1Password MCP server
Commit Oct 15, 2026Exposes 1Password vaults and items to AI agents with opaque-by-default secret handling and explicit plaintext reveal requests.
Also known as kefapps/onepassword-mcp-codex, mcp-1password
- Stars
- 1
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Oct 15, 2026
- License
- —
What is 1Password MCP?
1Password exposes 1Password vaults and items to AI agents with opaque-by-default secret handling and explicit plaintext reveal requests.
Summary generated from the project's README
About 1Password MCP server
Connecting AI agents to your 1Password vaults while maintaining strict security is what this MCP server enables. It provides a way for models to search and read items, vaults, and environments, but it uses an opaque-by-default approach where secrets are redacted unless you explicitly request a plaintext reveal. This ensures that sensitive data is never exposed to the AI without a per-call acknowledgement from the user.
Developers can choose between several authentication modes including desktop integration via the 1Password beta channel, 1Password Connect for local or remote setups, or service accounts for headless CI environments. The server supports stdio for local use or an HTTP transport protected by a bearer token for remote agents. It also includes a script runner that allows agents to execute pre-approved shell commands with 1Password-backed environment values injected directly into the process.
For those needing more control, the server offers optional capabilities for writing, deleting, or archiving items, as well as managing vault permissions. Every sensitive action is recorded in a JSONL audit log located at ~/.onepassword-mcp/audit.jsonl to maintain a clear history of agent activity.
What you can do with it
- 1Securely reveal specific secretsAsk an AI agent to retrieve a specific plaintext password from a vault only after providing an explicit reason and acknowledgement.
- 2Execute scripts with injected credentialsHave an AI agent run a pre-approved shell script that automatically uses secrets from 1Password as environment variables.
- 3Manage vault permissions and itemsInstruct an AI to update existing items or modify group permissions on specific vaults when write capabilities are enabled.
- 4Audit sensitive agent actionsMonitor all sensitive operations performed by the AI agent by reviewing the local JSONL audit log.
Written from the project's README. Every use case is checked against a quote from it.
How to install 1Password MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall 1Password MCP in Claude Code
$ claude mcp add onepassword-mcp-codex -- npx -y mcp-1passwordInstall 1Password MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"onepassword-mcp-codex": {
"command": "npx",
"args": [
"-y",
"mcp-1password"
]
}
}
}Install 1Password MCP in VS Code
.vscode/mcp.json
{
"servers": {
"onepassword-mcp-codex": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"mcp-1password"
]
}
}
}Install 1Password MCP in VS Code CLI
$ code --add-mcp '{"name":"onepassword-mcp-codex","type":"stdio","command":"npx","args":["-y","mcp-1password"]}'Install 1Password MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"onepassword-mcp-codex": {
"command": "npx",
"args": [
"-y",
"mcp-1password"
]
}
}
}Install 1Password MCP in Codex
$ codex mcp add onepassword-mcp-codex -- npx -y mcp-1passwordInstall 1Password MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.onepassword-mcp-codex] command = "npx" args = ["-y", "mcp-1password"]
Install 1Password MCP in Gemini CLI
$ gemini mcp add -s user onepassword-mcp-codex npx -- -y mcp-1passwordInstall 1Password MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"onepassword-mcp-codex": {
"command": "npx",
"args": [
"-y",
"mcp-1password"
]
}
}
}Configuration
OP_CONNECT_TOKENOP_MCP_HTTP_BEARER_TOKENOP_SERVICE_ACCOUNT_TOKEN
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablekefapps/onepassword-mcp-codex is public and reachablegithub.com/kefapps/onepassword-mcp-codex ↗Pass
- Package names this repository as its sourcemcp-1password names kefapps/onepassword-mcp-codex as sourcenpmjs.com/package/mcp-1password ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-10-15github.com/kefapps/onepassword-mcp-codex ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from mcp-1passwordPass
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubmcp-1password
Status: Public Beta
This package is under active development (v0.x). The API and CLI flags may change between minor versions. The underlying
@1password/sdkdependency is also a beta release. Pin an exact version (mcp-1password@x.y.z) in production-like environments.
