
Secure Vault
io.github.mdfifty50-boopPublished by GitHub account mdfifty50-boopv0.1.1Updated Oct 24, 2026
Encrypted secrets and credential management for agents
Overview
A local MCP server that stores secrets encrypted, issues short-lived scoped tokens, and injects credentials into request templates so the assistant never sees a
- What you can do
- Store encrypted secrets with optional rotation policies and list stored secret names and metadata without values. Issue short-lived, scoped agent tokens for a service, and rotate a service's secrets, invalidating old tokens. Inject a secret into a request template server-side using a token ID. Scan pasted config text for exposed credentials such as cloud, API, chat and payment keys. Review an audit trail of secret access over a time range, filtered by agent or secret.
- When to use it
- Useful when an assistant needs to call APIs with credentials but should not handle plaintext values, and when you want token scoping, rotation and an access audit trail. Also handy for checking config files for leaked keys before committing them.
- Requirements
- Runs locally over stdio, typically launched with npx from the npm package secure-vault-mcp; Node.js is needed. No accounts, API keys, environment variables or headers are declared. Secrets are held in memory only for the server session lifetime.
Installation
In SourceWeft
- Open Secure Vault in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
secure-vault-mcp
MCP server for agent-native secrets management. 24,008 secrets have been found in MCP config files on public GitHub. This server solves that.
Agents need secrets to call APIs, but they shouldn't see raw values. secure-vault-mcp stores secrets encrypted with AES-256-GCM, issues short-lived scoped tokens, and injects secrets into requests server-side so the agent never handles plaintext credentials.
Install
Claude Desktop
Add to claude_desktop_config.json:
From source
Tools
store_secret
Store an encrypted secret with optional rotation policy.
get_agent_token
Issue a short-lived, scoped token. The agent receives an opaque token ID, never the raw secret.
rotate_secrets
Rotate all secrets for a service. Old tokens are invalidated.
audit_secret_access
View who accessed what secrets over a time range.
scan_config_for_leaks
Scan config text for exposed secrets. Detects AWS keys, GitHub tokens, OpenAI/Anthropic keys, Slack tokens, Stripe keys, private key blocks, bearer tokens, and generic credentials using 12 regex patterns.
inject_secret_to_request
Return a request with the secret injected server-side. The agent provides a template with {{SECRET}} placeholder and a valid token ID.
Resources
Usage Pattern
Security Model
- Secrets encrypted at rest with AES-256-GCM using a server-generated key
- Agents receive opaque token IDs, never raw secret values
- Tokens are scoped (read/write/admin) and time-limited (default 5 minutes)
- Token rotation invalidates all outstanding tokens for the rotated secret
- Full audit trail of every store, token issuance, and injection
- In-memory storage — secrets exist only for the server session lifetime
Tests
License
MIT
Source: README.md at commit 8b3aff4
Tools
0Version history
1- v0.1.1LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.