mcpcut
MCP serverJournal, approve or block, and sandbox every MCP tool call your AI agent makes
Runs locally- Open source
- Security
Journal, approve or block, and sandbox every MCP tool call your AI agent makes
Runs locallyOpen-source MCP proxy that enforces policies, budgets and approvals on agent tool calls
Not checked yetVerify blockchain timestamp proofs offline and anchor file hashes through ProofLedger
Runs locallyCheck whether an MCP server changed its tool list, using a signed public log
Not checked yetRead your Golem agent fleet sessions, live activity and signed record from any client
Not checked yetThreat-intelligence verdicts on a URL, domain or IP before a coding agent connects
Not checked yetSelf-assessment AI governance MCP server with A3 scorecards and ISO 42001 evidence
Runs locallyLocal MCP runtime that checks, approves and records every agent tool call
Runs locally
Read and update your property insurance sites, audits, compliance, actions and values
Not checked yetGrade a URL like an attacker would, scan repos and check Supabase, Stripe and Vercel
Runs locallyOne managed MCP endpoint for a company's tools, with per-person sign-in and audit
Not checked yet
Manage SOC 2, HIPAA and ISO 27001 controls and audit readiness from your AI client
Not checked yetLocal ACT, BLOCK or ESCALATE check that runs before an AI agent takes an action
Runs locally
Read-only guarded SQL access to eight database engines for AI agents
Runs locallyCheck an AI agent you did not build: identity, mandate and tamper-evident work record
Not checked yetGuard that holds risky MCP tool calls for human approval and signs the decisions
Not checked yetCheck an agent's proposed action against its operator's mandate: permit, deny or escalate
Not checked yet
Identity-aware AI tool gateway: every call runs as the requester, under rules, with audit
Not checked yetRead-only MCP registry of evidence reports on AI agents; a signal, not a certification
Not checked yetScan a site's HTTP security headers and get a 0-100 score with copy-paste fixes
Not checked yetAuthorization checks that decide whether an AI agent may make an x402 payment
Not checked yetPermission-aware MCP server that lets Claude read your Odoo 18 or 19 data as one user
Not checked yetMandate gateway for AI trading agents: checks each order, seals reasoning, binds the fill
Runs locallyDeterministic allow/warn/deny risk checks for AI trading agents on Robinhood Chain
Not checked yet
Screen Base smart contracts and B20 tokens: free on-chain check, paid audit over x402
Not checked yetLocal approvals and audit so coding agents use credentials without ever seeing them
Runs locallyExact-action approval and signed receipts for consequential AI agent actions
Runs locallyPolicy-enforced, permission-aware retrieval over your vector databases for agents
Runs locallyGo daemon giving AI agents scoped Linux host tools over MCP instead of an SSH shell
Not checked yetGoverned local memory for coding agents with signed provenance and policy-gated recall
Runs locally