A Model Context Protocol server that exposes 1Password to AI agents with opaque-by-default secret handling. Secrets are never revealed unless you explicitly opt in.
Features
- Read and search vaults, items, and environments with secrets redacted by default.
- Create tracked item requests, then update, archive, and delete items and vaults when write/destructive capabilities are enabled.
- Manage group permissions on vaults when permission mutation is enabled.
- Reveal plaintext secrets only on explicit request with a per-call acknowledgement.
- Generate plaintext passwords only with a reason and explicit acknowledgement.
- Run pre-approved scripts with injected 1Password-backed environment values.
- Optionally run unrestricted local shell commands under explicitly approved workspace roots, after local browser confirmation.
- Use stdio by default, or a local/single-user HTTP transport protected by a bearer token.
- Write a JSONL audit log for sensitive actions at
~/.onepassword-mcp/audit.jsonl.
Requirements
- Node.js >= 20.10
- 1Password desktop app for
--auth-mode=desktop; this requires the 1Password beta channel with SDK integration enabled. - 1Password Connect for
--auth-mode=connect; the POC only accepts a localhost Connect host. - 1Password CLI (
op) only when scripts need CLI authentication or you configure script runner CLI auth; Connect-backedenvSecretRefsdo not requireop.
Enable Desktop Integration
Desktop auth requires the 1Password beta channel and SDK integration:
- In 1Password, switch to the beta channel: Settings -> Updates -> Beta channel.
- Enable SDK integration: Settings -> Developer -> Connect with 1Password SDKs.
Installation
# Public beta install
npm install -g mcp-1password@beta
# Connect-only binary after global install
OP_CONNECT_TOKEN="<connect-token>" \
mcp-1password-connect --connect-host=http://127.0.0.1:8090
# Run on demand without a global install
npx -y mcp-1password@beta --auth-mode=desktop --account="My Account"
During beta, prefer mcp-1password@beta or an exact version instead of relying on the default npm tag.
Quick Start
Connect-Only Binary
Use mcp-1password-connect when you want a path where Connect is the only possible 1Password backend. This binary forces --auth-mode=connect, rejects Desktop/service-account auth, rejects non-Connect op CLI auth modes, and never instantiates the Desktop SDK service.
# From the project root, create/update the trust file and manifest first.
mcp-1password-connect trust-workspace
OP_CONNECT_TOKEN="<connect-token>" \
mcp-1password-connect \
--connect-host=http://127.0.0.1:8090 \
--enable-script-runner=true \
--script-runner-allowlist-manifest="$HOME/.onepassword-mcp/workspace-trust.json"
For each new project that should be trusted for Connect workspace commands:
mcp-1password-connect trust-workspace
Then call workspace_trust_reload in the running MCP session.
Claude Desktop (stdio Transport)
Edit ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"1password": {
"command": "npx",
"args": [
"-y", "mcp-1password@beta",
"--auth-mode=desktop",
"--account=1Password account name or UUID"
]
}
}
}
Service Account (CI / Headless)
{
"mcpServers": {
"1password": {
"command": "npx",
"args": ["-y", "mcp-1password@beta", "--auth-mode=service-account"],
"env": {
"OP_SERVICE_ACCOUNT_TOKEN": "<service-account-token>"
}
}
}
}
Local 1Password Connect POC
Run the local Connect containers from docker-compose.connect.example.yml, then start the MCP without Desktop auth:
OP_CONNECT_TOKEN="<connect-token>" \
mcp-1password \
--auth-mode=connect \
--connect-host=http://127.0.0.1:8090
Connect mode supports vault/item reads, tracked placeholder creation through item_request_create, managed-item review through item_request_list, item update/delete, password_update, password_read, and secret_reveal. It does not expose generic password_create or item_create, vault mutation, group permissions, 1Password Environments, files, or item archive. See docs/connect-local-poc.md.
