What data does Chron log?
Every exchange records the user message’s received timestamp and the assistant response’s sent timestamp, along with full content and session metadata.
@SirinivasK
Basic information
AI tools show when you sent a message. Chron logs when the AI responded too — and keeps a permanent, queryable record of every exchange across every tool you use. Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible AI tool. Every exchange is stored wi
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"chron": {
"command": "npx",
"args": [
"-y",
"chron-mcp"
]
}
}
}Initialize or resume an audit session. Returns session_id, message_count, first_message_at, and recent messages in a single call — use this instead of calling start_session + get_session_history separately.
Create a new audit session or resume an existing one by title. Call this at the start of every conversation.
Record a single message (user or assistant) with the current local datetime and timezone offset. Call before responding for user messages, and before sending for assistant messages.
Record an AI tool invocation as a first-class audit event (event_type=tool_call). Call immediately before executing a tool. Returns tool_call_id to pass to log_tool_result.
Record the result of a tool call as a first-class audit event (event_type=tool_result). Call immediately after receiving tool output. Links back to log_tool_call via tool_call_id.
Record a file edit as a first-class audit event (event_type=code_change). Call after every Edit or Write tool call with the unified diff. Diff content is included in the hash chain.
Record a user+assistant exchange from historical or batch imports only. Do NOT use for live conversations — both timestamps are captured at the same instant with no real gap. For live sessions always call log_message twice: once for the user message, once for the assistant response.
List all audit sessions ordered by most recently active. Returns id, title, ai_tool, message_count, created_at, updated_at.
Retrieve the full timestamped audit log for a session, oldest first.
Verify the tamper-evident hash chain for a session. Returns valid=true if no rows were edited after logging, or the first broken link if tampering is detected.
Scan a prompt for secrets and sensitive data before sending to any AI. Returns detected secrets, a redacted version with tokens, and a token_map to restore the real values after the AI responds.
Permanently delete a session and all its messages. Cascades to secrets_detected. Returns deleted=true or deleted=false if not found.
Full-text search across all logged AI conversations. Returns matching sessions with excerpts. Uses SQLite FTS5 with porter stemming — supports phrases ("exact match"), boolean (term1 OR term2), and prefix (migrat*).
Return a structured summary of a session: timeline with latencies, mutations detected, secrets touched, and possible prod-account references. Useful for compliance review and change-control evidence.
Restore real secret values into an AI response that contains $CHRON_* tokens. Pass the token_map returned by scan_prompt.
Chron is an MCP server that provides a timestamped audit trail for every AI conversation. It logs each exchange with precise local datetime (including timezone offset) to a local SQLite file you own. Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible AI tool.
Add the server to your AI tool’s MCP configuration by setting command to npx and args to ["-y", "chron-mcp"]. First run automatically creates ~/.chron/chron.db. For Claude Code, additionally install the companion skill hook to enable automatic session logging. Run as HTTP+SSE for team/self-hosted use by setting CHRON_TRANSPORT=http.
Every exchange records the user message’s received timestamp and the assistant response’s sent timestamp, along with full content and session metadata.
Your audit log lives in a single SQLite file at `~/.chron/chron.db` (configurable via `CHRON_DB_PATH`). No data leaves your machine; no cloud or telemetry.
Each message is linked to the previous one via a SHA-256 chain. The `verify_session` tool walks the chain and reports whether any message has been modified post-logging and the exact row of the first break.
Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible AI tool. Installation instructions are provided for each.
No. In stdio mode (default) no API key is required. An API key is optional and only needed when using HTTP+SSE mode.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools


Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
Comments