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.
-
Evaluation and runtime governance layer for local LLMs (Ollama + MLX-LM): deterministic policy/provenance guardrails, MCP server, regression gate, and reviewer console
★ 1 -
repo-seatbeltgithub.com/berkcangumusisik/repo-seatbeltupdated this year
A safety layer for AI coding agents. CLAUDE.md/AGENTS.md generator, MCP runtime guardrail, pre-commit hook, GitHub Action.
npm MIT ★ 8 -
Secure-by-design Jenkins MCP server with runtime guardrails. Minibridge integration for Rego/HTTP policy enforcement, Jenkins-aware prompt-injection guardrails, destructive tools opt-in, hardened non-root image, and a Helm chart verified on real clusters.
NOASSERTION ★ 2 -
Lightweight security guardrails for tool-enabled agent runtimes: scan risky payloads, redact secrets, expose stdio/HTTP MCP tools, and write audit logs.
npm MIT -
ACID transactional Saga runtime, Step-0 security guardrail, and MCP server for autonomous AI agents.
Apache-2.0 ★ 1 -
Paid-search BI agent (Strands + Claude) with an NL-to-SQL MCP server on AWS Bedrock AgentCore: sqlglot guardrails, YAML semantic layer, per-runtime least-privilege IAM, held-out eval on 3 seeded warehouses.
NOASSERTION -
The most complete Mailchimp Marketing API MCP server: 227 tools across campaigns, audiences, reports, segments, automations and full e-commerce, with multi-account support and runtime-security guardrails (read-only, dry-run, audit, per-tool risk metadata).
pypi MIT ★ 25 -
Declaw -- Secure AI Sandboxesno update data
Secure runtime for AI agents. Run AI agents and their tools in Firecracker microVMs with network policies, PII scanning, prompt injection defense, and audit logging. 7 tools: create_sandbox, run_command, read_file, write_file, list_files, kill_sandbox, list_sandboxes. Security presets (none / standard / strict) let you control guardrails per sandbox: restrict outbound traffic to specific domains, redact PII from command output, block prompt injections, and get full audit trails.
smithery -
Zero-dependency runtime control for production Python agents - stop loops, retry storms, and budget burn
pypi MIT -
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 -
mcp-supervisorgithub.com/arielsanroj/runtime-supervisorupdated this year
MCP server exposing runtime-supervisor tools to LLM agents (Claude Desktop, Cursor, etc.)
pypi Apache-2.0 -
Deterministic in-process AST security runtime, secret zeroization, and Ed25519 Merkle receipts for Cursor, Claude Code, and autonomous AI agents (<35µs latency).
pypi Apache-2.0 -
pop-paygithub.com/100xPercent/pop-payupdated this year
The runtime security layer for AI agent commerce
npm MIT ★ 1 -
pop-pay-pythongithub.com/100xPercent/pop-pay-pythonupdated this year
The runtime security layer for AI agent commerce
pypi MIT ★ 1 -
MCP server exposing CerbereAG runtime security checks (prompt injection, PII redaction, tool authorization) to any MCP-compatible AI agent (Claude, Cursor, Cline, custom agents).
pypi 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 -
Stateless HTTP 402 micropayment gateway and pre-socket runtime defense engine for autonomous AI agents on Arc Layer 1.
pypi -
⚡ High-frequency (~60Hz) in-browser behavior tree execution engine for autonomous AI agents. Reactive priority interrupts, safety guardrails & deterministic action replay over MCP.
npm MIT ★ 8 -
Attack. Defend. Verify. Red-team your AI agents, enforce zero-trust policy at runtime, and prove each fix holds in CI. Includes an MCP proxy.
NOASSERTION -
The policy layer for AI coding agents. aiZee governs what Cursor, Claude Code, Copilot, Windsurf, Devin & MCP agents may do — 139 enforcement gates, 29 personas, 245 skills, BMAD runtime, hybrid memory, tamper-evident audit. pip install aizee
pypi MIT ★ 6 -
A runtime gate for coding agents: an MCP server that blocks the tool calls that wreck a repo (force-push main, rm -rf, secret exfil, CI wipe) and lets real work through. Machine-checked git-branch core. Tested on 3,790 real commands.
MIT ★ 1 -
zadeh.aigithub.com/deegitech/zadeh-netupdated this year
The AI companion to Zadeh.NET: turn LLM confidence into deterministic Execute/Confirm/Clarify/Reject decisions (ConfidenceGate), generate fuzzy rule sets from plain-language policy via any LLM (RuleSmith), compute adaptive similarity thresholds for RAG/semantic caching (AdaptiveThreshold), and expose fuzzy engines as MCP tools for AI agents. AI designs, fuzzy decides — zero hallucination at runtime. Uses only the .NET base library — no external dependencies. Licensed under AGPL-3.0 / Commercial dual license.
nuget AGPL-3.0-only