https://cybertoolchain.io/tools/token-security New releases and features in Token Security, tracked by The Cyber Toolchain. en Thu, 06 Aug 2026 15:13:39 GMT https://www.token.security/blog/token-security-brings-anthropic-claude-compliance-api-into-its-identity-control-plane https://www.token.security/blog/token-security-brings-anthropic-claude-compliance-api-into-its-identity-control-plane Thu, 06 Aug 2026 15:13:39 GMT Token Security integrates with Claude's Compliance API to discover, map, and govern Anthropic API keys and AI agent identities. • Integrates with Claude's Compliance API to pull Anthropic identity and activity signals — API keys, workspaces, projects, users, service accounts, model activity, tool usage, administrative events, and key lifecycle events — into Token's identity control plane. • Enables discovery and ownership mapping of Anthropic API keys across the full access chain: from creation in Claude through storage in repository secrets, invocation by CI/CD pipelines, and execution inside cloud workloads. • Surfaces Claude-specific identity posture risks including stale Anthropic keys, keys without clear owners, abandoned workspaces, over-privileged access, and unrotated credentials. • Correlates Claude activity signals with identity and access context from cloud, SaaS, source control, CI/CD, and MCP servers into a unified identity graph, enabling blast-radius analysis for compromised Anthropic identities. • Brings Claude-related identities into Token's posture scoring and remediation workflows alongside other non-human and AI agent identities. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/token-security https://www.token.security/blog/token-security-mcp-server-discovery-capability-uncovers-hidden-ai-servers-and-secrets https://www.token.security/blog/token-security-mcp-server-discovery-capability-uncovers-hidden-ai-servers-and-secrets Thu, 06 Aug 2026 15:13:39 GMT Token Security adds MCP Server Discovery to automatically find, inventory, and analyze hidden AI/MCP servers and embedded secrets across enterprise endpoints. • Automatically retrieves MCP configuration files (e.g., `claude_desktop_config.json`, `.mcp.json` configs) from endpoints via CrowdStrike Real Time Response (RTR) without user disruption. • New MCP Server Discovery capability continuously scans and inventories MCP servers and AI agent processes across enterprise environments, integrating with CrowdStrike and other endpoint ecosystems without requiring additional agents. • Analyzes CrowdStrike logs for IDE and Claude Code instances to pinpoint which MCP servers they are communicating with, surfacing discoveries in near real time. • Scans collected MCP configuration files to identify hardcoded secrets (API keys, plaintext tokens, credentials), correlates them to identities, and safely redacts sensitive values in the platform UI. • Produces a Risk Graph showing each MCP server's connections, access scope, and authentication classification for actionable governance. Full history on Cyber Toolchain: https://cybertoolchain.io/tools/token-security