mcp-1password (kefapps/onepassword-mcp-codex) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: there is no public source to read and no endpoint we can reach, so there is nothing for us to inspect. No publisher has claimed this listing.

Back to MCP Trust Indexm8ven
C
Emerging
74/100
2 months ago

mcp-1password

An MCP server that integrates 1Password with AI agents, providing secure access to vaults and items with secrets redacted by default.

→ kefapps/onepassword-mcp-codex· listed on glama

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

kefapps

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 6 credentials: OP_CONNECT_TOKEN, OP_MCP_HTTP_BEARER_TOKEN, OP_MCP_HTTP_REQUIRE_BEARER, OP_MCP_SERVICE_ACCOUNT_TOKEN, OP_MCP_TEST_SECRET, OP_SERVICE_ACCOUNT_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configComSpec
configOP_CONNECT_HOSTconnect-host http://127.0.0.1:8080 Localhost Connect API URL, required to stay on localhost for this POC
🔐 secretOP_CONNECT_TOKEN"<connect-token>" \
configOP_MCP_ACCOUNTaccount - Account name or UUID, required in desktop mode
configOP_MCP_ACKNOWLEDGE_UNRESTRICTED_RUNNERacknowledge-unrestricted-runner - Required only when disabling session approval; exact value: I_UNDERSTAND_THIS_ALLOWS_UNRESTRICTED_LOCAL_COMMAND_EXECUTION
configOP_MCP_APPROVAL_REMEMBER_KEY_PATHapproval-remember-key-path ~/.onepassword-mcp/approval-grants.key Local 32-byte AES key file used to encrypt remembered approval grants
configOP_MCP_APPROVAL_REMEMBER_STORE_PATHapproval-remember-store-path ~/.onepassword-mcp/approval-grants.enc.json Encrypted local approval grants file for the approval page's 24h remember checkbox
configOP_MCP_APPROVAL_REMEMBER_TTL_MSapproval-remember-ttl-ms 86400000 Lifetime for approvals remembered across MCP sessions
configOP_MCP_AUDIT_LOG_PATHaudit-log-path ~/.onepassword-mcp/audit.jsonl Audit log path
configOP_MCP_AUTH_MODEauth-mode desktop desktop, service-account, or connect
configOP_MCP_CONNECT_TIMEOUT_MSconnect-timeout-ms 30000 Connect request timeout
configOP_MCP_DIAGNOSTICS
configOP_MCP_ENABLE_DESTRUCTIVE_ACTIONSenable-destructive-actions false Allow archive and delete operations
configOP_MCP_ENABLE_PERMISSION_MUTATIONenable-permission-mutation false Allow vault permission changes
configOP_MCP_ENABLE_SCRIPT_RUNNERenable-script-runner false Allow execution of allowlisted scripts
configOP_MCP_ENABLE_SECRET_REVEALenable-secret-reveal false Allow plaintext secret reveal
configOP_MCP_ENABLE_UNRESTRICTED_RUNNERenable-unrestricted-runner false Allow the separate free-form shell command runner
configOP_MCP_ENABLE_UNRESTRICTED_SCRIPT_RUNNERenable-unrestricted-script-runner false Enable op_script_run free-form shell commands with 1Password injection after one local approval per MCP process; allowlists are ignored
configOP_MCP_ENABLE_WRITESenable-writes false Allow item and vault creation/update
configOP_MCP_HTTP_ALLOWED_ORIGINShttp-allowed-origin Localhost origins for the current port Browser origins allowed for HTTP transport; strict Origin validation, repeatable flag, comma-separated env
🔐 secretOP_MCP_HTTP_BEARER_TOKEN"$(openssl rand -base64 32)" \
configOP_MCP_HTTP_HOSThttp-host 127.0.0.1 HTTP bind address
configOP_MCP_HTTP_MAX_SESSIONShttp-max-sessions 64 Maximum active HTTP MCP sessions
configOP_MCP_HTTP_PATHhttp-path /mcp HTTP path prefix
configOP_MCP_HTTP_PORThttp-port 17337 HTTP port
configOP_MCP_HTTP_REQUEST_TIMEOUT_MShttp-request-timeout-ms 30000 HTTP request timeout
🔐 secretOP_MCP_HTTP_REQUIRE_BEARERhttp-require-bearer true when HTTP is enabled Require Authorization: Bearer
configOP_MCP_HTTP_SESSION_IDLE_MShttp-session-idle-ms 900000 Idle HTTP session expiry
configOP_MCP_LOG_LEVELlog-level info debug, info, warn, or error
configOP_MCP_OP_CLI_AUTH_MODEop-cli-auth-mode auto auto, desktop, manual-session, or service-account
configOP_MCP_OP_CLI_PATHop-cli-path op Path to the op binary; must be absolute when the script runner is enabled
configOP_MCP_SCRIPT_RUNNER_ALLOWLISTSscript-runner-allowlist - Absolute path to an allowlist file; repeatable
configOP_MCP_SCRIPT_RUNNER_ALLOWLIST_MANIFESTSscript-runner-allowlist-manifest - Absolute path to a manifest listing allowlist files; repeatable
configOP_MCP_SCRIPT_RUNNER_ROOTSscript-runner-root - Trusted workspace root; repeatable
🔐 secretOP_MCP_SERVICE_ACCOUNT_TOKEN
configOP_MCP_SMOKE_AUDIT_LOG_PATH
🔐 secretOP_MCP_TEST_SECRET
configOP_MCP_TRANSPORTtransport stdio stdio or http
configOP_MCP_UNRESTRICTED_RUNNER_APPROVAL_HOSTunrestricted-runner-approval-host 127.0.0.1 Local approval server bind host; localhost only
configOP_MCP_UNRESTRICTED_RUNNER_APPROVAL_PORTunrestricted-runner-approval-port 0 Local approval server port; 0 picks a free port
configOP_MCP_UNRESTRICTED_RUNNER_APPROVAL_TTL_MSunrestricted-runner-approval-ttl-ms 43200000 In-memory approval lifetime
configOP_MCP_UNRESTRICTED_RUNNER_COMMAND_TIMEOUT_MSunrestricted-runner-command-timeout-ms 600000 Free-form command timeout
configOP_MCP_UNRESTRICTED_RUNNER_REQUIRE_SESSION_APPROVALunrestricted-runner-require-session-approval true Require local approval page before commands can run
configOP_MCP_UNRESTRICTED_RUNNER_ROOTSunrestricted-runner-root - Root path eligible for unrestricted execution approval; repeatable
🔐 secretOP_SERVICE_ACCOUNT_TOKEN"": "<service-account-token>"
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

32/32 tools missing one or more hints — sdk_capabilities (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); op_session_status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); op_script_list (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +29 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tool inputs are validated

27/32 tool handlers declare input schemas (84%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

21/32 tool handlers wrap calls in try/catch (66%)

Wrap each tool handler body in try/catch and return a structured error response.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/kefapps-onepassword-mcp-codex-0tk1uf)](https://m8ven.ai/mcp/kefapps-onepassword-mcp-codex-0tk1uf)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: f5912ef27b608f47562592e65800171523c4bfba
code hash: f3d209fcc230ad5aa4e01334f9457a3f400f8329ac40d8810e60ec704808428b
verified: 6/15/2026, 1:48:22 PM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client