95 tagged agent-security, measured the same way as everything else here.
Browse within: mcp-server 45policy-as-code 33ai-security 22llm-security 16AI Safety 9agent-security-tools 7api 7Guardrails 5ai-governance 5mcp-security 5model-context-protocol 5
MCP server Claude CodeCodexCursor +2
Open-source antivirus and runtime protection for AI agents, tools, MCP servers, plugins, skills, and package installs. Runs locally from the hol-guard Python package.
emiliaprotocol/emilia-protocol
MCP server Claude CodeCodexCursor +2
Exact-action approval for consequential agent actions: request, track, and verify signed receipts. Runs locally from the @emilia-protocol/mcp-server npm package. Needs 3 environment variables to run.
MCP server Cursor
One of 2 in mcp.json
Gives the agent read and write access to a set of allowed directories on the local filesystem. Runs locally from the @modelcontextprotocol/server-filesystem npm package.
MCP server Claude CodeCodexCursor +2
MCP server exposing Signet cryptographic signing, verification, and content hash tools over stdio. Runs locally from the @signet-auth/mcp-tools npm package.
MCP server Claude CodeCodexCursor +2
MCP server "free-memory-report" as configured in qualixar/skillfortify. Runs json.tool with python. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
One of 2 in .mcp.json
MCP server "solana-dev", hosted remotely at mcp.solana.com, as configured in GeckoVision/gecko-surf.
agentveil-protocol/agentveil-sdk
MCP server Claude CodeCodexCursor +2
Python SDK for routed AI-agent action decisions, approvals, receipt records, and bounded evidence. Runs locally from the agentveil Python package.
MCP server Claude CodeCodexCursor +2
One of 2 in server.json
Accountable Autonomy for AI agents under the EU AI Act: policy-gated tool calls, hash-chained tamper-evident audit trails with external time anchoring, and independently verifiable attestation plus execution receipts per MCP tool call. Runs locally from the vaara Python package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval. Remote server at mcp.tap.human.tech.
gautamvarmadatla/mcpsafetywarden
MCP server Claude CodeCodexCursor +2
MCP proxy server with behavioral profiling, security scanning, risk gating, and safe execution. Runs locally from the mcpsafetywarden Python package.
MCP server Claude CodeCodexCursor +2
Check tokens, pages and x402 payments before your agent trusts them. Offline verdicts. Runs locally from the wormhole-x402 npm package. Needs 3 environment variables to run.
MCP server Claude CodeCodexCursor +2
One of 3 in claude_desktop_config.json
MCP server "github" as configured in arshan846/pluto-aguard. Runs in Docker (ghcr.io/github/github-mcp-server). Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine. Runs locally from the @kryptosai/mcp-seatbelt npm package.
MCP server Claude CodeCodexCursor +2
Defenter proxy. Runs locally from the defenter-proxy Python package.
MCP server Claude CodeCodexCursor +2
Scan AI agents for security vulnerabilities. Audit MCP servers before installation. Runs locally from the @inkog-io/mcp npm package. Needs 1 environment variable to run.
doteyeso-ops/mcp-server-vibes-coded
MCP server Claude CodeCodexCursor +2
Agent supply-chain security, scanner consensus, x402 reliability, and commerce MCP tools. Remote server at vibes-coded-mcp-production.up.railway.app.
MCP server Claude CodeCodexCursor +2
Autonomous security scanner for AI agents. Detects prompt injection, tool abuse, data exfiltration, and OWASP ASI Top 10 vulnerabilities. Runs locally from the dfx-agentguard Python package.
MCP server Claude CodeCodexCursor +2
MCP server "shield" as configured in kobepaw/goop-shield-community. Launched with goop-shield mcp --port 8787.
MCP server Claude CodeCodexCursor +2
Open proof-required execution kernel for consequential actions. Runs locally from the actenon-kernel Python package.
MCP server Claude CodeCodexCursor +2
Audit AI agent configs for prompt injection & rogue MCP servers; vet packages. Runs locally from the zyrax-guard npm package.
MCP server Claude CodeCodexCursor +2
MCP server "velvet-rope" as configured in paulchum/velvet-rope. Runs locally from the velvet-rope Python package.
MCP server Claude CodeCodexCursor +2
MCP server "mcpkernel" as configured in piyushptiwari1/mcpkernel. Launched with mcpkernel serve --host 127.0.0.1 --port 8000. Needs 1 environment variable to run.
rudimentall1/agentic-wallet-guardian-v3
MCP server Claude CodeCodexCursor +2
Decision infrastructure for autonomous AI agents: evaluates a proposed blockchain action intent and returns an explainable ALLOW/WARN/BLOCK decision before execution, signed as a verifiable OAA token. Runs locally from the agentic-wallet-guardian-mcp Python package.
MCP server Claude CodeCodexCursor +2
MCP server "aisentinel" as configured in Kabzhanov/AISentinel. Launched with https://github.com/Kabzhanov/AISentinel/releases/download/v1.0.6/aisentinel-v1.0.