HTTP Transport (Remote Agents)
OP_MCP_HTTP_BEARER_TOKEN="$(openssl rand -base64 32)" \
mcp-1password \
--auth-mode=desktop \
--account="My Account" \
--transport=http
HTTP security: The HTTP transport is designed for local/single-user use. The bearer token must be at least 16 characters, and
--http-require-bearer=falseis only allowed on localhost. If you bind the server to any interface other than127.0.0.1, put it behind a reverse proxy with TLS termination (nginx, Caddy, Traefik). For multi-user or public deployments, add a real upstream authorization layer such as OIDC/OAuth with client identity, scopes, and expiry.
Configuration Reference
Every flag can also be set through an environment variable.
| Flag | Environment variable | Default | Description |
|---|---|---|---|
--auth-mode |
OP_MCP_AUTH_MODE |
desktop |
desktop, service-account, or connect |
--account |
OP_MCP_ACCOUNT |
- | Account name or UUID, required in desktop mode |
--service-account-token |
OP_SERVICE_ACCOUNT_TOKEN |
- | Token, required in service-account mode |
--connect-host |
OP_CONNECT_HOST |
http://127.0.0.1:8090 |
Localhost Connect API URL, required to stay on localhost for this POC |
--connect-token |
OP_CONNECT_TOKEN |
- | Connect access token, required in connect mode |
--connect-timeout-ms |
OP_MCP_CONNECT_TIMEOUT_MS |
30000 |
Connect request timeout |
--enable-secret-reveal |
OP_MCP_ENABLE_SECRET_REVEAL |
false |
Allow plaintext secret reveal |
--enable-writes |
OP_MCP_ENABLE_WRITES |
false |
Allow tracked item requests plus item/vault updates and vault creation |
--enable-destructive-actions |
OP_MCP_ENABLE_DESTRUCTIVE_ACTIONS |
false |
Allow archive and delete operations |
--enable-permission-mutation |
OP_MCP_ENABLE_PERMISSION_MUTATION |
false |
Allow vault permission changes |
--enable-script-runner |
OP_MCP_ENABLE_SCRIPT_RUNNER |
false |
Allow execution of allowlisted scripts |
--enable-unrestricted-script-runner |
OP_MCP_ENABLE_UNRESTRICTED_SCRIPT_RUNNER |
false |
Enable op_script_run free-form shell commands with 1Password injection after one local approval per MCP process in Desktop/service-account mode; allowlists are ignored |
--script-runner-allowlist |
OP_MCP_SCRIPT_RUNNER_ALLOWLISTS |
- | Absolute path to an allowlist file; repeatable |
--script-runner-allowlist-manifest |
OP_MCP_SCRIPT_RUNNER_ALLOWLIST_MANIFESTS |
- | Absolute path to a manifest listing allowlist files; repeatable |
--script-runner-root |
OP_MCP_SCRIPT_RUNNER_ROOTS |
- | Trusted workspace root; repeatable |
--enable-unrestricted-runner |
OP_MCP_ENABLE_UNRESTRICTED_RUNNER |
false |
Allow the separate free-form shell command runner |
--unrestricted-runner-root |
OP_MCP_UNRESTRICTED_RUNNER_ROOTS |
- | Root path eligible for unrestricted execution approval; repeatable |
--unrestricted-runner-require-session-approval |
OP_MCP_UNRESTRICTED_RUNNER_REQUIRE_SESSION_APPROVAL |
true |
Require local approval page before commands can run |
--unrestricted-runner-approval-host |
OP_MCP_UNRESTRICTED_RUNNER_APPROVAL_HOST |
127.0.0.1 |
Local approval server bind host; localhost only |
--unrestricted-runner-approval-port |
OP_MCP_UNRESTRICTED_RUNNER_APPROVAL_PORT |
0 |
Local approval server port; 0 picks a free port |
--unrestricted-runner-approval-ttl-ms |
OP_MCP_UNRESTRICTED_RUNNER_APPROVAL_TTL_MS |
43200000 |
In-memory approval lifetime |
--unrestricted-runner-command-timeout-ms |
OP_MCP_UNRESTRICTED_RUNNER_COMMAND_TIMEOUT_MS |
600000 |
Free-form command timeout |
--approval-remember-store-path |
OP_MCP_APPROVAL_REMEMBER_STORE_PATH |
~/.onepassword-mcp/approval-grants.enc.json |
