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

io.github.juanisidoro/securecode

NPM · @SECURECODE/MCP-SERVER · SCANNED AUG 3

Secrets vault for Claude Code with audit logs, access rules, and AES-256 encryption.

+23 this week 69 Trust /100
Trust breakdown (6 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 →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability77
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1370 tokens (~80/item across 17 items; 17 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
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
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @securecode/mcp-server

# add to Claude Code
claude mcp add juanisidoro-securecode -- npx -y @securecode/mcp-server
# add to Codex CLI
codex mcp add juanisidoro-securecode -- npx -y @securecode/mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "juanisidoro-securecode": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@securecode/mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add juanisidoro-securecode --command npx --arg -y --arg @securecode/mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  juanisidoro-securecode:
    command: "npx"
    args: ["-y", "@securecode/mcp-server"]
// mcp.json
{
  "mcpServers": {
    "juanisidoro-securecode": {
      "command": "npx",
      "args": [
        "-y",
        "@securecode/mcp-server"
      ]
    }
  }
}
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.

  • 3 Aug 26 +3
    • Stability: unverified → 0.23 functional
  • 2 Aug 26 +45
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Tool coverage: 100 → unverified functional
    • Security disclosure: fail → unverified functional
    • Schema quality: unverified → excellent functional
    • License: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Licence: MIT functional
  • 31 Jul 26 −25
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 +19
    • Dependency health: partial → unverified functional
    • Tool coverage: unverified → 100 functional
  • 28 Jul 26 −19
    • Tool coverage: 100 → unverified functional
    • Dependency health: unverified → partial functional
    • First check of Schema quality: unverified functional
  • 27 Jul 26 46

    First indexed and scored.

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 3 Aug 2026 · Analysed npm/@securecode/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 17 exposed · ~1,370 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.

Tool Tokens
byebye ~40

End your work session. Locks the session, cleans up all injected secrets from disk, and says goodbye. Use this when you finish working for the day.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

create-secret ~148

Create a new secret. Secrets with the same name can coexist if they have different env tags.

NameTypeReqDescription
descriptionstringHuman-readable description of what this secret is for
domainstringAssociated domain for browser extension, e.g. "api.stripe.com"
namestringyesName for the secret (e.g. STRIPE_SECRET_KEY)
tagsobjectTags as key:value pairs, e.g. { "env": "production", "project": "acme" }
ttlHoursnumberTime-to-live in hours. Omit for permanent (no expiry)
valuestringyesThe secret value to encrypt and store

No output schema declared.

No examples provided.

delete-secret ~49

Delete a secret (soft delete, can be recovered)

NameTypeReqDescription
namestringyesThe name of the secret to delete
tagsobjectFilter tags to disambiguate same-name secrets

No output schema declared.

No examples provided.

export-env ~66

Export all secrets as .env or CSV format. Returns the full content with decrypted values.

NameTypeReqDescription
formatstringExport format: "env" (default) or "csv"
tagsobjectFilter by tags, e.g. { "env": "production" }

No output schema declared.

No examples provided.

get-active-rules ~42

List active MCP access rules. Read-only — rules can only be created or modified from the dashboard. Use this to understand why access to a secret was blocked.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get-secret ~170

Get a secret by name. By default, injects the value into a local file so it never appears in the AI conversation. Use reveal:true to see the raw value (audited as conscious action). Use cleanup:true to remove all injected secrets from disk.

NameTypeReqDescription
cleanupbooleanIf true, removes all injected secret files from disk
namestringThe exact name of the secret (e.g. STRIPE_SECRET_KEY)
revealbooleanIf true, returns the raw value in the conversation (audited as reveal). Default: false (inject mode — value written to local file, never shown)
tagsobjectFilter tags to disambiguate same-name secrets, e.g. { "env": "production", "project": "acme" }

No output schema declared.

No examples provided.

get-status ~43

Get your SecureCodeHQ account status: plan, usage limits, secrets count, and MCP server version. Useful to check remaining capacity and verify the server is up to date.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

help ~52

Get SecureCode documentation: available tools, usage patterns, SDK setup, and common workflows. Use this to understand how to help the user with SecureCode.

NameTypeReqDescription
topicstringDocumentation topic. Default: "all"

No output schema declared.

No examples provided.

import-env ~52

Import secrets from .env files into SecureCode. For security, .env import must be done through the web interface — the AI agent never sees secret values during import. This tool provides the link to the import page.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list-secrets ~56

List all available secrets with their tags and expiration status. Returns names and metadata, never values.

NameTypeReqDescription
tagsobjectFilter by tags, e.g. { "env": "production", "project": "acme" }

No output schema declared.

No examples provided.

onboard ~265

Start or continue the SecureCode onboarding. Guides the user through signup, .env import, API key creation, MCP configuration, and optional SDK setup — all from Claude Code. Call this tool multiple times to progress through the steps.

NameTypeReqDescription
actionstringAction to perform. "start" (default) progresses through signup/import steps. "configure-auto" lets the agent write the API key to the MCP config file automatically. "configure-manual" shows the API k…
configPathstringPath to the MCP config file (.mcp.json or claude.json). Only needed for configure-auto if auto-detection fails.
selectedEnvstringEnvironment tag selected by user (from select-secrets action). Used to configure .securecoderc.
selectedProjectstringProject tag selected by user (from select-secrets action). Used to configure .securecoderc.

No output schema declared.

No examples provided.

renew-secret ~79

Renew an expired secret or change its TTL. Use this to reactivate expired secrets or extend expiration.

NameTypeReqDescription
namestringyesThe name of the secret to renew
tagsobjectFilter tags to disambiguate same-name secrets
ttlHoursnumberNew TTL in hours. Omit to make permanent (no expiry)

No output schema declared.

No examples provided.

security-check ~38

Analyze the project for security issues after SecureCode setup. Returns a list of actions the agent MUST execute to protect secrets. Call this after SDK installation.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

session-status ~29

Check the current session status: active or sleeping, scope restrictions, and time remaining before auto-sleep.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

sleep-session ~32

Lock the session immediately. All secret access will be blocked until you wake it again. Use this when you finish working.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

update-secret ~120

Update an existing secret's value, description, tags, or domain. Only provided fields are changed.

NameTypeReqDescription
descriptionstringNew description
domainstringNew domain
filterTagsobjectFilter tags to disambiguate same-name secrets (different from the "tags" field which sets new tags)
namestringyesThe name of the secret to update
tagsobjectNew tags (replaces ALL existing tags)
valuestringNew secret value (omit to keep current value)

No output schema declared.

No examples provided.

wake-session ~89

Wake (unlock) the session to start accessing secrets. Optionally restrict access to specific tag scope and set auto-sleep timer.

NameTypeReqDescription
autoSleepMinutesintegerMinutes of inactivity before auto-sleep. Default: 120 (2 hours).
scopearrayTag filters to restrict which secrets are accessible. E.g. [{project:"acme"}]. Omit for all secrets.

No output schema declared.

No examples provided.