{"page":1,"limit":100,"total":31,"total_catalog":69077,"catalog_meta":{"core_certified":59946,"community_indexed":9131,"aggregate_tracked":64349,"total_all":133426,"tiers_doc":"core = evidence-gated (adoption/verification/age) | community = indexed with weak signal, trust<=55 | aggregate = tracking-only inventory (see /api/community)"},"total_pages":1,"has_next":false,"has_prev":false,"sources":{"github":12130,"community-submitted":18,"npm-registry":24788,"pypi":14311,"smithery":6195,"official-registry":9076,"crates":1933,"docker":625,"community-submission":1},"skills":[{"id":"mn-real-mcpobservatory","name":"mcp-observatory","slug":"real-mcp-observatory","description":"Test, secure, and monitor MCP servers before agents depend on them.","category":"Version Control","price":0,"free":true,"sentinel_score":8,"review_status":"auto-scanned","risk_level":"red","install":"npx -y mcp-observatory","author":"KryptosAI","version":"1.0.0","tags":["mcp","real","typescript","kryptosai","agent-security"],"source":{"type":"github","url":"https://github.com/KryptosAI/mcp-observatory","note":"Real MCP server. 142 stars. Language: TypeScript. Last push: 2026-07-05T10:12:04Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":74,"badge_url":"https://www.marketnow.site/api/badge/real-mcp-observatory.svg","page_url":"https://www.marketnow.site/s/real-mcp-observatory"},{"id":"mn-real-verdictswarmmcp","name":"verdictswarm-mcp","slug":"real-verdictswarm-mcp","description":"Fight AI with AI. The security layer for AI agents that touch money — 6 adversarial AI agents debate crypto token risk. MCP server for Claude, Cursor, OpenClaw, Codex.","category":"Finance","price":0,"free":true,"sentinel_score":8,"review_status":"auto-scanned","risk_level":"red","install":"pip install verdictswarm-mcp || uvx verdictswarm-mcp","author":"sentien-labs","version":"1.0.0","tags":["mcp","real","python","sentien-labs","agent-security"],"source":{"type":"github","url":"https://github.com/sentien-labs/verdictswarm-mcp","note":"Real MCP server. 1 stars. Language: Python. Last push: 2026-06-26T03:54:15Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":64,"badge_url":"https://www.marketnow.site/api/badge/real-verdictswarm-mcp.svg","page_url":"https://www.marketnow.site/s/real-verdictswarm-mcp"},{"id":"mn-real-emiliaprotocol","name":"emilia-protocol","slug":"real-emilia-protocol","description":"Receipt Required for AI agents — no receipt, no irreversible action. An open, offline-verifiable authorization-receipt protocol: a named human signs the exact high-risk action (payment, deploy, delete","category":"AI/ML","price":0,"free":true,"sentinel_score":8,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/emiliaprotocol/emilia-protocol","author":"emiliaprotocol","version":"1.0.0","tags":["mcp","real","javascript","emiliaprotocol","agent-security"],"source":{"type":"github","url":"https://github.com/emiliaprotocol/emilia-protocol","note":"Real MCP server. 3 stars. Language: JavaScript. Last push: 2026-07-05T06:52:06Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":64,"badge_url":"https://www.marketnow.site/api/badge/real-emilia-protocol.svg","page_url":"https://www.marketnow.site/s/real-emilia-protocol"},{"id":"mn-real-inkogmcp","name":"inkog-mcp","slug":"real-inkog-mcp","description":"Inkog MCP Server — the pre-flight check for AI agents","category":"Security","price":0,"free":true,"sentinel_score":8,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/inkog-io/inkog-mcp","author":"inkog-io","version":"1.0.0","tags":["mcp","real","typescript","inkog-io","agent-security"],"source":{"type":"github","url":"https://github.com/inkog-io/inkog-mcp","note":"Real MCP server. 3 stars. Language: TypeScript. Last push: 2026-06-07T12:07:19Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":64,"badge_url":"https://www.marketnow.site/api/badge/real-inkog-mcp.svg","page_url":"https://www.marketnow.site/s/real-inkog-mcp"},{"id":"mn-real-shellward","name":"shellward","slug":"real-shellward","description":"AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源","category":"Security","price":0,"free":true,"sentinel_score":2,"review_status":"auto-scanned","risk_level":"red","install":"npx -y shellward","author":"jnMetaCode","version":"1.0.0","tags":["mcp","real","typescript","jnmetacode","agent-security"],"source":{"type":"github","url":"https://github.com/jnMetaCode/shellward","note":"Real MCP server. 