zero-trust-mcp
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.
Zero-Trust Model Context Protocol (MCP) Integration Server
A lightweight, local-first Model Context Protocol (MCP) server built in Python that enforces zero-trust data privacy for AI agents.
By intercepting tool calls prior to cloud transmission, this server encrypts payloads locally using AES-256-GCM and persists them to a local SQLite database. Sensitive contextual data stays encrypted at rest, gated behind an access token, and every access attempt is actively logged.
π Key Features
Model Context Protocol (MCP) Native: Exposes secure tools over standard I/O (
stdio) via FastMCP.Zero-Trust Encryption: AES-256-GCM with random 96-bit nonces for authenticated local encryption.
Password-Derived Keys: The encryption key is derived from a master password via
scrypt, using a salt persisted in the database β ensuring the vault survives server restarts.Access Control: Every tool call (
secure_store,secure_retrieve,audit_recent) requires a valid HMAC access token, verified in constant time to resist timing attacks.Audit Logging: Every store/retrieve attempt β successful or not β is written to an append-only
audit_logtable to ensure complete observability.Live Security Dashboard: Includes a lightweight FastAPI web interface to visually monitor the SQLite audit trail in real-time.
AI Client Simulator: An async Python client (
ai_client.py) demonstrating programmatic tool-calling over the MCP standard, including rejected-token handling.
Related MCP server: llm-localfirst
π Repository Structure
βββ crypto_engine.py # AES-256-GCM + scrypt key derivation
βββ access_control.py # Constant-time access token verification
βββ audit_log.py # Append-only audit trail logic
βββ mcp_server.py # FastMCP protocol server & SQLite DB logic
βββ ai_client.py # Async AI Agent simulator acting as an MCP client
βββ dashboard.py # FastAPI web UI for visualizing security logs
βββ test_mcp.py # Unit tests for crypto, access control, and audit logs
βββ .env.example # Template for required environment variables
βββ .gitignore # Git ignore rules
βββ requirements.txt # Core dependenciesπ§ Threat Model
What this protects against:
Data at Rest Theft: Secrets sitting in vault.db are unreadable if the file alone is stolen (they're AES-256-GCM ciphertext, keyed off a password never written to disk).
Tampered Ciphertext: GCM is authenticated β tampering causes decryption to fail loudly rather than silently returning garbage.
Unauthorized Tool Calls: No access token, no data.
What this does not protect against:
A compromised local environment that already holds the master password and access token in memory.
Multi-tenant isolation β right now there is one shared secret vault, not per-agent scoped secrets.
Network-level threats β this is a local stdio server, not exposed over a network by default.
π οΈ Setup & Usage
Install Dependencies
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txtConfigure Environment Create a .env file in the root directory and add your passwords (the scripts will auto-load this using python-dotenv):
ZTMCP_MASTER_PASSWORD=your_secure_password
ZTMCP_ACCESS_TOKEN=your_secure_tokenRun the AI Client Simulator Watch the automated client connect to the MCP server, authenticate, and securely process data.
python ai_client.pyView the Audit Dashboard Launch the FastAPI server to view real-time access logs.
uvicorn dashboard:app --reload --port 8000
# Open http://127.0.0.1:8000 in your browserRun the Test Suite
python -m unittest test_mcp.py -vπ Roadmap
Per-Agent Identity: Transition from one shared token to agent-specific tokens to log which agent accessed what.
Secret Expiry / TTL: Allow secure_store to take an optional expires_at timestamp.
Rate Limiting: Throttle brute-force loops against secure_retrieve.
Key Rotation: Build a rotate_key tool that re-encrypts all secrets under a new password/salt.
OS Keyring Integration: Swap SQLite salt storage for OS keyring integration (e.g. via the keyring package).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
This server cannot be deployed
Maintenance
Related MCP Connectors
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server for secureFlows: token-free URL builders and integration-linting tools for AI agents.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA local-first MCP memory server providing persistent, searchable memory for AI agents, powered by SQLite.1 npm1Apache 2.0
- AlicenseNot gradedqualityCmaintenanceA local-first LLM routing MCP server that keeps sensitive data on your own models, with fail-closed privacy and manager-worker delegation, exposing route and complete tools to any MCP client.72 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceLocal-first MCP server that lets AI agents query their own LLM call history as a branchable DAG and offload conversation context into immutable, AES-256-GCM-encrypted capsules β restorable in full or per segment, crypto-shreddable, with RAID-style replication. 12 tools, no API keys, no cloud.79 npm3MIT
- AlicenseNot gradedqualityBmaintenanceLocal-first MCP server providing a shared, AES-256-GCM encrypted SQLite ledger of structured user state (stack, projects, preferences) that any MCP-aware tool can read/write, with user-held keys and optional zero-knowledge sync.1Apache 2.0