Skip to main content
Glama
Keyway MCP Server

Keyway MCP Server

by keywaysh

This repository has been archived

This repository has been merged into the keywaysh/keyway monorepo.

The code now lives at packages/mcp/.

Please open all issues and pull requests in the monorepo.

Available Tools

8 tools
keyway_diffC

Compare secrets between two environments to find differences.

Inputs: env1 (required), env2 (required).

keyway_generateA

Generate a secure secret and store it directly in the vault. The value is never exposed in the conversation.

Inputs: name (required), type, length, environment.

keyway_inject_runB

Run a command with Keyway secrets injected as environment variables. Secrets are only available to this command.

Inputs: command (required), args, environment, timeout.

keyway_list_environmentsB

List available environments for the current repository vault.

Inputs: no named parameters.

keyway_list_secretsA

List all secret names in the Keyway vault for the current repository. Returns only the keys, not the values.

Inputs: environment.

keyway_scanC

Scan the codebase for potential secret leaks. Detects AWS keys, GitHub tokens, Stripe keys, private keys, and more.

Inputs: path, exclude.

keyway_set_secretB

Create or update a secret in the Keyway vault. The key must be uppercase with underscores (e.g., DATABASE_URL).

Inputs: name (required), value (required), environment.

keyway_validateB

Validate that required secrets exist in an environment. Useful for pre-deployment checks.

Inputs: environment (required), required, autoDetect, path.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: diff compares environments, generate creates secrets, inject_run executes commands, list_environments and list_secrets retrieve metadata, scan detects leaks, set_secret modifies data, and validate checks completeness. The descriptions make it impossible to confuse any two tools.

    Naming Consistency5/5

    All tools follow a consistent 'keyway_verb_noun' pattern with snake_case throughout (e.g., keyway_diff, keyway_generate, keyway_inject_run). This predictable naming scheme makes it easy for agents to understand and select the right tool based on its function.

    Tool Count5/5

    With 8 tools, this server is well-scoped for secret management, covering essential operations like listing, setting, generating, validating, scanning, and injecting secrets, as well as environment comparison. Each tool serves a unique and necessary function without redundancy.

    Completeness5/5

    The toolset provides complete coverage for secret management workflows: CRUD operations (list, set, generate), environment handling (list, diff), security (scan, validate), and runtime integration (inject_run). There are no obvious gaps, enabling agents to handle the full lifecycle of secrets in this domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      A cross-platform secrets manager that stores named credential sets in the system keychain and injects them as environment variables, enabling secure secret management for AI coding assistants and CLI tools.
      5
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables agents to securely use credentials for GitHub, Cloudflare, OpenAI, Stripe, and xAI without ever reading the secret values, including credential health, rotation, and audit features.
      -
    • A
      license
      C
      quality
      C
      maintenance
      Enables AI agents to securely store and manage encrypted secrets locally while using them indirectly through environment-variable injection or file writes, so plaintext values never enter the agent's context.
      8
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI coding agents to securely inject API keys and secrets into environment files, configs, or commands without the agent ever seeing the secret values.
      10 npm
      MIT