Le catalogue réel des outils pour IA

Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

Local spend caps, kill-switch blocking and Ed25519-signed receipts for AI agent tool calls.

AgentGuard — 20-tool AI safety MCP: policy preflight, risk scoring, audit logging, rate limits.

Safety execution proxy protecting clients during tool calls.

Policy proxy for MCP tool calls. A denied call never reaches the downstream server.

Network-egress firewall for agent tools: check URLs against a declarative policy.

MCP policy proxy: enforces a code of conduct across connectors before the upstream is called.

MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.

MCP policy proxy: enforces a code of conduct across connectors before the upstream is called.

MCP proxy that checks every tools/call against Agent Trust policy, with evidence, before it runs.

{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} free no key

Mask PII in outbound MCP tool-call arguments, unmask the results. Indian identifiers included.

Secret, CVE and dependency-vulnerability scanning for AI agents (free, OSV.dev).

AI cold calling: add leads, preview the cost, run outbound call campaigns, read transcripts.

Score call recordings: booked or lost, lead quality, missed questions, 0 to 10 score, next step

International call & VoIP rates: per-minute prices to call 200+ countries, comparison, dialing help.

FFIEC Call Reports MCP — US bank line-item detail (fleet #338).

Calling codes, phone analysis, dialing guidance, batch normalization and calling windows.

Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.