Keyway MCP Server
Provides GitHub-native secret management, allowing AI assistants to validate environment configurations, scan for leaked GitHub tokens, and manage repository-specific secrets without exposing them in conversation history.
Supports the detection of leaked Slack webhooks during automated security scans of the codebase.
Enables the detection of leaked Stripe API keys within a codebase and validates that required Stripe credentials are present in specific deployment environments.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Keyway MCP Server Generate a new JWT secret for production"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This repository has been archived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 toolskeyway_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
Scored across 8 tools
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.
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.
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.
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
Related MCP Connectors
Secrets for developers and agents—secure context and workflows without exposing secret values.
Encrypted secret store and rotation for autonomous agent credentials
Password vault for AI agents with scoped, user-approved access
A secret store for AI agents: the agent never sees the plaintext.
Related MCP Servers
- AlicenseAqualityBmaintenanceA 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.5MIT
- FlicenseNot gradedqualityBmaintenanceEnables 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.-
- AlicenseCqualityCmaintenanceEnables 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.8MIT
- AlicenseNot gradedqualityCmaintenanceEnables 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 npmMIT