Triage errors, inspect traces, and query events from Sentry.
- Home
- Top MCPs for Security
- HashiCorp Vault
HashiCorp Vault
Read dynamic and static secrets from HashiCorp Vault inside agent workflows.
Quick answer
What it does
Reads from HashiCorp Vault — KV v2 secrets, dynamic database credentials, and PKI issuance — without leaking values into the conversation.
Best for
- Dynamic database credential issuance
- KV v2 secret reads
- PKI certificate issuance
- Per-token scoped agent access
Not for
- Teams without an existing Vault deployment
- Single-developer secret stores
Setup recipe
Pick your client, then follow the three steps.
- 1
Install
claude_desktop_config.jsonjson{ "mcpServers": { "vault": { "command": "go", "args": [ "install", "github.com/hashicorp/mcp-server-vault@latest" ], "env": { "VAULT_ADDR": "${VAULT_ADDR}", "VAULT_TOKEN": "${VAULT_TOKEN}", "VAULT_NAMESPACE": "${VAULT_NAMESPACE}" } } } }Paste under mcpServers. Fully quit and reopen Claude after editing.
CLI or .mcp.jsonshell# export VAULT_ADDR=https://vault.example.com # export VAULT_TOKEN=hvs.… # export VAULT_NAMESPACE=admin (Enterprise only) claude mcp add vault -- go install github.com/hashicorp/mcp-server-vault@latestRun from your repo. Commit .mcp.json to share with your team.
.cursor/mcp.jsonjson{ "mcpServers": { "vault": { "command": "go", "args": [ "install", "github.com/hashicorp/mcp-server-vault@latest" ], "env": { "VAULT_ADDR": "${VAULT_ADDR}", "VAULT_TOKEN": "${VAULT_TOKEN}", "VAULT_NAMESPACE": "${VAULT_NAMESPACE}" } } } }Global path: ~/.cursor/mcp.json. Reload window after editing.
.vscode/mcp.jsonjsonc{ "servers": { "vault": { "command": "go", "args": [ "install", "github.com/hashicorp/mcp-server-vault@latest" ], "env": { "VAULT_ADDR": "${VAULT_ADDR}", "VAULT_TOKEN": "${VAULT_TOKEN}", "VAULT_NAMESPACE": "${VAULT_NAMESPACE}" } } } }VS Code uses the "servers" key (not "mcpServers").
~/.codeium/windsurf/mcp_config.jsonjson{ "mcpServers": { "vault": { "command": "go", "args": [ "install", "github.com/hashicorp/mcp-server-vault@latest" ], "env": { "VAULT_ADDR": "${VAULT_ADDR}", "VAULT_TOKEN": "${VAULT_TOKEN}", "VAULT_NAMESPACE": "${VAULT_NAMESPACE}" } } } }Open via Cascade → hammer icon → Configure.
cline_mcp_settings.jsonjson{ "mcpServers": { "vault": { "command": "go", "args": [ "install", "github.com/hashicorp/mcp-server-vault@latest" ], "env": { "VAULT_ADDR": "${VAULT_ADDR}", "VAULT_TOKEN": "${VAULT_TOKEN}", "VAULT_NAMESPACE": "${VAULT_NAMESPACE}" } } } }Open via the Cline sidebar → MCP Servers → Edit.
~/.continue/config.jsonjson{ "experimental": { "modelContextProtocolServers": [ { "transport": { "type": "stdio", "command": "go", "args": [ "install", "github.com/hashicorp/mcp-server-vault@latest" ], "env": { "VAULT_ADDR": "${VAULT_ADDR}", "VAULT_TOKEN": "${VAULT_TOKEN}", "VAULT_NAMESPACE": "${VAULT_NAMESPACE}" } } } ] } }Continue uses modelContextProtocolServers with a transport block.
~/.codex/config.tomlshell# ~/.codex/config.toml [mcp_servers.vault] command = "go" args = [ "install", "github.com/hashicorp/mcp-server-vault@latest", ] env = { VAULT_ADDR = "${VAULT_ADDR}", VAULT_TOKEN = "${VAULT_TOKEN}", VAULT_NAMESPACE = "${VAULT_NAMESPACE}" }Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.
