Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.gambadio/onepassword-agent-mcp

NPM · ONEPASSWORD-AGENT-MCP

Save and use 1Password secrets locally without exposing plaintext to AI agents.

+1 this week 93 Trust /100

Last scanned (7 hours ago)

Scores higher than 96% of npm servers

Category Security

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 34 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to gambadio/onepassword-agent-mcp). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 9 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 1222 tokens (~81/item across 15 items; 15 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage81
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 44% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 31 Oct 26 +1
    • Stability: 0.97 → pass security
  • 29 Oct 26 −1
    • Stability: pass → 0.93 functional
  • 27 Oct 26 +15
    • Malware scan: unverified → pass ▲ security
  • 26 Oct 26 −15
    • Malware scan: pass → unverified ▼ security
    • Package version: 0.4.1 → 0.4.2 functional
  • 23 Oct 26 +1
    • Stability: 0.97 → pass security
  • 22 Oct 26 −1
    • Stability: pass → 0.97 functional
  • 16 Oct 26 +1
    • Stability: 0.97 → pass security
  • 14 Oct 26 +43
    • Injection markers: unverified → pass ▲ security
    • Schema quality: 67 → 81 ▼ functional
    • Tool coverage: unverified → 100 ▲ functional
    • MCP protocol: unverified → pass ▲ functional
    • Stability: unverified → 0.93 ▲ functional
    • Package version: 0.3.8 → 0.4.1 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 5 Nov 2026 · Analysed npm/onepassword-agent-mcp@0.4.2

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo gambadio/onepassword-agent-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/gambadio/onepassword-agent-mcp/.github/workflows/publish.yml@refs/tags/v0.4.2
Rekor log index 3498859189
Predicate type SLSA build provenance https://slsa.dev/provenance/v1
Subject digest sha512:53dd3585648d745243d8d92dfe6c5892dde963e69d4c922f801b95247ac5eee557d159dac6279438515e9ce8f5d3a72c5ccd426709333c0d4c7bf8512

Background: How many MCP packages publish verified provenance →

Dependencies 96 packages
Packages resolved 96
Stale 34
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 15 exposed · ~1,222 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
admin_ui_info ~24

Return the local admin UI URL and state path. Does not return secrets.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

clear_password_clipboard ~22

Clear the OS clipboard after a copy/paste password operation.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

clear_secret_clipboard ~21

Clear the OS clipboard after a copy/paste operation.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

copy_password ~84

Compatibility alias for copy_secret. Resolves an encrypted handle, copies it to the clipboard, and returns no plaintext.

NameTypeReqDescription
clearAfterSecondsinteger––
encryptedPasswordHandlestringyesOpaque handle returned by find_passwords_for_site or find_secrets_for_site.
expectedSitestring–Current website/origin. Required unless local policy allows omission.

No output schema declared.

No examples provided.

copy_secret ~78

Resolve an encrypted secret handle at the last moment, copy the value to the OS clipboard, and return no plaintext.

NameTypeReqDescription
clearAfterSecondsinteger––
encryptedSecretHandlestringyesOpaque handle returned by find_secrets_for_site.
expectedSitestring–Current website/origin. Required unless local policy allows omission.

No output schema declared.

No examples provided.

find_passwords_for_site ~48

Compatibility alias for find_secrets_for_site. Returns approved encrypted handles and never returns plaintext.

NameTypeReqDescription
sitestringyesCurrent website or origin, for example https://github.com/login

No output schema declared.

No examples provided.

find_secrets_for_site ~67

Return approved encrypted handles for a website. Handles can represent passwords, API credentials, credit-card fields, secure notes, or other approved 1Password fields. Plaintext is never returned.

NameTypeReqDescription
sitestringyesCurrent website or origin, for example https://github.com/login

No output schema declared.

No examples provided.

get_profile_data ~79

Return user-defined profile data from the local admin page, such as email, phone, address, name, company, or username. This tool returns plaintext profile values that the user explicitly added for agent use.

NameTypeReqDescription
kindsarray––
sitestring–Current website/origin. If omitted, only all-sites profile fields are returned.

No output schema declared.

No examples provided.

list_approved_passwords ~27

Compatibility alias for list_approved_secrets. Does not return plaintext secret values.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_approved_secrets ~26

List approved encrypted handles and allowed sites. Does not return plaintext secret values.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

onepassword_status ~23

Check local policy and 1Password CLI status. Never returns secrets.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

paste_password ~86

Compatibility alias for paste_secret. Resolves an encrypted handle, pastes it into the active app, and returns no plaintext.