Encrypted local approval grants file for the approval page's 24h remember checkbox |
--approval-remember-key-path |
OP_MCP_APPROVAL_REMEMBER_KEY_PATH |
~/.onepassword-mcp/approval-grants.key |
Local 32-byte AES key file used to encrypt remembered approval grants |
--approval-remember-ttl-ms |
OP_MCP_APPROVAL_REMEMBER_TTL_MS |
86400000 |
Lifetime for approvals remembered across MCP sessions |
--acknowledge-unrestricted-runner |
OP_MCP_ACKNOWLEDGE_UNRESTRICTED_RUNNER |
- | Required only when disabling session approval; exact value: I_UNDERSTAND_THIS_ALLOWS_UNRESTRICTED_LOCAL_COMMAND_EXECUTION |
--op-cli-path |
OP_MCP_OP_CLI_PATH |
op |
Path to the op binary; must be absolute when the script runner uses op CLI auth |
--op-cli-auth-mode |
OP_MCP_OP_CLI_AUTH_MODE |
auto |
auto, desktop, manual-session, or service-account; auto uses Connect when --auth-mode=connect |
--transport |
OP_MCP_TRANSPORT |
stdio |
stdio or http |
--http-host |
OP_MCP_HTTP_HOST |
127.0.0.1 |
HTTP bind address |
--http-port |
OP_MCP_HTTP_PORT |
17337 |
HTTP port |
--http-path |
OP_MCP_HTTP_PATH |
/mcp |
HTTP path prefix |
--http-require-bearer |
OP_MCP_HTTP_REQUIRE_BEARER |
true when HTTP is enabled |
Require Authorization: Bearer |
| - | OP_MCP_HTTP_BEARER_TOKEN |
- | Bearer token required by default with --transport=http; minimum 16 characters |
--http-allowed-origin |
OP_MCP_HTTP_ALLOWED_ORIGINS |
Localhost origins for the current port | Browser origins allowed for HTTP transport; strict Origin validation, repeatable flag, comma-separated env |
--http-max-sessions |
OP_MCP_HTTP_MAX_SESSIONS |
64 |
Maximum active HTTP MCP sessions |
--http-session-idle-ms |
OP_MCP_HTTP_SESSION_IDLE_MS |
900000 |
Idle HTTP session expiry |
--http-request-timeout-ms |
OP_MCP_HTTP_REQUEST_TIMEOUT_MS |
30000 |
HTTP request timeout |
--audit-log-path |
OP_MCP_AUDIT_LOG_PATH |
~/.onepassword-mcp/audit.jsonl |
Audit log path |
--log-level |
OP_MCP_LOG_LEVEL |
info |
debug, info, warn, or error |
Script Runner
The script runner lets agents invoke pre-approved shell commands with 1Password-backed environment injection. In --auth-mode=connect, the MCP exposes workspace_trust_list, workspace_command_run, and workspace_trust_reload; envSecretRefs are resolved through Connect and injected directly into the child process without the op binary, OP_SESSION, or Desktop SDK auth. With Desktop or service-account auth, the MCP exposes the older op_script_list, op_script_run, and op_script_reload_allowlists tools, and the runner can also inject CLI authentication for commands that call op. By default, only startup-configured commandId entries can run. In Connect mode, workspace_trust_list resolves the requested workspaceRoot against startup-configured workspace trust entries and returns workspaceCommandResolution; when that resolution reports freeformCommands: true, workspace_command_run may accept a free-form command rooted in that workspace or its subdirectories. The startup command catalog and workspace trust files can be reloaded on demand with the reload tool.
For a new Connect-mode project, run this from the project root:
mcp-1password trust-workspace
This creates or updates .onepassword-mcp.json in the project, enables workspace commands for that project, and adds the file to ~/.onepassword-mcp/workspace-trust.json. Start the MCP with that manifest configured once:
mcp-1password \
--auth-mode=connect \
--enable-script-runner=true \
--script-runner-allowlist-manifest="$HOME/.onepassword-mcp/workspace-trust.json"
If the MCP is already running with that manifest, call workspace_trust_reload after trusting a new project.