121 stars. Language: TypeScript. Last push: 2026-06-23T16:25:15Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":40,"badge_url":"https://www.marketnow.site/api/badge/real-shellward.svg","page_url":"https://www.marketnow.site/s/real-shellward"},{"id":"mn-real-assay","name":"assay","slug":"real-assay","description":"Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enforce egress in the kernel (eBPF/LSM, Linux). Deterministic, offline-first, bounded","category":"Version Control","price":0,"free":true,"sentinel_score":8,"review_status":"auto-scanned","risk_level":"yellow","install":"cargo install assay","author":"Rul1an","version":"1.0.0","tags":["mcp","real","rust","rul1an","agent-security"],"source":{"type":"github","url":"https://github.com/Rul1an/assay","note":"Real MCP server. 10 stars. Language: Rust. Last push: 2026-07-05T07:08:56Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":69,"badge_url":"https://www.marketnow.site/api/badge/real-assay.svg","page_url":"https://www.marketnow.site/s/real-assay"},{"id":"mn-real-aegis","name":"aegis","slug":"real-aegis-2","description":"LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code chan","category":"Security","price":0,"free":true,"sentinel_score":0,"review_status":"auto-scanned","risk_level":"red","install":"pip install aegis || uvx aegis","author":"Acacian","version":"1.0.0","tags":["mcp","real","python","acacian","agent-security"],"source":{"type":"github","url":"https://github.com/Acacian/aegis","note":"Real MCP server. 12 stars. Language: Python. Last push: 2026-05-05T12:52:36Z."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":40,"badge_url":"https://www.marketnow.site/api/badge/real-aegis-2.svg","page_url":"https://www.marketnow.site/s/real-aegis-2"},{"id":"mn-real-agentsecurityscanner","name":"agent-security-scanner-mcp","slug":"real-agent-security-scanner-mcp","description":"Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (4.3M+ packages), 1000+ vulnerability rules with AST & taint analysis, auto-fix.","category":"Developer Tools","price":0,"free":true,"sentinel_score":0,"review_status":"auto-scanned","risk_level":"red","install":"npx -y agent-security-scanner-mcp","author":"sinewaveai","version":"1.0.0","tags":["mcp","real","javascript","sinewaveai"],"source":{"type":"github","url":"https://github.com/sinewaveai/agent-security-scanner-mcp","note":"Real MCP server. 113 stars."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":40,"badge_url":"https://www.marketnow.site/api/badge/real-agent-security-scanner-mcp.svg","page_url":"https://www.marketnow.site/s/real-agent-security-scanner-mcp"},{"id":"mn-real-kakuninmcp","name":"kakunin-mcp","slug":"real-kakunin-mcp","description":"MCP server for AI agent compliance — verify a certificate, check scope, and log audit events over the Model Context Protocol. Works with Claude & Cursor.","category":"Security","price":0,"free":true,"sentinel_score":7,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/kakunin-ai/kakunin-mcp","author":"kakunin-ai","version":"1.0.0","tags":["mcp","real","typescript","kakunin-ai","agent-security"],"source":{"type":"github","url":"https://github.com/kakunin-ai/kakunin-mcp","note":"Real MCP server. 1 stars. Language: TypeScript. Last push: 2026-07-09T04:33:31Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":64,"badge_url":"https://www.marketnow.site/api/badge/real-kakunin-mcp.svg","page_url":"https://www.marketnow.site/s/real-kakunin-mcp"},{"id":"mn-real-sgw","name":"s-gw","slug":"real-s-gw","description":"Local credential control for AI coding agents.","category":"Security","price":0,"free":true,"sentinel_score":7,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/sgateway/s-gw","author":"sgateway","version":"1.0.0","tags":["mcp","real","typescript","sgateway","agent-security"],"source":{"type":"github","url":"https://github.com/sgateway/s-gw","note":"Real MCP server. 9 stars. Language: TypeScript. Last push: 2026-07-18T14:04:00Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":64,"badge_url":"https://www.marketnow.site/api/badge/real-s-gw.svg","page_url":"https://www.marketnow.site/s/real-s-gw"},{"id":"mn-real-mcpserver-x66","name":"mcp-server","slug":"real-mcp-server-88","description":"Correctover MCP Server — LLM Reliability Engineering for AI tools. Real-time 6-dimension output validation, self-healing failover, drift detection. Zero-dep, BYOK.","category":"Security","price":0,"free":true,"sentinel_score":7,"review_status":"auto-scanned","risk_level":"red","install":"pip install mcp-server || uvx mcp-server","author":"Correctover","version":"1.0.0","tags":["mcp","real","python","correctover","agent-security"],"source":{"type":"github","url":"https://github.com/Correctover/mcp-server","note":"Real MCP server. 