Compatible with every major AI agent and IDE
What is the HashiCorp Vault MCP Server?
Connect your HashiCorp Vault instance to any AI agent to automate secrets management and security operations through natural language.
What you can do
- Secrets Management — Read, write, and list KV secrets directly from your secure mounts using the KV engine.
- Dynamic Credentials — Generate on-demand credentials for Databases, AWS, and PKI certificates without manual intervention.
- Token Operations — Create, lookup, and renew tokens to manage session lifecycles and access control.
- Transit Encryption — Encrypt and decrypt data using Vault's transit engine to protect sensitive information without exposing keys.
- System Administration — Check cluster health, manage mounts, and configure auth methods or ACL policies directly.
How it works
- Subscribe to this server
- Provide your Vault Address and Token
- Start managing your infrastructure security from Claude, Cursor, or any MCP-compatible client
Who is this for?
- DevOps Engineers — automate secret rotation and infrastructure provisioning workflows.
- Security Teams — audit token accessors and manage ACL policies through conversation.
- Developers — fetch development secrets and generate local database credentials without leaving the IDE.
Built-in capabilities (50)
Login using AppRole authentication
Configure AWS root credentials
Configure a database connection
Configure Kubernetes authentication
Create or update an ACL policy
Create or update an AppRole role
Create an AWS role
Create a database role
Create a PKI role
Create a new Vault token
Create a new Transit key
Create a new Userpass user
Decrypt data using Transit engine
Delete the latest version of a KV v2 secret
Enable an audit device
Enable a new auth method
Enable a new secrets engine
Encrypt data using Transit engine
Generate a new Secret ID for an AppRole
Generate dynamic AWS credentials
Generate dynamic database credentials
Generate a new PKI root certificate
Check Vault initialization status
Generate OpenAPI V3 document of mounted backends
Check Vault system health
Login using GitHub personal access token
Initialize a new Vault cluster
Issue a new PKI certificate
Login using Kubernetes authentication
List ACL policies
List enabled audit devices
List enabled auth methods
List secrets in a KV v2 engine path
List mounted secrets engines
List token accessors (requires sudo)
Lookup a lease by ID
Lookup details about the current Vault token
Map a GitHub team to Vault policies
Read metadata for a KV v2 secret
Read a secret from KV v2 engine
Renew a lease
Renew the current Vault token
Revoke a lease
Revoke a PKI certificate
Revoke the current Vault token
Rotate a Transit key
Seal the Vault
Unseal the Vault with a key share
Login using Username and Password
Create or update a secret in KV v2 engine
Why Claude Code?
Claude Code registers HashiCorp Vault as an MCP server in a single terminal command. Once connected, Claude Code discovers all 50 tools at runtime and can call them headlessly. ideal for CI/CD pipelines, cron jobs, and automated workflows where HashiCorp Vault data drives decisions without human intervention.
- —
Single-command setup:
claude mcp addregisters the server instantly. no config files to edit or applications to restart - —
Terminal-native workflow means MCP tools integrate seamlessly into shell scripts, CI/CD pipelines, and automated DevOps tasks
- —
Claude Code runs headlessly, enabling unattended batch processing using HashiCorp Vault tools in cron jobs or deployment scripts
- —
Built by the same team that created the MCP protocol, ensuring first-class compatibility and the fastest adoption of new protocol features
HashiCorp Vault in Claude Code
HashiCorp Vault and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect HashiCorp Vault to Claude Code through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for HashiCorp Vault in Claude Code
The HashiCorp Vault MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 50 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Claude Code only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
HashiCorp Vault for Claude Code
Every tool call from Claude Code to the HashiCorp Vault MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check the remaining TTL and policies of my current session token?
Yes. Use the lookup_self_token tool. It returns the creation time, TTL, associated policies, and metadata for the token currently in use.
How do I retrieve a specific secret from a KV version 2 engine?
Use the read_kv_secret tool by providing the path to the secret. The agent will fetch the data and present the key-value pairs securely.
Is it possible to generate temporary database credentials through the agent?
Yes. If the database engine is configured, use generate_database_creds with the specific role name to receive a temporary username and password.
How do I add an MCP server to Claude Code?
Run claude mcp add <name> --transport http "<url>" in your terminal. Claude Code registers the server and discovers all tools immediately.
Can Claude Code run MCP tools in headless mode?
Yes. Claude Code supports non-interactive execution, making it ideal for scripts, cron jobs, and CI/CD pipelines that need MCP tool access.
How do I list all connected MCP servers?
Run claude mcp in your terminal to see all registered servers and their status, or type /mcp inside an active Claude Code session.
Command not found: claude
Ensure Claude Code is installed globally: npm install -g @anthropic-ai/claude-code
Connection timeout
Check your internet connection and verify the Edge URL is reachable
Explore More MCP Servers
View all →
Datadog Cloud SIEM
10 toolsManage cloud security via Datadog — search security signals, triage alerts, and audit detection rules directly from any AI agent.

NCREIF Custom Query
3 toolsInstitutional real estate data — execute custom SQL-like queries on NPI and other indices via NCREIF.

Lob
9 toolsSend physical mail programmatically with an API for postcards, letters, and checks that integrates into your digital workflows.

Adobe Customer Journey Analytics (CJA)
6 toolsOmnichannel journey insights — manage data views, connections, and reports via AI.
