AgentVault
Securely stores and retrieves OpenAI API keys for autonomous agents, with TTL-bound decryption and spending budget enforcement.
Securely stores and retrieves SendGrid API keys for autonomous agents, with TTL-bound decryption and spending budget enforcement, also used for alerts.
Securely stores and retrieves Stripe API keys for autonomous agents, with TTL-bound decryption and spending budget enforcement.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
AgentVault
AI-native credential management for autonomous agents. Store API keys with column-level Fernet encryption, issue unique avk_ keys to registered agent identities, proxy decrypted values with TTL, enforce per-agent spending budgets, log every access, and expose everything as an MCP server.
Status: Production (Railway + Postgres + Stripe live)
Why
Autonomous agents need API keys to do anything useful — Stripe, OpenAI, SendGrid, your own internal services. Three bad options today:
Hardcode in the agent prompt or config. Leaks in logs, can't rotate, no audit trail.
Pass via env vars at spawn. No per-agent isolation, no budget controls, no revocation without redeploy.
Roll your own vault. Real work — encryption at rest and in transit, audit logs, key rotation, budget tracking.
AgentVault is option 3 as a service. One avk_ key per agent. Permission patterns (["stripe_*", "openai_*"]). Daily/monthly spending caps. Full access log. MCP-native so agents can vault.get_credential("stripe_key") and get a TTL-bound decrypted value back.
Related MCP server: Janee
Quickstart
Direct HTTP
import httpx
resp = httpx.post(
"https://agentvault-api-production.up.railway.app/api/v1/vault/get/stripe_key",
headers={"X-Agent-Key": "avk_..."},
params={"cost": 0.05},
)
stripe_key = resp.json()["value"]MCP (Claude Desktop / Cursor / Cline)
{
"mcpServers": {
"agentvault": {
"command": "python",
"args": ["-m", "mcp_server"],
"env": {
"AGENTVAULT_API_URL": "https://agentvault-api-production.up.railway.app",
"AGENTVAULT_AGENT_KEY": "avk_..."
}
}
}
}Then in Claude: vault.get_credential("stripe_key") returns the decrypted value.
How it works
Column-level Fernet encryption — credentials are encrypted with
VAULT_ENCRYPTION_KEYbefore they hit the database. Stronger than at-rest disk encryption alone.avk_agent keys — SHA-256 hashed at rest, never stored plaintext. Recognizable prefix likesk_live_/whsec_.Permission patterns —
["stripe_*", "openai_*"]scopes an agent without a full policy engine. fnmatch-based.Budget enforcement — daily and monthly caps per agent.
/vault/get?cost=0.05records the spend; 429 once the cap is hit.Audit log — every access (success or denied) goes into
credential_access_logswith IP, user-agent, error reason.MCP server —
mcp_server/exposeslist_credentials,get_credential,vault_status,set_budget,view_audit_logas stdio MCP tools.
Pricing
Tier | $/mo | Agents | Credentials | Audit | Rotation | Budgets | Team |
Free | $0 | 3 | 10 | – | – | – | – |
Pro | $49 | 25 | 100 | ✓ | ✓ | – | – |
Business | $149 | ∞ | ∞ | ✓ | ✓ | ✓ | ✓ |
Enterprise | $499 | ∞ | ∞ | ✓ | ✓ | ✓ | ✓ + SSO + compliance |
Self-host
git clone https://github.com/bch1212/agentvault
cd agentvault
pip install -r requirements.txt
cp .env.example .env # then fill in VAULT_ENCRYPTION_KEY and DATABASE_URL
python -m api.mainRun tests:
python -m pytest -v # 34 testsDeploy to Railway:
bash deploy.shArchitecture
api/
├── main.py # FastAPI + lifespan
├── database.py # Async SQLAlchemy (auto-rewrites postgresql:// → postgresql+asyncpg://)
├── services/
│ ├── encryption.py # Fernet encrypt/decrypt
│ ├── auth.py # avk_ key gen + SHA-256 hashing
│ ├── budget.py # Per-agent spend tracking
│ ├── audit.py # Access log
│ └── alerts.py # SendGrid alerts
├── middleware/ # X-Agent-Key + Bearer auth
└── routers/ # users, agents, credentials, vault, audit, budgets, billing
mcp_server/ # FastMCP stdio server
tests/ # 34 tests, SQLite in-memoryLicense
MIT.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Credential broker for AI agents: scoped, revocable API access with policy enforcement and audit.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server that lets AI agents call APIs without ever seeing the credentials, using a local encrypted vault and per-secret allowlist policies for HTTP requests and subprocess environment variables.1AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceSecrets management MCP server that injects credentials into API requests for AI agents, enforcing policies and logging all activity without exposing raw keys.109 npm30MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents and MCP clients to securely store, retrieve, and manage encrypted credentials without hardcoding API keys.AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceEncrypted secrets management MCP server for AI agents, enabling secure storage, retrieval, rotation, and auditing of API keys and credentials with AES-128 encryption.MIT