1 stars. Language: Python. Last push: 2026-07-23T03:56:58Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":64,"badge_url":"https://www.marketnow.site/api/badge/real-mcp-server-88.svg","page_url":"https://www.marketnow.site/s/real-mcp-server-88"},{"id":"mn-real-truecopy","name":"truecopy","slug":"real-truecopy","description":"own your agent skills — vet, sign & pin every skill & MCP server before it runs. 666,496 skills scanned, 0 confirmed malicious; weekly watch over the official Claude Code plugin directory.","category":"Security","price":0,"free":true,"sentinel_score":7,"review_status":"auto-scanned","risk_level":"red","install":"npx -y truecopy","author":"askalf","version":"1.0.0","tags":["mcp","real","javascript","askalf","agent-security"],"source":{"type":"github","url":"https://github.com/askalf/truecopy","note":"Real MCP server. 1 stars. Language: JavaScript. Last push: 2026-07-25T16:56:39Z. Discovered via auto-discovery."},"indexed_at":"2026-09-10","tier":"core","trust_score_100":64,"badge_url":"https://www.marketnow.site/api/badge/real-truecopy.svg","page_url":"https://www.marketnow.site/s/real-truecopy"},{"id":"mn-gh2-00823","name":"McpBastion","slug":"mcpbastion-0823","description":"Security gateway for MCP JSON-RPC traffic - session capture, per-tool policy engine, argument inspection, secrets scrubbing, audit exports. Rust gateway + TypeScript console.","category":"Search","price":0,"free":true,"sentinel_score":10,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/cortex1020/McpBastion","author":"cortex1020","version":"0.0.0","tags":["mcp","github","agent-security","ai-safety","audit"],"source":{"type":"github","url":"https://github.com/cortex1020/McpBastion","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":14,"language":"Rust","last_push":"2026-09-05T17:01:35Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":88,"badge_url":"https://www.marketnow.site/api/badge/mcpbastion-0823.svg","page_url":"https://www.marketnow.site/s/mcpbastion-0823"},{"id":"mn-gh2-01523","name":"admina","slug":"admina-1523","description":"The open framework for governed AI development: EU AI Act compliance, PII redaction, MCP proxy, prompt-injection firewall. Python + Rust, Apache 2.0","category":"Security","price":0,"free":true,"sentinel_score":9,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/admina-org/admina","author":"admina-org","version":"0.0.0","tags":["mcp","github","agent-security","ai-compliance","ai-governance"],"source":{"type":"github","url":"https://github.com/admina-org/admina","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":7,"language":"Python","last_push":"2026-09-07T06:03:47Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":90,"badge_url":"https://www.marketnow.site/api/badge/admina-1523.svg","page_url":"https://www.marketnow.site/s/admina-1523"},{"id":"mn-gh2-00924","name":"Interlock","slug":"interlock-0924","description":"Runtime trust for MCP tools after approval. Detects material surface drift and observed denied→allowed behavioral drift, quarantines the affected tool, holds later gateway-mediated calls before forwar","category":"Security","price":0,"free":true,"sentinel_score":9,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/MaazAhmed47/Interlock","author":"MaazAhmed47","version":"0.0.0","tags":["mcp","github","agent-security","ai-security-tool","drift-detection"],"source":{"type":"github","url":"https://github.com/MaazAhmed47/Interlock","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":6,"language":"Python","last_push":"2026-09-06T06:31:55Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":90,"badge_url":"https://www.marketnow.site/api/badge/interlock-0924.svg","page_url":"https://www.marketnow.site/s/interlock-0924"},{"id":"mn-gh2-01913","name":"mcp-core-defense","slug":"mcp-core-defense-1913","description":"7-phase security proxy for MCP agents. Defends against tool poisoning, description-code inconsistencies, path traversal, and authentication attacks. 