NameTypeReqDescription
clearAfterSecondsinteger––
encryptedPasswordHandlestringyesOpaque handle returned by find_passwords_for_site or find_secrets_for_site.
expectedSitestring–Current website/origin. Required unless local policy allows omission.

No output schema declared.

No examples provided.

paste_secret ~78

Resolve an encrypted secret handle, copy it to the clipboard, paste into the active app, and return no plaintext.

NameTypeReqDescription
clearAfterSecondsinteger––
encryptedSecretHandlestringyesOpaque handle returned by find_secrets_for_site.
expectedSitestring–Current website/origin. Required unless local policy allows omission.

No output schema declared.

No examples provided.

save_secret_from_clipboard ~210

Copy the intended password or text with the browser or operating-system Copy action, then call this tool using metadata only. It captures local clipboard text without returning it, encrypts a retry snapshot for 15 minutes, clears the clipboard if still unchanged, and saves/verifies the value in MCPVAULT. Never read, quote, or pass the secret to this tool. Reuse the same requestId and metadata for retries. Requires clipboard saving and agent creation enabled in the dashboard.

NameTypeReqDescription
allowedSitesarray––
approveFieldstring––
approveForAgentsboolean–Omit to follow dashboard automatic approval; false skips approval for this save.
categorystring––
requestIdstringyesRequired stable ID for this capture. Reuse it on every retry. After expiry, check the existing save before deliberately copying again with a new ID.
titlestringyes–
urlstring––
usernamestring––

No output schema declared.

No examples provided.

save_secret_item ~349

Create a new item in the configured MCPVAULT. Use this when the user asks the agent to save a new password, API credential, secure note, or credit-card entry. If local automatic approval is enabled, all supported fields are approved after verification. Secret values are sent to the local 1Password CLI through stdin, not command arguments.

NameTypeReqDescription
allowedSitesarray–Allowed websites for approvals. Empty means all sites. If omitted, automatic approvals use the saved item's website; explicit single-field approvals allow all sites.
approveFieldstring–Field id, label, or kind for an explicit single-field approval when automatic approval is off, such as password, credential, ccnum, or credit_card_number.
approveForAgentsboolean–Omit to follow local automatic approval settings. False skips approval for this save. True requests the primary field when automatic approval is off; when on, all supported fields are approved.
cardNumberstring––
cardholderNamestring––
categorystring––
credentialstring––
expirystring–Credit-card expiry in 1Password MONTH_YEAR format such as 2028/09.
hostnamestring––
notesstring––
passwordstring––
pinstring––
requestIdstring–Stable ID for this save. Reuse on retries; use a new ID only for an intentional new item. Identical input is deduplicated when omitted.
titlestringyes–
urlstring––
usernamestring––
verificationNumberstring––

No output schema declared.

No examples provided.

Install

How do I install the io.github.gambadio/onepassword-agent-mcp server?

io.github.gambadio/onepassword-agent-mcp runs locally as an npm package, launched with npx -y onepassword-agent-mcp mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · onepassword-agent-mcp

# add to Claude Code
claude mcp add gambadio-onepassword-agent-mcp -- npx -y onepassword-agent-mcp mcp
Common questions

What is the io.github.gambadio/onepassword-agent-mcp server?

io.github.gambadio/onepassword-agent-mcp is listed in the public MCP registry as io.github.gambadio/onepassword-agent-mcp. Save and use 1Password secrets locally without exposing plaintext to AI agents. This page covers its npm package (onepassword-agent-mcp).

Is the io.github.gambadio/onepassword-agent-mcp server safe to use?

io.github.gambadio/onepassword-agent-mcp scores 93 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.gambadio/onepassword-agent-mcp server expose?

io.github.gambadio/onepassword-agent-mcp exposes 15 tools: onepassword_status, find_secrets_for_site, find_passwords_for_site, list_approved_secrets, list_approved_passwords, and 10 more. Their descriptions and schemas cost roughly 1,222 tokens of context every time the server is loaded.

Is the io.github.gambadio/onepassword-agent-mcp server still maintained?

io.github.gambadio/onepassword-agent-mcp is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.gambadio/onepassword-agent-mcp server under?

io.github.gambadio/onepassword-agent-mcp declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the io.github.gambadio/onepassword-agent-mcp server?

VerifyMCP ran 16 checks on io.github.gambadio/onepassword-agent-mcp, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.