For local single-user sessions where preapproving every command is too expensive, start the server with:
mcp-1password \
--auth-mode=desktop \
--account="My Account" \
--enable-unrestricted-script-runner=true \
--op-cli-path=/absolute/path/to/op
With --enable-unrestricted-script-runner=true, op_script_run ignores --script-runner-root, --script-runner-allowlist, and --script-runner-allowlist-manifest. The first free-form op_script_run call returns an approvalUrl; open it locally, tick the checkbox, and type:
I_UNDERSTAND_THIS_ALLOWS_UNRESTRICTED_LOCAL_COMMAND_EXECUTION
By default, that approval is in memory only and applies once per MCP server process. If you tick Remember this approval for 24 hours on this machine, the server writes an encrypted local grant containing only the approval scope and expiration timestamp. After approval, op_script_run accepts command instead of commandId, runs it through a non-login /bin/sh -c shell in the requested workspace, and still supports envSecretRefs so secrets are injected into the child process without being returned to the model. When the remembered grant expires, the approval page is required again.
Command Catalog And Workspace Trust Format
Create a .onepassword-mcp.json file at the root of your project:
{
"version": 1,
"workspaceRoot": ".",
"allowWorkspaceCommands": false,
"commands": {
"deploy-staging": {
"description": "Deploy to staging",
"command": "/usr/local/bin/deploy.sh",
"args": ["--env", "staging"],
"cwd": ".",
"timeoutMs": 120000,
"sensitiveOutput": false
}
}
}
commandmust be an absolute path to an executable.- The directory containing
commandis not automatically prepended toPATH. Use absolute paths in scripts, or configure--op-cli-pathso the directory containingopcan be injected. - In
--auth-mode=connect,allowWorkspaceCommands: truemarks the matchingworkspaceRoot,workspaceRoots, orworkspaceRootPrefixesas a trusted workspace command scope.workspace_trust_listexposes the decision asworkspaceCommandResolution.freeformCommands; when it istrue,workspace_command_runaccepts a free-formcommandfor that resolved workspace or its subdirectories. Secrets passed withenvSecretRefsare resolved through Connect only, injected only into the child process, and are not returned to the model. This is an explicit trust decision for local worktrees you control. sensitiveOutput: truewithholds stdout/stderr from the agent unlessreturnOutput=trueis explicitly requested with reveal acknowledgement.workspace_command_runin Connect mode andop_script_runin Desktop/service-account mode accept an optionalenvSecretRefsobject that maps environment variable names toop://references. The server resolves those references, injects only the values into the child process environment, and never returns or audits the plaintext values.returnOutput=truedoes not require startup secret reveal for ordinary output. WhenenvSecretRefsis provided or the command hassensitiveOutput: true, stdout/stderr/error messages are returned only withacknowledgePlaintext: "I_UNDERSTAND_THIS_RETURNS_SECRET_PLAINTEXT"; without that acknowledgement, execution is skipped withexecutionSkipped: trueandoutputState: "skipped_ack_missing". Returned stdout/stderr/error messages are redacted by exact secret value.- After editing a startup-configured command catalog or workspace trust file, call
workspace_trust_reloadin Connect mode orop_script_reload_allowlistsin Desktop/service-account mode with a reason. If the edited file is invalid, the reload fails and the previous in-memory configuration remains active.
Startup Manifest Format
Use --script-runner-allowlist-manifest=/absolute/path/to/workspace-trust.json when you want to add or remove workspace trust or command catalog files without restarting the MCP process. Manifest entries may be absolute paths or paths relative to the manifest file:
{
"version": 1,
"allowlists": [
"/absolute/path/to/project-a/.onepassword-mcp.json",
"../project-b/.onepassword-mcp.json"
]
}
After editing the manifest, call workspace_trust_reload in Connect mode or op_script_reload_allowlists in Desktop/service-account mode with a reason. Any new workspace roots are still checked against startup-configured --script-runner-root values when roots are provided.