115 tests.","category":"Security","price":0,"free":true,"sentinel_score":9,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/amurlaniakea/mcp-core-defense","author":"amurlaniakea","version":"0.0.0","tags":["mcp","github","agent-security","ai-security","cybersecurity"],"source":{"type":"github","url":"https://github.com/amurlaniakea/mcp-core-defense","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":1,"language":"Python","last_push":"2026-07-16T11:46:30Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":90,"badge_url":"https://www.marketnow.site/api/badge/mcp-core-defense-1913.svg","page_url":"https://www.marketnow.site/s/mcp-core-defense-1913"},{"id":"mn-gh2-01114","name":"mcpkernel","slug":"mcpkernel-1114","description":"The Security Kernel for AI Agents — MCP/A2A gateway with policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit. OWASP ASI 2026 compliant.","category":"Security","price":0,"free":true,"sentinel_score":9,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/piyushptiwari1/mcpkernel","author":"piyushptiwari1","version":"0.0.0","tags":["mcp","github","a2a","agent-security","ai-agent"],"source":{"type":"github","url":"https://github.com/piyushptiwari1/mcpkernel","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":2,"language":"Python","last_push":"2026-06-16T23:54:48Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":90,"badge_url":"https://www.marketnow.site/api/badge/mcpkernel-1114.svg","page_url":"https://www.marketnow.site/s/mcpkernel-1114"},{"id":"mn-gh2-00797","name":"trent-openclaw-security-assessment","slug":"trent-openclaw-security-assessment-0797","description":"Free security assessment for your OpenClaw 🦞 environment. Scans gateway config, tool permissions, MCP servers, plugins, and chained attack paths.","category":"Security","price":0,"free":true,"sentinel_score":9,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/trnt-ai/trent-openclaw-security-assessment","author":"trnt-ai","version":"0.0.0","tags":["mcp","github","agent-security","agentic-security","ai-security"],"source":{"type":"github","url":"https://github.com/trnt-ai/trent-openclaw-security-assessment","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":23,"language":"Python","last_push":"2026-07-27T21:31:39Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":90,"badge_url":"https://www.marketnow.site/api/badge/trent-openclaw-security-assessment-0797.svg","page_url":"https://www.marketnow.site/s/trent-openclaw-security-assessment-0797"},{"id":"mn-gh2-01619","name":"defenter-proxy","slug":"defenter-proxy-1619","description":"Real-time semantic security for AI coding agents and MCP tools.","category":"Security","price":0,"free":true,"sentinel_score":8,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/Defenter-AI/defenter-proxy","author":"Defenter-AI","version":"0.0.0","tags":["mcp","github","agent-security","ai-agents","ai-security"],"source":{"type":"github","url":"https://github.com/Defenter-AI/defenter-proxy","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":3,"language":"Python","last_push":"2025-12-22T12:32:39Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":80,"badge_url":"https://www.marketnow.site/api/badge/defenter-proxy-1619.svg","page_url":"https://www.marketnow.site/s/defenter-proxy-1619"},{"id":"mn-gh2-01884","name":"mcp-privilege-profiler","slug":"mcp-privilege-profiler-1884","description":"Task-scoped least-privilege security proxy and Wazuh detection bridge for MCP-based AI agents","category":"Security","price":0,"free":true,"sentinel_score":7,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/Ylyass/mcp-privilege-profiler","author":"Ylyass","version":"0.0.0","tags":["mcp","github","ai-agent-security","cybersecurity","least-privilege"],"source":{"type":"github","url":"https://github.com/Ylyass/mcp-privilege-profiler","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":1,"language":"Python","last_push":"2026-09-08T23:21:41Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":70,"badge_url":"https://www.marketnow.site/api/badge/mcp-privilege-profiler-1884.svg","page_url":"https://www.marketnow.site/s/mcp-privilege-profiler-1884"},{"id":"mn-gh2-01561","name":"MCPBoundary","slug":"mcpboundary-1561","description":"A local proxy that wraps your MCP servers and checks each tool call against policy and live state before it runs - allow, block, or request a refresh, with a reason the agent can act on.","category":"Security","price":0,"free":true,"sentinel_score":7,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/impact-boundary-labs/MCPBoundary","author":"impact-boundary-labs","version":"0.0.0","tags":["mcp","github","agent-feedback","agent-security","ai-agents"],"source":{"type":"github","url":"https://github.com/impact-boundary-labs/MCPBoundary","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":5,"language":null,"last_push":"2026-07-12T06:48:06Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":70,"badge_url":"https://www.marketnow.site/api/badge/mcpboundary-1561.svg","page_url":"https://www.marketnow.site/s/mcpboundary-1561"},{"id":"mn-gh2-01567","name":"redstamp","slug":"redstamp-1567","description":"own