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.

Vault MCP

NPM · CHILLAI-VAULT-MCP

MCP server for credential isolation — bots use passwords and API keys without seeing them

Available components

0 this week 72 Trust /100

Last scanned (15 hours ago)

Scores higher than 44% 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 Security81
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 33 of 131 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency13
  • Repository check failed: the declared repository URL redirects; it must resolve directly. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Maintenance check failed: the publisher has marked this version as deprecated on the registry, telling users to stop installing it. See how to fix → Fail
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability79
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 670 tokens (~67/item across 10 items; 10 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 Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "vault_remove" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 10 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 (15)

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

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.

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.

  • 21 Nov 26 0
    • Security disclosure: fail → unverified ▼ functional
  • 19 Nov 26 +1
    • Stability: 0.97 → pass security
    • Security disclosure: unverified → fail ▼ functional
  • 18 Nov 26 −1
    • Stability: pass → 0.97 functional
  • 12 Nov 26 +1
    • Stability: 0.97 → pass security
  • 11 Nov 26 0
    • Security disclosure: fail → unverified ▼ functional
  • 10 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 0
    • Security disclosure: unverified → fail ▼ functional
  • 8 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

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 21 Nov 2026 · Analysed npm/chillai-vault-mcp@0.2.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 131 packages
Packages resolved 131
Stale 33
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 10 exposed · ~670 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
vault_add ~121

Securely add a new credential to the vault. Opens a browser form where the user enters their password directly — the password NEVER passes through the AI agent. Supports templates for popular services (github, jira, stripe, etc.).

NameTypeReqDescription
service_typestring–Type of credential (default: web_login, or from template)
session_scopedboolean–If true, credential auto-deletes when MCP session ends
site_idstring–Pre-fill the site identifier (e.g. "github"). If a template exists, selectors auto-fill.

No output schema declared.

No examples provided.

vault_api_request ~140

Make an API request with stored credentials. The API key is injected automatically — the bot never sees it. Supports header, query param, and basic auth patterns.

NameTypeReqDescription
auth_typestring–Auth pattern: "header" (default), "query" (append key as URL param), "basic" (HTTP Basic Auth)
bodystring–Request body (JSON string)
headersobject–Additional headers
methodstring–HTTP method (default: GET)
servicestringyesThe service identifier (e.g. "openai", "stripe")
urlstringyesThe API endpoint URL

No output schema declared.

No examples provided.

vault_check ~43

Verify a credential is valid and ready to use. Checks existence, active status, required fields, and expiration.

NameTypeReqDescription
site_idstringyesThe site identifier to check

No output schema declared.

No examples provided.

vault_import ~101

Import API keys from a .env file. Each key is stored as an encrypted api_key credential. The .env values pass through memory only — never returned to the agent.

NameTypeReqDescription
file_pathstringyesPath to the .env file
mappingobject–Map .env variable names to site IDs, e.g. {"STRIPE_KEY": "stripe", "OPENAI_KEY": "openai"}. If omitted, all variables are imported.

No output schema declared.

No examples provided.

vault_list ~26

List all available credentials in the vault. Returns only site IDs and types — no secrets.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

vault_login ~100

Log into a website using stored credentials. The bot never sees the password — Vault fills the login form via Chrome DevTools Protocol. Supports TOTP 2FA if configured.

NameTypeReqDescription
site_idstringyesThe site identifier (e.g. "github", "jira")
timeout_msnumber–Login timeout in milliseconds (default: 15000)
totp_selectorstring–CSS selector for TOTP/2FA input field

No output schema declared.

No examples provided.

vault_remove ~29

Remove a credential from the vault permanently.

NameTypeReqDescription
site_idstringyesThe site identifier to remove

No output schema declared.

No examples provided.

vault_status ~39

Check the status of a specific credential: active/inactive, last used, audit count.

NameTypeReqDescription
site_idstringyesThe site identifier to check

No output schema declared.

No examples provided.

vault_templates ~25

List available credential templates for popular services. Templates auto-fill login URLs and CSS selectors.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

vault_update ~46

Update an existing credential. Opens a browser form to enter new password/API key — the secret NEVER passes through the AI agent.

NameTypeReqDescription
site_idstringyesThe site identifier to update

No output schema declared.

No examples provided.

Install

How do I install the Vault MCP server?

Vault MCP runs locally as an npm package, launched with npx -y chillai-vault-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 · chillai-vault-mcp

# add to Claude Code
claude mcp add chill-ai-space-vault -- npx -y chillai-vault-mcp
Common questions

What is the Vault MCP server?

Vault MCP is listed in the public MCP registry as io.github.Chill-AI-Space/vault. MCP server for credential isolation, bots use passwords and API keys without seeing them. This page covers its npm package (chillai-vault-mcp).

Is the Vault MCP server safe to use?

Vault MCP scores 72 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. 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 Vault MCP server expose?

Vault MCP exposes 10 tools: vault_login, vault_api_request, vault_list, vault_status, vault_add, and 5 more. Their descriptions and schemas cost roughly 670 tokens of context every time the server is loaded.

Is the Vault MCP server still maintained?

Vault MCP is still listed as active in the MCP registry. We last reached this channel on 21 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 Vault MCP server under?

Vault 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 Vault MCP server?

VerifyMCP ran 15 checks on Vault MCP, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Vault MCP: Security disclosure. 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.