> ## Documentation Index
> Fetch the complete documentation index at: https://docs.flintai.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> What's new in Flint AI Platform

Release notes for Flint AI Platform.

<Update label="July 30, 2026">
  **Added:**

  * **ROI charts** - Agent detail pages and the dashboard now chart return on investment over time, and the agent table carries ROI columns
  * **Agent spend caps** - Set a cap per agent or per month, with a cap-aware burn rate and a dashboard summary, so teams can track and manage agent spend
  * **Cost data page** - Spend and per-model pricing in one place
  * **MCP server for coding agents** - This release adds `flintai-mcp`, a read-only server that gives Claude Code, Cursor, and other MCP-aware agents access to scan findings, inventory, and remediation guidance, so an agent can fix flagged code without leaving its editing loop. The installable package follows in a later release

  **Changed:**

  * **Automatic re-authentication** - Sessions prompt a new sign-in when authentication expires, keeping access secure

  **Fixed:**

  * **Agent table columns** - Last seen and created dates display correctly
  * **Severity for local services** - Findings on services bound to localhost now score as local rather than network-reachable, giving more accurate severity
  * **Platform reliability** - Service availability, update handling, and API request validation improved across the platform

  **Security:**

  * **Platform hardening** - Tightened service security configuration and updated dependencies
</Update>

<Update label="July 23, 2026">
  **Added:**

  * **Organization member removal** - Remove a member from your organization in the interface or through the API
  * **Identity lookup from API keys** - A new endpoint returns the identity behind an API key, so you can attribute activity in your own logging and workflows
  * **Agent cost tracking** - Per-model pricing and cost calculation give an early view of agent spend
  * **API reference** - Platform endpoints are documented in the [API reference](/flintai/api-reference/index)

  **Changed:**

  * **Guardrail coverage stays in place** - An organization always keeps at least one active policy, so agents are never left unprotected. See [Policies](/flintai/platform/protection/policies)
  * **Guardrails availability during updates** - Guardrails keep evaluating while the platform updates

  **Fixed:**

  * **Guardrails under concurrent load** - Detectors evaluate reliably when many requests arrive at once
  * **Connected assets on the agent detail page** - Connected assets now display consistently
  * **Gemini requests without a role field** - Improved compatibility for requests that omit a role
  * **Inventory finding severity** - Inventory findings display with their intended informational severity
  * **Organization creation** - Creating an organization produces a single organization, even if the request is retried
  * **Invitations for existing members** - Inviting someone who already belongs to the organization returns a clear conflict response
</Update>

<Update label="July 14, 2026">
  Initial early access release.

  **Added:**

  * **Sign-in and organization setup** - Sign in with GitHub, Google, or email, then create organizations and workspaces, invite teammates, and issue organization-scoped API keys
  * **GitHub-based agent discovery** - Find the agents in your repositories with a GitHub Action. See [Discover your agents](/flintai/platform/getting-started/discover)
  * **Central agent inventory** - See the models, prompts, tools, MCP servers, and sub-agents behind every agent in one place. See [Discovery results](/flintai/platform/discovery/results)
  * **LLM-based scanning** - Scan agent code and MCP servers for issues
  * **Guardrails onboarding through the Flint SDK** - Connect running agents using the Python or TypeScript SDK. See [Monitor and protect your agents](/flintai/platform/getting-started/runtime)
  * **Policy-based guardrails** - Detectors for jailbreaks, toxicity, PII, secrets, PHI, and custom regular expressions, plus tool allow and block lists
  * **Configurable enforcement actions** - Block, redact, or alert when a policy matches. See [Detectors and actions](/flintai/platform/protection/detectors-actions)
</Update>