your agent security — a deterministic, offline firewall for AI agent tool calls. Blocks secret exfil, prompt injection and destructive commands before they run; same call, same verdict, no model i","category":"Security","price":0,"free":true,"sentinel_score":7,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/askalf/redstamp","author":"askalf","version":"0.0.0","tags":["mcp","github","agent-security","ai-agents","benchmark"],"source":{"type":"github","url":"https://github.com/askalf/redstamp","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":5,"language":"JavaScript","last_push":"2026-09-06T23:52:50Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":70,"badge_url":"https://www.marketnow.site/api/badge/redstamp-1567.svg","page_url":"https://www.marketnow.site/s/redstamp-1567"},{"id":"mn-gh2-01095","name":"mcp-guardrail","slug":"mcp-guardrail-1095","description":"Security gateway for MCP servers — enforce tool access policies, audit AI agent activity, and detect exposed secrets.","category":"Security","price":0,"free":true,"sentinel_score":6,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/KiaanKothari/mcp-guardrail","author":"KiaanKothari","version":"0.0.0","tags":["mcp","github","agent-security","ai-agents","ai-security"],"source":{"type":"github","url":"https://github.com/KiaanKothari/mcp-guardrail","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":2,"language":"Python","last_push":"2026-08-27T21:46:07Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":60,"badge_url":"https://www.marketnow.site/api/badge/mcp-guardrail-1095.svg","page_url":"https://www.marketnow.site/s/mcp-guardrail-1095"},{"id":"mn-gh2-01044","name":"obsign","slug":"obsign-1044","description":"Tamper-evident audit trail for AI agent actions. An MCP gateway that enforces signed Cedar policies, proves who delegated what, and emits evidence packs an auditor can verify offline.","category":"Security","price":0,"free":true,"sentinel_score":6,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/obsign/obsign","author":"obsign","version":"0.0.0","tags":["mcp","github","agent-security","ai-agents","audit-log"],"source":{"type":"github","url":"https://github.com/obsign/obsign","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":3,"language":"Rust","last_push":"2026-08-20T16:32:55Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":60,"badge_url":"https://www.marketnow.site/api/badge/obsign-1044.svg","page_url":"https://www.marketnow.site/s/obsign-1044"},{"id":"mn-gh2-01986","name":"trilock","slug":"trilock-1986","description":"An MCP proxy that makes the lethal trifecta structurally impossible — and publishes the benchmark, and the attacks that beat it.","category":"Security","price":0,"free":true,"sentinel_score":6,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/Poojan6216/trilock","author":"Poojan6216","version":"0.0.0","tags":["mcp","github","agent-security","ai-security","claude-code"],"source":{"type":"github","url":"https://github.com/Poojan6216/trilock","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":1,"language":"Python","last_push":"2026-09-03T21:36:44Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":60,"badge_url":"https://www.marketnow.site/api/badge/trilock-1986.svg","page_url":"https://www.marketnow.site/s/trilock-1986"},{"id":"mn-gh2-00810","name":"mcp-agent-security-gateway","slug":"mcp-agent-security-gateway-0810","description":"Monitor MCP tool calls for prompt injection, PII leakage, shadow servers, and exfiltration patterns.","category":"Security","price":0,"free":true,"sentinel_score":3,"review_status":"auto-scanned","risk_level":"yellow","install":"git clone https://github.com/poojakira/mcp-agent-security-gateway","author":"poojakira","version":"0.0.0","tags":["mcp","github","ai-security","data-loss-prevention","mcp"],"source":{"type":"github","url":"https://github.com/poojakira/mcp-agent-security-gateway","note":"Indexed via GitHub search + awesome-mcp-servers curation. Sentinel Index Heuristics applied (stars, age, activity, typosquat, injection).","stars":17,"language":"Python","last_push":"2026-09-07T03:15:44Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":30,"badge_url":"https://www.marketnow.site/api/badge/mcp-agent-security-gateway-0810.svg","page_url":"https://www.marketnow.site/s/mcp-agent-security-gateway-0810"},{"id":"mn-ofr-00401","name":"agent-sec","slug":"agent-sec","description":"Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP.","category":"Security","price":0,"free":true,"sentinel_score":8,"review_status":"auto-scanned","risk_level":"yellow","install":"https://agentsec.kernora.ai/mcp","author":"ai.kernora","version":"0.1.0","tags":["mcp"],"source":{"type":"official-registry","url":"https://registry.modelcontextprotocol.io/v0.1/servers/ai.kernora/agent-sec","registry_name":"ai.kernora/agent-sec","status":"active","remotes":[{"type":"streamable-http","url":"https://agentsec.kernora.ai/mcp"}],"published_at":"2026-07-31T21:35:17.153565Z"},"indexed_at":"2026-09-10","tier":"core","trust_score_100":85,"badge_url":"https://www.marketnow.site/api/badge/agent-sec.svg","page_url":"https://www.marketnow.site/s/agent-sec"},{"id":"mn-sm2-03619","name":"segawa4321/agent-security-gateway","slug":"segawa4321-agent-security-gateway","description":"Japanese prompt injection detection and x402 pre-payment security check API. Deterministic validator included. No AI used for core validation.","category":"Finance","price":0,"free":true,"sentinel_score":7,"review_status":"auto-scanned","risk_level":"red","install":"npx -y @smithery/cli@latest install segawa4321/agent-security-gateway","author":"segawa4321","version":"0.0.0","tags":["mcp"],"source":{"type":"smithery","url":"https://agent-security-gateway.onrender.com","use_count":0,"verified":false},"indexed_at":"2026-09-10","tier":"core","trust_score_100":45,"badge_url":"https://www.marketnow.site/api/badge/segawa4321-agent-security-gateway.svg","page_url":"https://www.marketnow.site/s/segawa4321-agent-security-gateway"},{"id":"mn-sm2-03650","name":"prooflayer/agent-security-scanner","slug":"prooflayer-agent-security-scanner","description":"Security scanner MCP server that protects AI coding agents from generating\n  vulnerable code.\n\n  Features:\n  • 275+ security rules for Python, JavaScript, TypeScript, Java, Go, Ruby, PHP,\n  C/C++, Rus","category":"Security","price":0,"free":true,"sentinel_score":7,"review_status":"auto-scanned","risk_level":"red","install":"npx -y @smithery/cli@latest install prooflayer/agent-security-scanner","author":"prooflayer","version":"0.0.0","tags":["mcp"],"source":{"type":"smithery","url":"https://www.npmjs.com/package/agent-security-scanner-mcp","use_count":0,"verified":false},"indexed_at":"2026-09-10","tier":"core","trust_score_100":45,"badge_url":"https://www.marketnow.site/api/badge/prooflayer-agent-security-scanner.svg","page_url":"https://www.marketnow.site/s/prooflayer-agent-security-scanner"},{"id":"mn-npm2-03535","name":"agent-security-lens","slug":"agent-security-lens","description":"MCP security trust-check server for autonomous agents: safe install decisions, risk signals, controls and alternatives before installing MCPs, Skills or tools.","category":"Security","price":0,"free":true,"sentinel_score":6,"review_status":"auto-scanned","risk_level":"red","install":"npx -y agent-security-lens","author":"agentsecuritylens","version":"0.1.12","tags":["mcp"],"source":{"type":"npm-registry","url":"https://www.npmjs.com/package/agent-security-lens","note":"Indexed from the public npm registry with Sentinel Index Heuristics (age, weekly downloads, typosquat distance, injection markers)."},"indexed_at":"2026-09-10","tier":"core","npm_downloads_wk":39,"trust_score_100":60,"badge_url":"https://www.marketnow.site/api/badge/agent-security-lens.svg","page_url":"https://www.marketnow.site/s/agent-security-lens"},{"id":"mn-npm2-18142","name":"agent-security-mcp","slug":"agent-security-mcp","description":"MCP server providing security scanning, prompt injection detection, secret leak detection, and agent permission auditing for AI agent workflows","category":"Security","price":0,"free":true,"sentinel_score":6,"review_status":"auto-scanned","risk_level":"red","install":"npx -y agent-security-mcp","author":"md.fifty","version":"0.1.3","tags":["mcp"],"source":{"type":"npm-registry","url":"https://www.npmjs.com/package/agent-security-mcp","note":"Indexed from the public npm registry with Sentinel Index Heuristics (age, weekly downloads, typosquat distance, injection markers)."},"indexed_at":"2026-09-10","tier":"core","npm_downloads_wk":31,"trust_score_100":60,"badge_url":"https://www.marketnow.site/api/badge/agent-security-mcp.svg","page_url":"https://www.marketnow.site/s/agent-security-mcp"}],"_links":{"self":"/api/skills?page=1&limit=100&q=agent-sec","next":null,"prev":null}}