guard-mcpgithub.com/data443/vaikora-guard-mcpupdated this year
Model Context Protocol server that enforces deterministic policy on AI tool calls using the Vaikora policy engine.
pypi MIT -
Alpha / research preview: local-first verifier for coding-agent patches (modeled runtime-failure analysis, behavioral contracts, differential replay, MCP) for Python
Apache-2.0 -
agent-guardgithub.com/sneiko/agent-guardupdated this year
Contract-based accountability runtime for AI agents. Define tasks with required evidence — no proof means not done. MCP server with multi-agent pipelines, independent verification, and append-only audit log.
MIT -
Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.
npm MIT -
AlembicCodexgithub.com/GxFn/AlembicCodexupdated this year
Installable Alembic Codex plugin distribution with MCP shim, embedded runtime, skills, marketplace metadata, and release playbook.
MIT -
goop-shield-communitygithub.com/kobepaw/goop-shield-communityupdated this year
Runtime defense for AI agents. 24 inline defenses, 3 output scanners, MCP server, framework adapters.
Apache-2.0 ★ 2 -
ctt-shellgithub.com/MauricioPerera/ctt-shellupdated this year
Universal AI agent framework — 1B models compose multi-step plans like 12B with structured context (CTT). 6 domains, 8 MCP tools, 167 tests, zero runtime deps.