Agent Routing Guidance
When an agent needs a secret only to run a local command, it should not call password_read with reveal=true or secret_reveal first. Prefer this flow:
- In Connect mode, call
workspace_trust_listfor the current workspace; in Desktop/service-account mode, callop_script_list. - In Connect mode, inspect
workspaceCommandResolution: iffreeformCommands=true, callworkspace_command_runwithcommand; otherwise pick a listedcommandIdthat performs the operation. - Call
workspace_command_runin Connect mode orop_script_runin Desktop/service-account mode withenvSecretRefs, mapping environment variable names toop://references. - Leave
returnOutput=falseunless command output is required.
This keeps the plaintext secret out of the model transcript while still letting the command receive it.
Tracked Secret Requests
When an agent needs a new credential to exist in 1Password, prefer item_request_create over asking the user to paste the value. The tool creates a managed item with:
- credential fields initialized to the
__FILL_ME__placeholder; - provenance fields for
project,justification, and optional Linear ticket details; - managed tags such as
mcp-managed,awaiting-fill, andproject:<slug>; op://references that the agent can wire into configs or scripts.
The user fills the returned references in 1Password. Later, item_request_list reports which managed items are still awaiting fill, without returning the credential values.
Unrestricted Runner
The unrestricted runner is a separate, dangerous escape hatch for trusted local worktrees where allowlisting every command is too expensive. Enable it only for roots you are willing to approve for arbitrary command execution:
mcp-1password \
--auth-mode=desktop \
--account="My Account" \
--enable-unrestricted-runner=true \
--unrestricted-runner-root=/absolute/path/to/trusted/worktree
When an MCP client first calls op_unrestricted_run for a configured root, the tool returns authorizationRequired: true and a local approvalUrl. Open that URL on the same machine, tick the risk checkbox, and type:
I_UNDERSTAND_THIS_ALLOWS_UNRESTRICTED_LOCAL_COMMAND_EXECUTION
That approval is in memory only and expires after --unrestricted-runner-approval-ttl-ms. It is not written to config. The configured root is an approval scope, not an operating-system sandbox: approved commands run with your normal OS permissions and can still cd, read, write, or execute outside that path if the OS allows it.
op_unrestricted_run starts the command in the requested workspace root through /bin/sh -c on Unix-like systems, with a minimal inherited environment and no 1Password secret injection. The shell is intentionally non-login so local profile hooks such as RVM do not run before the requested command. Use op_script_run when a command needs 1Password values injected safely. As with script output, returnOutput=true without acknowledgePlaintext: "I_UNDERSTAND_THIS_RETURNS_SECRET_PLAINTEXT" skips execution and returns the required acknowledgement.
You can disable the browser approval page only with an explicit startup acknowledgement:
mcp-1password \
--auth-mode=desktop \
--account="My Account" \
--enable-unrestricted-runner=true \
--unrestricted-runner-root=/absolute/path/to/trusted/worktree \
--unrestricted-runner-require-session-approval=false \
--acknowledge-unrestricted-runner=I_UNDERSTAND_THIS_ALLOWS_UNRESTRICTED_LOCAL_COMMAND_EXECUTION
1Password MCP questions
How do I add 1Password MCP to Claude Code?
Run claude mcp add onepassword-mcp-codex -- npx -y mcp-1password in your terminal. Add --scope user to make it available in every project.
How do I add 1Password MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How are secrets handled by default?
Secrets are redacted by default and are never revealed unless you explicitly opt in via an explicit request with a per-call acknowledgement.
What are the requirements for desktop integration?
Desktop integration requires the 1Password beta channel with SDK integration enabled.
Can I run scripts with 1Password secrets?
Yes, the script runner allows agents to invoke pre-approved shell commands with 1Password-backed environment injection.
Where are sensitive actions logged?
Sensitive actions are recorded in a JSONL audit log located at ~/.onepassword-mcp/audit.jsonl.