~/.config/zed/settings.jsonjsonc{ "context_servers": { "vault": { "command": { "path": "go", "args": [ "install", "github.com/hashicorp/mcp-server-vault@latest" ] }, "env": { "VAULT_ADDR": "${VAULT_ADDR}", "VAULT_TOKEN": "${VAULT_TOKEN}", "VAULT_NAMESPACE": "${VAULT_NAMESPACE}" } } } }Zed calls them "context_servers". Settings live-reload on save.
ChatGPT → Apps directorynoneHashiCorp Vault doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.
- 2
Set required secrets
Set
VAULT_ADDR,VAULT_TOKEN,VAULT_NAMESPACEin your shell environment before launching your MCP client. - 3
Try a minimum working prompt
Minimum working prompt pending verification. Try any prompt from the MCP’s README once installed.
Tools & permissions
| Tool | Description | Args | Side effects |
|---|---|---|---|
kv_v2_get | Read a KV v2 secret at a path. | mount: string, path: string | Read |
database_creds | Request dynamic database credentials. | mount: string, role: string | Read |
pki_issue | Issue a certificate from a PKI role. | mount: string, role: string, common_name: string | Write |
Security & scope
- Access scope
- Read-only
- Sandbox
- Vault token in env. All capability checks happen at the Vault side — the MCP is a thin client. Treat the token as a high-value credential and prefer short-lived tokens issued at session start.
- Gotchas
- A wildcard policy on the agent token defeats the entire purpose. Mint narrowly-scoped tokens, one per workflow.
- Dynamic credentials revoke when their TTL expires — design the workflow around that lifetime.
- Audit logs on the Vault side are your forensic trail. Make sure they are enabled and shipped off-host.
Agent prompt pack
— copy into Claude, Cursor, or ChatGPT.Recommend the best MCP servers for [task: e.g. security work] in [client: Claude]. Constraints: - Prefer tools that are [official | open-source | read-only] — pick what matters for my use case. - Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport]. - Return at most 3 picks, ranked. For each pick include: 1. One-sentence rationale. 2. The ready-to-paste install snippet for my client. 3. Any required secrets I need to create before installing. Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-security
Compare HashiCorp Vault MCP vs [1Password MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"]. Judge them on: - Setup time and complexity (what a new user hits first). - Auth model (none / API key / OAuth 2.1) and credential risk. - Transport (stdio / Streamable HTTP / SSE) and where the server runs. - Required secrets and the blast radius if they leak. - Operational risk in an unattended agent loop. - Which one is "good enough" for a weekend prototype vs. production. End with one sentence: which should I pick for my scenario, which is: [my scenario]. References: - https://top-mcps.com/mcp/vault - top-mcps.com listing for 1Password
Install the HashiCorp Vault MCP server for my [client: Claude] at the default config path for that client. Use the exact install snippet published at https://top-mcps.com/mcp/vault (fetch https://top-mcps.com/mcp/vault.json for the canonical server.json if you can read URLs). Before finishing: 1. Create the required secrets (VAULT_ADDR, VAULT_TOKEN, VAULT_NAMESPACE) and put them in the appropriate env block — do not hard-code them. 2. Restart or reload the client so it picks up the new server. 3. Verify the server is connected (green / running state) and at least one tool is listed. 4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry. Confirm when done and list the tools the server now exposes.
Frequently asked questions
What changed
— 2 updates tracked.Refreshed install snippets and fact sheet; verified for 2026.
Initial directory listing.
More Security MCPs
Other tools in the same category worth evaluating.
Manage Workers, R2 buckets, DNS, and edge policies on Cloudflare.
Inject 1Password secrets into an AI agent's tool calls without exposing them in chat.
Compared with HashiCorp Vault
Side-by-side breakdowns for the choices people most often weigh against this MCP.
Exploring Top MCPs for Security? See all Security MCPs →