Install Aegis in Claude Code
This server doesn't publish a package to a registry, so follow the install steps in its README. Once it runs, register it with Claude Code:
claude mcp add aegis -- <command to start the server>Frequently asked questions
What does the Aegis MCP server do?
Admission control for agent file edits: checks syntax, structural-cost regressions and workspace boundaries, returning BLOCK, WARN or PASS verdicts.
Is the Aegis MCP server free?
Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.
Does Aegis run locally or remotely?
Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.
How do I add Aegis to Claude Code?
Follow the install steps in the project's README at https://github.com/wei9072/aegis, then register it with "claude mcp add".
More security & identity MCP servers
View allAgentforge Trust
KOVY/agentforge-trust-mcp
Query AgentForge Trust Scores for MCP servers before connecting, covering security, code health, behavioral audit, community trust and EU compliance.
Mandare
mandarelabs/mandare
Accountability for AI agent fleets: verify a signed, hash-chained ledger, check budgets, kill an agent, and issue passports and mandates, all through the local CLI.
Clawguard
joergmichno/clawguard-mcp
Security scanner for AI agents that detects prompt injections using regex patterns.
Kakunin
kakunin-ai/kakunin-mcp
Agent compliance and identity: verify an agent's X.509 certificate scope, read its behavioral risk score and append to an immutable audit trail.
Dawshund
samvas-codes/dawshund_mcp
Enumerate AWS IAM data, analyze effective permissions and visualize access relationships across users, roles and resources, based on dAWShund.
Algenta
thyn-ai/algenta-sdk
Algenta decision engine: dataset discovery, exact queries, utility models, decision memory and governed agent runs with approvals and execution receipts.